{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/image-generation","name":"Image Generation","slug":"image-generation","description_markdown":"**Image Generation** (synthesis) is the task of generating new images from an existing dataset.\r\n\r\n- **Unconditional generation** refers to generating samples unconditionally from the dataset, i.e. $p(y)$\r\n- **[Conditional image generation](/task/conditional-image-generation)** (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.\r\n\r\nIn this section, you can find state-of-the-art leaderboards for **unconditional generation**. For conditional  generation, and other types of image generations, refer to the subtasks.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [StyleGAN](https://github.com/NVlabs/stylegan) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Medical","url":"/area/medical"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":6689,"papers_with_code":3102,"benchmarks":93,"benchmark_tables_in_archive":93,"benchmark_tables_shown":93,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":79,"subtasks":23,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/image-generation-on-imagenet-256x256","slug":"image-generation-on-imagenet-256x256","dataset":"ImageNet 256x256","dataset_url":null,"rows_in_archive":94,"metrics":["FID","Inception score","NFE"],"first_row_in_archive_order":{"model":"SiT-XL/2 + UCGM-S (E2E-VAE + 40 sampling steps + CFG)","paper_title":"Unified Continuous Generative Models","paper_url":"/paper/unified-continuous-generative-models","paper_date":"2025-05-12","arxiv_id":"2505.07447","code_links":[{"title":"LINs-Lab/UCGM","url":"https://github.com/LINs-Lab/UCGM"}],"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":7,"n_instrument":12,"n_unverified":2,"n_honours":3,"n_violates":1,"n_no_contract":3,"n_pointer_only":4,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 1 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/unified-continuous-generative-models#ran","syntology_url":"https://syntology.ai/paper/2505.07447","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07447"}},"official":{"repos":["LINs-Lab/UCGM"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-cifar-10","slug":"image-generation-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":78,"metrics":["FID","IS","NFE"],"first_row_in_archive_order":{"model":"GMem","paper_title":"Generative Modeling with Explicit Memory","paper_url":"/paper/generative-modeling-with-explicit-memory","paper_date":"2024-12-11","arxiv_id":"2412.08781","code_links":[{"title":"lins-lab/gmem","url":"https://github.com/lins-lab/gmem"}],"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":5,"n_instrument":8,"n_unverified":2,"n_honours":3,"n_violates":1,"n_no_contract":1,"n_pointer_only":15,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 1 violated, 1 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/generative-modeling-with-explicit-memory#ran","syntology_url":"https://syntology.ai/paper/2412.08781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.08781"}},"official":{"repos":["lins-lab/gmem"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-imagenet-64x64","slug":"image-generation-on-imagenet-64x64","dataset":"ImageNet 64x64","dataset_url":null,"rows_in_archive":65,"metrics":["FID","Bits per dim","NFE","Inception Score","KID"],"first_row_in_archive_order":{"model":"SIMS","paper_title":"Self-Improving Diffusion Models with Synthetic Data","paper_url":"/paper/self-improving-diffusion-models-with","paper_date":"2024-08-29","arxiv_id":"2408.16333","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-generation-on-imagenet-512x512","slug":"image-generation-on-imagenet-512x512","dataset":"ImageNet 512x512","dataset_url":null,"rows_in_archive":52,"metrics":["FID","NFE","Inception score"],"first_row_in_archive_order":{"model":"EDM2-L + DDO (SD-VAE, 25 steps, DPM-Solver-v3)","paper_title":"Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator","paper_url":"/paper/direct-discriminative-optimization-your-1","paper_date":"2025-03-03","arxiv_id":"2503.01103","code_links":[{"title":"nvlabs/ddo","url":"https://github.com/nvlabs/ddo"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-ffhq-256-x-256","slug":"image-generation-on-ffhq-256-x-256","dataset":"FFHQ 256 x 256","dataset_url":"/dataset/ffhq","rows_in_archive":51,"metrics":["FID","FD","Precision","Recall","bits/dimension","Density","Coverage"],"first_row_in_archive_order":{"model":"StyleSAN-XL","paper_title":"SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer","paper_url":"/paper/adversarially-slicing-generative-networks","paper_date":"2023-01-30","arxiv_id":"2301.12811","code_links":[{"title":"sony/san","url":"https://github.com/sony/san"}],"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarially-slicing-generative-networks#ran","syntology_url":"https://syntology.ai/paper/2301.12811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12811"}},"official":{"repos":["sony/san"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-celeba-64x64","slug":"image-generation-on-celeba-64x64","dataset":"CelebA 64x64","dataset_url":"/dataset/celeba","rows_in_archive":39,"metrics":["FID","bits/dimension","Precision","Recall","FID_CLIP","Model Size (MB)"],"first_row_in_archive_order":{"model":"DDPM-IP","paper_title":"Input Perturbation Reduces Exposure Bias in Diffusion Models","paper_url":"/paper/input-perturbation-reduces-exposure-bias-in","paper_date":"2023-01-27","arxiv_id":"2301.11706","code_links":[{"title":"forever208/ddpm-ip","url":"https://github.com/forever208/ddpm-ip"}],"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/input-perturbation-reduces-exposure-bias-in#ran","syntology_url":"https://syntology.ai/paper/2301.11706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11706"}},"official":{"repos":["forever208/ddpm-ip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-imagenet-32x32","slug":"image-generation-on-imagenet-32x32","dataset":"ImageNet 32x32","dataset_url":null,"rows_in_archive":35,"metrics":["FID","bpd","Inception score"],"first_row_in_archive_order":{"model":"PaGoDA","paper_title":"PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher","paper_url":"/paper/pagoda-progressive-growing-of-a-one-step","paper_date":"2024-05-23","arxiv_id":"2405.14822","code_links":[{"title":"sony/pagoda","url":"https://github.com/sony/pagoda"}],"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":1,"n_instrument":14,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 14 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/pagoda-progressive-growing-of-a-one-step#ran","syntology_url":"https://syntology.ai/paper/2405.14822","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14822"}},"official":{"repos":["sony/pagoda"],"state":"official (archive's flag): 15 ran","n_ran":15,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-lsun-bedroom-256-x-256","slug":"image-generation-on-lsun-bedroom-256-x-256","dataset":"LSUN Bedroom 256 x 256","dataset_url":"/dataset/lsun","rows_in_archive":32,"metrics":["FID","FD","Precision","Recall","FID-10k-training-steps","NFE"],"first_row_in_archive_order":{"model":"Diffusion ProjectedGAN","paper_title":"Diffusion-GAN: Training GANs with Diffusion","paper_url":"/paper/diffusion-gan-training-gans-with-diffusion","paper_date":"2022-06-05","arxiv_id":"2206.02262","code_links":[{"title":"Zhendong-Wang/Diffusion-GAN","url":"https://github.com/Zhendong-Wang/Diffusion-GAN"},{"title":"zhendong-wang/prompt-diffusion","url":"https://github.com/zhendong-wang/prompt-diffusion"},{"title":"mingyuanzhou/sid-lsg","url":"https://github.com/mingyuanzhou/sid-lsg"},{"title":"jegzheng/truncated-diffusion-probabilistic-models","url":"https://github.com/jegzheng/truncated-diffusion-probabilistic-models"}],"syntology":{"n":18,"n_ran":15,"n_constructed":1,"n_ran_checked":6,"n_instrument":9,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":8,"phrase":"15 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diffusion-gan-training-gans-with-diffusion#ran","syntology_url":"https://syntology.ai/paper/2206.02262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02262"}},"official":{"repos":["Zhendong-Wang/Diffusion-GAN"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/image-generation-on-stl-10","slug":"image-generation-on-stl-10","dataset":"STL-10","dataset_url":"/dataset/stl-10","rows_in_archive":31,"metrics":["FID","Inception score","Model Size (MB)","Recall","NFE"],"first_row_in_archive_order":{"model":"Diffusion ProjectedGAN","paper_title":"Diffusion-GAN: Training GANs with Diffusion","paper_url":"/paper/diffusion-gan-training-gans-with-diffusion","paper_date":"2022-06-05","arxiv_id":"2206.02262","code_links":[{"title":"Zhendong-Wang/Diffusion-GAN","url":"https://github.com/Zhendong-Wang/Diffusion-GAN"},{"title":"zhendong-wang/prompt-diffusion","url":"https://github.com/zhendong-wang/prompt-diffusion"},{"title":"mingyuanzhou/sid-lsg","url":"https://github.com/mingyuanzhou/sid-lsg"},{"title":"jegzheng/truncated-diffusion-probabilistic-models","url":"https://github.com/jegzheng/truncated-diffusion-probabilistic-models"}],"syntology":{"n":18,"n_ran":15,"n_constructed":1,"n_ran_checked":6,"n_instrument":9,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":8,"phrase":"15 ran (of which 1 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 9 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diffusion-gan-training-gans-with-diffusion#ran","syntology_url":"https://syntology.ai/paper/2206.02262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.02262"}},"official":{"repos":["Zhendong-Wang/Diffusion-GAN"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/image-generation-on-lsun-churches-256-x-256","slug":"image-generation-on-lsun-churches-256-x-256","dataset":"LSUN Churches 256 x 256","dataset_url":"/dataset/lsun","rows_in_archive":27,"metrics":["FID","Clean-FID (trainfull)","NFE","Recall","clean-FID"],"first_row_in_archive_order":{"model":"Projected GAN","paper_title":"Projected GANs Converge Faster","paper_url":"/paper/projected-gans-converge-faster","paper_date":"2021-11-01","arxiv_id":"2111.01007","code_links":[{"title":"autonomousvision/projected_gan","url":"https://github.com/autonomousvision/projected_gan"},{"title":"dome272/ProjectedGAN-pytorch","url":"https://github.com/dome272/ProjectedGAN-pytorch"},{"title":"tsubota-kouga/ProjectedGAN","url":"https://github.com/tsubota-kouga/ProjectedGAN"}],"syntology":{"n":49,"n_ran":38,"n_constructed":14,"n_ran_checked":20,"n_instrument":18,"n_unverified":11,"n_honours":3,"n_violates":0,"n_no_contract":17,"n_pointer_only":6,"phrase":"38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/projected-gans-converge-faster#ran","syntology_url":"https://syntology.ai/paper/2111.01007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01007"}},"official":{"repos":["autonomousvision/projected_gan"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-imagenet-128x128","slug":"image-generation-on-imagenet-128x128","dataset":"ImageNet 128x128","dataset_url":null,"rows_in_archive":23,"metrics":["FID","IS","Precision","Recall"],"first_row_in_archive_order":{"model":"SiD2","paper_title":"Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion","paper_url":"/paper/simpler-diffusion-sid2-1-5-fid-on-imagenet512","paper_date":"2024-10-25","arxiv_id":"2410.19324","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-generation-on-ffhq-1024-x-1024","slug":"image-generation-on-ffhq-1024-x-1024","dataset":"FFHQ 1024 x 1024","dataset_url":"/dataset/ffhq","rows_in_archive":20,"metrics":["FID","bits/dimension"],"first_row_in_archive_order":{"model":"StyleSAN-XL","paper_title":"SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer","paper_url":"/paper/adversarially-slicing-generative-networks","paper_date":"2023-01-30","arxiv_id":"2301.12811","code_links":[{"title":"sony/san","url":"https://github.com/sony/san"}],"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarially-slicing-generative-networks#ran","syntology_url":"https://syntology.ai/paper/2301.12811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12811"}},"official":{"repos":["sony/san"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-celeba-hq-256x256","slug":"image-generation-on-celeba-hq-256x256","dataset":"CelebA-HQ 256x256","dataset_url":"/dataset/celeba-hq","rows_in_archive":19,"metrics":["FID","bits/dimension","Recall","NFE","Precision","clean-FID"],"first_row_in_archive_order":{"model":"RDM","paper_title":"Relay Diffusion: Unifying diffusion process across resolutions for image synthesis","paper_url":"/paper/relay-diffusion-unifying-diffusion-process-1","paper_date":"2023-09-04","arxiv_id":"2309.03350","code_links":[{"title":"THUDM/RelayDiffusion","url":"https://github.com/THUDM/RelayDiffusion"}],"syntology":{"n":17,"n_ran":14,"n_constructed":0,"n_ran_checked":6,"n_instrument":8,"n_unverified":3,"n_honours":4,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 4 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/relay-diffusion-unifying-diffusion-process-1#ran","syntology_url":"https://syntology.ai/paper/2309.03350","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03350"}},"official":{"repos":["THUDM/RelayDiffusion"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-celeba-256x256","slug":"image-generation-on-celeba-256x256","dataset":"CelebA 256x256","dataset_url":"/dataset/celeba","rows_in_archive":17,"metrics":["bpd","FID","bpd (8-bits)"],"first_row_in_archive_order":{"model":"Efficient-VDVAE","paper_title":"Efficient-VDVAE: Less is more","paper_url":"/paper/efficient-vdvae-less-is-more","paper_date":"2022-03-25","arxiv_id":"2203.13751","code_links":[{"title":"Rayhane-mamah/Efficient-VDVAE","url":"https://github.com/Rayhane-mamah/Efficient-VDVAE"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-mnist","slug":"image-generation-on-mnist","dataset":"MNIST","dataset_url":"/dataset/mnist","rows_in_archive":15,"metrics":["bits/dimension","FID","Precision","Recall","PSNR","SSIM"],"first_row_in_archive_order":{"model":"Locally Masked PixelCNN (8 orders)","paper_title":"Locally Masked Convolution for Autoregressive Models","paper_url":"/paper/locally-masked-convolution-for-autoregressive","paper_date":"2020-06-22","arxiv_id":"2006.12486","code_links":[{"title":"ajayjain/lmconv","url":"https://github.com/ajayjain/lmconv"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-wise","slug":"image-generation-on-wise","dataset":"WISE","dataset_url":"/dataset/wise","rows_in_archive":14,"metrics":["Overall","Cultural","Time","Space","Biology","Physics","Chemistry"],"first_row_in_archive_order":{"model":"MindOmni\n(w/ cot)","paper_title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","paper_url":"/paper/mindomni-unleashing-reasoning-generation-in","paper_date":"2025-05-19","arxiv_id":"2505.13031","code_links":[{"title":"easonxiao-888/mindomni","url":"https://github.com/easonxiao-888/mindomni"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-ffhq-u","slug":"image-generation-on-ffhq-u","dataset":"FFHQ-U","dataset_url":"/dataset/ffhq","rows_in_archive":13,"metrics":["FID","EQ-T","EQ-R"],"first_row_in_archive_order":{"model":"Alias-Free-R","paper_title":"Alias-Free Generative Adversarial Networks","paper_url":"/paper/alias-free-generative-adversarial-networks","paper_date":"2021-06-23","arxiv_id":"2106.12423","code_links":[{"title":"NVlabs/stylegan3","url":"https://github.com/NVlabs/stylegan3"},{"title":"rosinality/alias-free-gan-pytorch","url":"https://github.com/rosinality/alias-free-gan-pytorch"},{"title":"kunheek/style-aware-discriminator","url":"https://github.com/kunheek/style-aware-discriminator"},{"title":"jychoi118/toward_spatial_unbiased","url":"https://github.com/jychoi118/toward_spatial_unbiased"},{"title":"duskvirkus/alias-free-gan-pytorch-lightning","url":"https://github.com/duskvirkus/alias-free-gan-pytorch-lightning"},{"title":"duskvirkus/alias-free-gan","url":"https://github.com/duskvirkus/alias-free-gan"},{"title":"lzhbrian/alias-free-gan-explanation","url":"https://github.com/lzhbrian/alias-free-gan-explanation"}],"syntology":{"n":31,"n_ran":30,"n_constructed":0,"n_ran_checked":20,"n_instrument":10,"n_unverified":1,"n_honours":5,"n_violates":4,"n_no_contract":11,"n_pointer_only":12,"phrase":"30 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 4 violated, 11 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/alias-free-generative-adversarial-networks#ran","syntology_url":"https://syntology.ai/paper/2106.12423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12423"}},"official":{"repos":["NVlabs/stylegan3"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-ffhq","slug":"image-generation-on-ffhq","dataset":"FFHQ","dataset_url":"/dataset/ffhq","rows_in_archive":12,"metrics":["FID","Clean-FID (70k)","FID-10k-training-steps"],"first_row_in_archive_order":{"model":"Anycost GAN","paper_title":"Anycost GANs for Interactive Image Synthesis and Editing","paper_url":"/paper/anycost-gans-for-interactive-image-synthesis","paper_date":"2021-03-04","arxiv_id":"2103.03243","code_links":[{"title":"mit-han-lab/anycost-gan","url":"https://github.com/mit-han-lab/anycost-gan"}],"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/anycost-gans-for-interactive-image-synthesis#ran","syntology_url":"https://syntology.ai/paper/2103.03243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2103.03243"}},"official":{"repos":["mit-han-lab/anycost-gan"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/image-generation-on-binarized-mnist","slug":"image-generation-on-binarized-mnist","dataset":"Binarized MNIST","dataset_url":"/dataset/binarized-mnist","rows_in_archive":10,"metrics":["nats","bits/dimension"],"first_row_in_archive_order":{"model":"CR-NVAE","paper_title":"Consistency Regularization for Variational Auto-Encoders","paper_url":"/paper/consistency-regularization-for-variational","paper_date":"2021-05-31","arxiv_id":"2105.14859","code_links":[{"title":"sinhasam/crvae","url":"https://github.com/sinhasam/crvae"}],"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/consistency-regularization-for-variational#ran","syntology_url":"https://syntology.ai/paper/2105.14859","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.14859"}},"official":{"repos":["sinhasam/crvae"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-celeba-hq-1024x1024","slug":"image-generation-on-celeba-hq-1024x1024","dataset":"CelebA-HQ 1024x1024","dataset_url":"/dataset/celeba-hq","rows_in_archive":10,"metrics":["FID","bits/dimension","NFE"],"first_row_in_archive_order":{"model":"StyleSwin","paper_title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","paper_url":"/paper/styleswin-transformer-based-gan-for-high-1","paper_date":"2021-12-20","arxiv_id":"2112.10762","code_links":[{"title":"microsoft/StyleSwin","url":"https://github.com/microsoft/StyleSwin"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/styleswin-transformer-based-gan-for-high-1#ran","syntology_url":"https://syntology.ai/paper/2112.10762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10762"}},"official":{"repos":["microsoft/StyleSwin"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-cifar-100","slug":"image-generation-on-cifar-100","dataset":"CIFAR-100","dataset_url":"/dataset/cifar-100","rows_in_archive":9,"metrics":["FID","Inception Score","Model Size (MB)"],"first_row_in_archive_order":{"model":"LeCAM (StyleGAN2 + ADA)","paper_title":"Regularizing Generative Adversarial Networks under Limited Data","paper_url":"/paper/regularizing-generative-adversarial-networks","paper_date":"2021-04-07","arxiv_id":"2104.03310","code_links":[{"title":"google/lecam-gan","url":"https://github.com/google/lecam-gan"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/regularizing-generative-adversarial-networks#ran","syntology_url":"https://syntology.ai/paper/2104.03310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03310"}},"official":{"repos":["google/lecam-gan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["found_in_text","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-afhq-cat","slug":"image-generation-on-afhq-cat","dataset":"AFHQ Cat","dataset_url":"/dataset/afhq","rows_in_archive":8,"metrics":["clean-KID","clean-FID","FID","MAE Signature","MAE log-signature","RMSE Signature","RMSE log-signature"],"first_row_in_archive_order":{"model":"Vision-aided GAN","paper_title":"Ensembling Off-the-shelf Models for GAN Training","paper_url":"/paper/ensembling-off-the-shelf-models-for-gan","paper_date":"2021-12-16","arxiv_id":"2112.09130","code_links":[{"title":"nupurkmr9/vision-aided-gan","url":"https://github.com/nupurkmr9/vision-aided-gan"}],"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ensembling-off-the-shelf-models-for-gan#ran","syntology_url":"https://syntology.ai/paper/2112.09130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.09130"}},"official":{"repos":["nupurkmr9/vision-aided-gan"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-lsun-cat-256-x-256","slug":"image-generation-on-lsun-cat-256-x-256","dataset":"LSUN Cat 256 x 256","dataset_url":"/dataset/lsun","rows_in_archive":8,"metrics":["FID","Clean-FID (trainfull)"],"first_row_in_archive_order":{"model":"Vision-aided GAN","paper_title":"Ensembling Off-the-shelf Models for GAN Training","paper_url":"/paper/ensembling-off-the-shelf-models-for-gan","paper_date":"2021-12-16","arxiv_id":"2112.09130","code_links":[{"title":"nupurkmr9/vision-aided-gan","url":"https://github.com/nupurkmr9/vision-aided-gan"}],"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ensembling-off-the-shelf-models-for-gan#ran","syntology_url":"https://syntology.ai/paper/2112.09130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.09130"}},"official":{"repos":["nupurkmr9/vision-aided-gan"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-afhqv2","slug":"image-generation-on-afhqv2","dataset":"AFHQV2","dataset_url":"/dataset/afhq","rows_in_archive":7,"metrics":["FID","EQ-T","EQ-R"],"first_row_in_archive_order":{"model":"Polarity-StyleGAN3","paper_title":"Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values","paper_url":"/paper/polarity-sampling-quality-and-diversity","paper_date":"2022-03-03","arxiv_id":"2203.01993","code_links":[{"title":"AhmedImtiazPrio/magnet-polarity","url":"https://github.com/AhmedImtiazPrio/magnet-polarity"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-celeba-hq-128x128","slug":"image-generation-on-celeba-hq-128x128","dataset":"CelebA-HQ 128x128","dataset_url":"/dataset/celeba-hq","rows_in_archive":7,"metrics":["FID","Inception score","IS"],"first_row_in_archive_order":{"model":"U-Net GAN","paper_title":"A U-Net Based Discriminator for Generative Adversarial Networks","paper_url":"/paper/a-u-net-based-discriminator-for-generative","paper_date":"2020-02-28","arxiv_id":"2002.12655","code_links":[{"title":"boschresearch/unetgan","url":"https://github.com/boschresearch/unetgan"},{"title":"xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch","url":"https://github.com/xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch"},{"title":"xingchenzhao/deep-learning-team-project","url":"https://github.com/xingchenzhao/deep-learning-team-project"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-fashion-mnist","slug":"image-generation-on-fashion-mnist","dataset":"Fashion-MNIST","dataset_url":"/dataset/fashion-mnist","rows_in_archive":7,"metrics":["FID","Precision","Recall"],"first_row_in_archive_order":{"model":"GLF+perceptual loss (ours)","paper_title":"Generative Latent Flow","paper_url":"/paper/generative-latent-flow-a-framework-for-non","paper_date":"2019-05-24","arxiv_id":"1905.10485","code_links":[{"title":"rakhimovv/GenerativeLatentFlow","url":"https://github.com/rakhimovv/GenerativeLatentFlow"}],"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generative-latent-flow-a-framework-for-non#ran","syntology_url":"https://syntology.ai/paper/1905.10485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.10485"}},"official":null}}},{"leaderboard":"/sota/image-generation-on-textatlaseval","slug":"image-generation-on-textatlaseval","dataset":"TextAtlasEval","dataset_url":"/dataset/textatlaseval","rows_in_archive":7,"metrics":["TextVsionBlend OCR (F1 Score)","TextVisionBlend OCR (Accuracy)","TextVisionBlend OCR (Cer)","TextVisionBlend FID","TextVisionBlend Clip Score","StyledTextSynth OCR (F1 Score)","StyledTextSynth OCR (Accuracy)","StyledTextSynth OCR (Cer)","StyledTextSynth FID","StyledTextSynth Clip Score","TextScenesHQ OCR (F1 Score)","TextScenesHQ OCR (Accuracy)","TextScenesHQ OCR (Cer)","TextScenesHQ FID","TextScenesHQ Clip Score"],"first_row_in_archive_order":{"model":"Grok3","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/image-generation-on-afhq-dog","slug":"image-generation-on-afhq-dog","dataset":"AFHQ Dog","dataset_url":"/dataset/afhq","rows_in_archive":6,"metrics":["FID","clean-FID","clean-KID","MAE Signature","MAE log-signature","RMSE Signature","RMSE log-signature"],"first_row_in_archive_order":{"model":"Projected GAN","paper_title":"Projected GANs Converge Faster","paper_url":"/paper/projected-gans-converge-faster","paper_date":"2021-11-01","arxiv_id":"2111.01007","code_links":[{"title":"autonomousvision/projected_gan","url":"https://github.com/autonomousvision/projected_gan"},{"title":"dome272/ProjectedGAN-pytorch","url":"https://github.com/dome272/ProjectedGAN-pytorch"},{"title":"tsubota-kouga/ProjectedGAN","url":"https://github.com/tsubota-kouga/ProjectedGAN"}],"syntology":{"n":49,"n_ran":38,"n_constructed":14,"n_ran_checked":20,"n_instrument":18,"n_unverified":11,"n_honours":3,"n_violates":0,"n_no_contract":17,"n_pointer_only":6,"phrase":"38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/projected-gans-converge-faster#ran","syntology_url":"https://syntology.ai/paper/2111.01007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01007"}},"official":{"repos":["autonomousvision/projected_gan"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-cityscapes","slug":"image-generation-on-cityscapes","dataset":"Cityscapes","dataset_url":"/dataset/cityscapes","rows_in_archive":6,"metrics":["FID-10k-training-steps"],"first_row_in_archive_order":{"model":"Projected GAN","paper_title":"Projected GANs Converge Faster","paper_url":"/paper/projected-gans-converge-faster","paper_date":"2021-11-01","arxiv_id":"2111.01007","code_links":[{"title":"autonomousvision/projected_gan","url":"https://github.com/autonomousvision/projected_gan"},{"title":"dome272/ProjectedGAN-pytorch","url":"https://github.com/dome272/ProjectedGAN-pytorch"},{"title":"tsubota-kouga/ProjectedGAN","url":"https://github.com/tsubota-kouga/ProjectedGAN"}],"syntology":{"n":49,"n_ran":38,"n_constructed":14,"n_ran_checked":20,"n_instrument":18,"n_unverified":11,"n_honours":3,"n_violates":0,"n_no_contract":17,"n_pointer_only":6,"phrase":"38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/projected-gans-converge-faster#ran","syntology_url":"https://syntology.ai/paper/2111.01007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01007"}},"official":{"repos":["autonomousvision/projected_gan"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-clevr","slug":"image-generation-on-clevr","dataset":"CLEVR","dataset_url":"/dataset/clevr","rows_in_archive":6,"metrics":["FID-5k-training-steps"],"first_row_in_archive_order":{"model":"Projected GAN","paper_title":"Projected GANs Converge Faster","paper_url":"/paper/projected-gans-converge-faster","paper_date":"2021-11-01","arxiv_id":"2111.01007","code_links":[{"title":"autonomousvision/projected_gan","url":"https://github.com/autonomousvision/projected_gan"},{"title":"dome272/ProjectedGAN-pytorch","url":"https://github.com/dome272/ProjectedGAN-pytorch"},{"title":"tsubota-kouga/ProjectedGAN","url":"https://github.com/tsubota-kouga/ProjectedGAN"}],"syntology":{"n":49,"n_ran":38,"n_constructed":14,"n_ran_checked":20,"n_instrument":18,"n_unverified":11,"n_honours":3,"n_violates":0,"n_no_contract":17,"n_pointer_only":6,"phrase":"38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/projected-gans-converge-faster#ran","syntology_url":"https://syntology.ai/paper/2111.01007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01007"}},"official":{"repos":["autonomousvision/projected_gan"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-lsun-horse-256-x-256","slug":"image-generation-on-lsun-horse-256-x-256","dataset":"LSUN Horse 256 x 256","dataset_url":"/dataset/lsun","rows_in_archive":6,"metrics":["FID","Clean-FID (trainfull)"],"first_row_in_archive_order":{"model":"Vision-aided GAN","paper_title":"Ensembling Off-the-shelf Models for GAN Training","paper_url":"/paper/ensembling-off-the-shelf-models-for-gan","paper_date":"2021-12-16","arxiv_id":"2112.09130","code_links":[{"title":"nupurkmr9/vision-aided-gan","url":"https://github.com/nupurkmr9/vision-aided-gan"}],"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ensembling-off-the-shelf-models-for-gan#ran","syntology_url":"https://syntology.ai/paper/2112.09130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.09130"}},"official":{"repos":["nupurkmr9/vision-aided-gan"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-afhq-wild","slug":"image-generation-on-afhq-wild","dataset":"AFHQ Wild","dataset_url":"/dataset/afhq","rows_in_archive":5,"metrics":["clean-KID","clean-FID","FID","MAE Signature","MAE log-signature","RMSE Signature","RMSE log-signature"],"first_row_in_archive_order":{"model":"Vision-aided GAN","paper_title":"Ensembling Off-the-shelf Models for GAN Training","paper_url":"/paper/ensembling-off-the-shelf-models-for-gan","paper_date":"2021-12-16","arxiv_id":"2112.09130","code_links":[{"title":"nupurkmr9/vision-aided-gan","url":"https://github.com/nupurkmr9/vision-aided-gan"}],"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":4,"n_instrument":10,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":8,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ensembling-off-the-shelf-models-for-gan#ran","syntology_url":"https://syntology.ai/paper/2112.09130","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.09130"}},"official":{"repos":["nupurkmr9/vision-aided-gan"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-celeba-128x128","slug":"image-generation-on-celeba-128x128","dataset":"CelebA 128x128","dataset_url":"/dataset/celeba","rows_in_archive":5,"metrics":["FID","Inception score","MS-SSIM"],"first_row_in_archive_order":{"model":"U-Net GAN","paper_title":"A U-Net Based Discriminator for Generative Adversarial Networks","paper_url":"/paper/a-u-net-based-discriminator-for-generative","paper_date":"2020-02-28","arxiv_id":"2002.12655","code_links":[{"title":"boschresearch/unetgan","url":"https://github.com/boschresearch/unetgan"},{"title":"xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch","url":"https://github.com/xingchenzhao/Generating-Human-Skeletons-with-Mutual-Actions-WGAN-Pytorch"},{"title":"xingchenzhao/deep-learning-team-project","url":"https://github.com/xingchenzhao/deep-learning-team-project"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-places50","slug":"image-generation-on-places50","dataset":"Places50","dataset_url":null,"rows_in_archive":5,"metrics":["LPIPS","SIFID"],"first_row_in_archive_order":{"model":"SinDiffusion","paper_title":"SinDiffusion: Learning a Diffusion Model from a Single Natural Image","paper_url":"/paper/sindiffusion-learning-a-diffusion-model-from","paper_date":"2022-11-22","arxiv_id":"2211.12445","code_links":[{"title":"weilunwang/sindiffusion","url":"https://github.com/weilunwang/sindiffusion"}],"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":6,"n_instrument":11,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":12,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 11 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/sindiffusion-learning-a-diffusion-model-from#ran","syntology_url":"https://syntology.ai/paper/2211.12445","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.12445"}},"official":{"repos":["weilunwang/sindiffusion"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-arkitscenes","slug":"image-generation-on-arkitscenes","dataset":"ARKitScenes","dataset_url":"/dataset/arkitscenes","rows_in_archive":4,"metrics":["FID","FID (SwAV)"],"first_row_in_archive_order":{"model":"GAUDI","paper_title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","paper_url":"/paper/gaudi-a-neural-architect-for-immersive-3d","paper_date":"2022-07-27","arxiv_id":"2207.13751","code_links":[{"title":"apple/ml-gaudi","url":"https://github.com/apple/ml-gaudi"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-cub-128-x-128","slug":"image-generation-on-cub-128-x-128","dataset":"CUB 128 x 128","dataset_url":"/dataset/cub-200-2011","rows_in_archive":4,"metrics":["FID","Inception score"],"first_row_in_archive_order":{"model":"Projected GAN","paper_title":"Projected GANs Converge Faster","paper_url":"/paper/projected-gans-converge-faster","paper_date":"2021-11-01","arxiv_id":"2111.01007","code_links":[{"title":"autonomousvision/projected_gan","url":"https://github.com/autonomousvision/projected_gan"},{"title":"dome272/ProjectedGAN-pytorch","url":"https://github.com/dome272/ProjectedGAN-pytorch"},{"title":"tsubota-kouga/ProjectedGAN","url":"https://github.com/tsubota-kouga/ProjectedGAN"}],"syntology":{"n":49,"n_ran":38,"n_constructed":14,"n_ran_checked":20,"n_instrument":18,"n_unverified":11,"n_honours":3,"n_violates":0,"n_no_contract":17,"n_pointer_only":6,"phrase":"38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/projected-gans-converge-faster#ran","syntology_url":"https://syntology.ai/paper/2111.01007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01007"}},"official":{"repos":["autonomousvision/projected_gan"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-pokemon-256x256","slug":"image-generation-on-pokemon-256x256","dataset":"Pokemon 256x256","dataset_url":null,"rows_in_archive":4,"metrics":["FID"],"first_row_in_archive_order":{"model":"StyleGAN-XL","paper_title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","paper_url":"/paper/stylegan-xl-scaling-stylegan-to-large-diverse","paper_date":"2022-02-01","arxiv_id":"2202.00273","code_links":[{"title":"autonomousvision/stylegan-xl","url":"https://github.com/autonomousvision/stylegan-xl"},{"title":"autonomousvision/stylegan_xl","url":"https://github.com/autonomousvision/stylegan_xl"}],"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":5,"n_instrument":11,"n_unverified":3,"n_honours":5,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 11 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stylegan-xl-scaling-stylegan-to-large-diverse#ran","syntology_url":"https://syntology.ai/paper/2202.00273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.00273"}},"official":{"repos":["autonomousvision/stylegan_xl"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-replica","slug":"image-generation-on-replica","dataset":"Replica","dataset_url":"/dataset/replica","rows_in_archive":4,"metrics":["FID","FID (SwAV)"],"first_row_in_archive_order":{"model":"GAUDI","paper_title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","paper_url":"/paper/gaudi-a-neural-architect-for-immersive-3d","paper_date":"2022-07-27","arxiv_id":"2207.13751","code_links":[{"title":"apple/ml-gaudi","url":"https://github.com/apple/ml-gaudi"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-stanford-cars","slug":"image-generation-on-stanford-cars","dataset":"Stanford Cars","dataset_url":"/dataset/stanford-cars","rows_in_archive":4,"metrics":["FID","Inception score"],"first_row_in_archive_order":{"model":"Projected GANs","paper_title":"Projected GANs Converge Faster","paper_url":"/paper/projected-gans-converge-faster","paper_date":"2021-11-01","arxiv_id":"2111.01007","code_links":[{"title":"autonomousvision/projected_gan","url":"https://github.com/autonomousvision/projected_gan"},{"title":"dome272/ProjectedGAN-pytorch","url":"https://github.com/dome272/ProjectedGAN-pytorch"},{"title":"tsubota-kouga/ProjectedGAN","url":"https://github.com/tsubota-kouga/ProjectedGAN"}],"syntology":{"n":49,"n_ran":38,"n_constructed":14,"n_ran_checked":20,"n_instrument":18,"n_unverified":11,"n_honours":3,"n_violates":0,"n_no_contract":17,"n_pointer_only":6,"phrase":"38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/projected-gans-converge-faster#ran","syntology_url":"https://syntology.ai/paper/2111.01007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01007"}},"official":{"repos":["autonomousvision/projected_gan"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-stanford-dogs","slug":"image-generation-on-stanford-dogs","dataset":"Stanford Dogs","dataset_url":"/dataset/stanford-dogs","rows_in_archive":4,"metrics":["FID","Inception score"],"first_row_in_archive_order":{"model":"Projected GAN","paper_title":"Projected GANs Converge Faster","paper_url":"/paper/projected-gans-converge-faster","paper_date":"2021-11-01","arxiv_id":"2111.01007","code_links":[{"title":"autonomousvision/projected_gan","url":"https://github.com/autonomousvision/projected_gan"},{"title":"dome272/ProjectedGAN-pytorch","url":"https://github.com/dome272/ProjectedGAN-pytorch"},{"title":"tsubota-kouga/ProjectedGAN","url":"https://github.com/tsubota-kouga/ProjectedGAN"}],"syntology":{"n":49,"n_ran":38,"n_constructed":14,"n_ran_checked":20,"n_instrument":18,"n_unverified":11,"n_honours":3,"n_violates":0,"n_no_contract":17,"n_pointer_only":6,"phrase":"38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/projected-gans-converge-faster#ran","syntology_url":"https://syntology.ai/paper/2111.01007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01007"}},"official":{"repos":["autonomousvision/projected_gan"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-vizdoom","slug":"image-generation-on-vizdoom","dataset":"VizDoom","dataset_url":"/dataset/vizdoom","rows_in_archive":4,"metrics":["FID","FID (SwAV)"],"first_row_in_archive_order":{"model":"GAUDI","paper_title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","paper_url":"/paper/gaudi-a-neural-architect-for-immersive-3d","paper_date":"2022-07-27","arxiv_id":"2207.13751","code_links":[{"title":"apple/ml-gaudi","url":"https://github.com/apple/ml-gaudi"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-vln-ce","slug":"image-generation-on-vln-ce","dataset":"VLN-CE","dataset_url":"/dataset/vln-ce","rows_in_archive":4,"metrics":["FID","FID (SwAV)"],"first_row_in_archive_order":{"model":"GAUDI","paper_title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","paper_url":"/paper/gaudi-a-neural-architect-for-immersive-3d","paper_date":"2022-07-27","arxiv_id":"2207.13751","code_links":[{"title":"apple/ml-gaudi","url":"https://github.com/apple/ml-gaudi"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-ade-indoor","slug":"image-generation-on-ade-indoor","dataset":"ADE-Indoor","dataset_url":null,"rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"Projected GAN","paper_title":"Projected GANs Converge Faster","paper_url":"/paper/projected-gans-converge-faster","paper_date":"2021-11-01","arxiv_id":"2111.01007","code_links":[{"title":"autonomousvision/projected_gan","url":"https://github.com/autonomousvision/projected_gan"},{"title":"dome272/ProjectedGAN-pytorch","url":"https://github.com/dome272/ProjectedGAN-pytorch"},{"title":"tsubota-kouga/ProjectedGAN","url":"https://github.com/tsubota-kouga/ProjectedGAN"}],"syntology":{"n":49,"n_ran":38,"n_constructed":14,"n_ran_checked":20,"n_instrument":18,"n_unverified":11,"n_honours":3,"n_violates":0,"n_no_contract":17,"n_pointer_only":6,"phrase":"38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/projected-gans-converge-faster#ran","syntology_url":"https://syntology.ai/paper/2111.01007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01007"}},"official":{"repos":["autonomousvision/projected_gan"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-cat-256x256","slug":"image-generation-on-cat-256x256","dataset":"CAT 256x256","dataset_url":null,"rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"StyleGAN2 + DA + RLC (Ours)","paper_title":"Regularizing Generative Adversarial Networks under Limited Data","paper_url":"/paper/regularizing-generative-adversarial-networks","paper_date":"2021-04-07","arxiv_id":"2104.03310","code_links":[{"title":"google/lecam-gan","url":"https://github.com/google/lecam-gan"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/regularizing-generative-adversarial-networks#ran","syntology_url":"https://syntology.ai/paper/2104.03310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03310"}},"official":{"repos":["google/lecam-gan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["found_in_text","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-celeba-hq-64x64","slug":"image-generation-on-celeba-hq-64x64","dataset":"CelebA-HQ 64x64","dataset_url":"/dataset/celeba-hq","rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"COCO-GAN","paper_title":"COCO-GAN: Generation by Parts via Conditional Coordinating","paper_url":"/paper/coco-gan-generation-by-parts-via-conditional","paper_date":"2019-03-30","arxiv_id":"1904.00284","code_links":[{"title":"hubert0527/COCO-GAN","url":"https://github.com/hubert0527/COCO-GAN"}],"syntology":{"n":6,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/coco-gan-generation-by-parts-via-conditional#ran","syntology_url":"https://syntology.ai/paper/1904.00284","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00284"}},"official":null}}},{"leaderboard":"/sota/image-generation-on-cifar-10-10-data","slug":"image-generation-on-cifar-10-10-data","dataset":"CIFAR-10 (10% data)","dataset_url":"/dataset/cifar-10","rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"DiffAugment-StyleGAN2","paper_title":"Differentiable Augmentation for Data-Efficient GAN Training","paper_url":"/paper/differentiable-augmentation-for-data","paper_date":"2020-06-18","arxiv_id":"2006.10738","code_links":[{"title":"POSTECH-CVLab/PyTorch-StudioGAN","url":"https://github.com/POSTECH-CVLab/PyTorch-StudioGAN"},{"title":"mit-han-lab/data-efficient-gans","url":"https://github.com/mit-han-lab/data-efficient-gans"},{"title":"jankrepl/mildlyoverfitted","url":"https://github.com/jankrepl/mildlyoverfitted"},{"title":"eps696/stylegan2","url":"https://github.com/eps696/stylegan2"},{"title":"VITA-Group/Ultra-Data-Efficient-GAN-Training","url":"https://github.com/VITA-Group/Ultra-Data-Efficient-GAN-Training"},{"title":"gaborvecsei/SLE-GAN","url":"https://github.com/gaborvecsei/SLE-GAN"},{"title":"milmor/TransGAN","url":"https://github.com/milmor/TransGAN"},{"title":"milmor/ladagan","url":"https://github.com/milmor/ladagan"},{"title":"milmor/self-supervised-gan","url":"https://github.com/milmor/self-supervised-gan"},{"title":"claim-berlin/3d_stylegan_circle_of_willis","url":"https://github.com/claim-berlin/3d_stylegan_circle_of_willis"},{"title":"uzielroy/StyleGan_FewShot","url":"https://github.com/uzielroy/StyleGan_FewShot"},{"title":"milmor/LadaGAN-pytorch","url":"https://github.com/milmor/LadaGAN-pytorch"},{"title":"shreshtashetty/CycleGANPhototoMonet","url":"https://github.com/shreshtashetty/CycleGANPhototoMonet"}],"syntology":{"n":58,"n_ran":49,"n_constructed":0,"n_ran_checked":17,"n_instrument":32,"n_unverified":9,"n_honours":3,"n_violates":1,"n_no_contract":13,"n_pointer_only":15,"phrase":"49 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 1 violated, 13 with no contract checked; 32 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/differentiable-augmentation-for-data#ran","syntology_url":"https://syntology.ai/paper/2006.10738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10738"}},"official":{"repos":["mit-han-lab/data-efficient-gans"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/image-generation-on-cifar-10-20-data","slug":"image-generation-on-cifar-10-20-data","dataset":"CIFAR-10 (20% data)","dataset_url":"/dataset/cifar-10","rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"DiffAugment-StyleGAN2","paper_title":"Differentiable Augmentation for Data-Efficient GAN Training","paper_url":"/paper/differentiable-augmentation-for-data","paper_date":"2020-06-18","arxiv_id":"2006.10738","code_links":[{"title":"POSTECH-CVLab/PyTorch-StudioGAN","url":"https://github.com/POSTECH-CVLab/PyTorch-StudioGAN"},{"title":"mit-han-lab/data-efficient-gans","url":"https://github.com/mit-han-lab/data-efficient-gans"},{"title":"jankrepl/mildlyoverfitted","url":"https://github.com/jankrepl/mildlyoverfitted"},{"title":"eps696/stylegan2","url":"https://github.com/eps696/stylegan2"},{"title":"VITA-Group/Ultra-Data-Efficient-GAN-Training","url":"https://github.com/VITA-Group/Ultra-Data-Efficient-GAN-Training"},{"title":"gaborvecsei/SLE-GAN","url":"https://github.com/gaborvecsei/SLE-GAN"},{"title":"milmor/TransGAN","url":"https://github.com/milmor/TransGAN"},{"title":"milmor/ladagan","url":"https://github.com/milmor/ladagan"},{"title":"milmor/self-supervised-gan","url":"https://github.com/milmor/self-supervised-gan"},{"title":"claim-berlin/3d_stylegan_circle_of_willis","url":"https://github.com/claim-berlin/3d_stylegan_circle_of_willis"},{"title":"uzielroy/StyleGan_FewShot","url":"https://github.com/uzielroy/StyleGan_FewShot"},{"title":"milmor/LadaGAN-pytorch","url":"https://github.com/milmor/LadaGAN-pytorch"},{"title":"shreshtashetty/CycleGANPhototoMonet","url":"https://github.com/shreshtashetty/CycleGANPhototoMonet"}],"syntology":{"n":58,"n_ran":49,"n_constructed":0,"n_ran_checked":17,"n_instrument":32,"n_unverified":9,"n_honours":3,"n_violates":1,"n_no_contract":13,"n_pointer_only":15,"phrase":"49 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 1 violated, 13 with no contract checked; 32 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/differentiable-augmentation-for-data#ran","syntology_url":"https://syntology.ai/paper/2006.10738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10738"}},"official":{"repos":["mit-han-lab/data-efficient-gans"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/image-generation-on-ffhq-128-x-128","slug":"image-generation-on-ffhq-128-x-128","dataset":"FFHQ 128 x 128","dataset_url":null,"rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"DDPM-IP","paper_title":"Input Perturbation Reduces Exposure Bias in Diffusion Models","paper_url":"/paper/input-perturbation-reduces-exposure-bias-in","paper_date":"2023-01-27","arxiv_id":"2301.11706","code_links":[{"title":"forever208/ddpm-ip","url":"https://github.com/forever208/ddpm-ip"}],"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/input-perturbation-reduces-exposure-bias-in#ran","syntology_url":"https://syntology.ai/paper/2301.11706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11706"}},"official":{"repos":["forever208/ddpm-ip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-ffhq-512-x-512","slug":"image-generation-on-ffhq-512-x-512","dataset":"FFHQ 512 x 512","dataset_url":"/dataset/ffhq","rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"StyleSAN-XL","paper_title":"SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer","paper_url":"/paper/adversarially-slicing-generative-networks","paper_date":"2023-01-30","arxiv_id":"2301.12811","code_links":[{"title":"sony/san","url":"https://github.com/sony/san"}],"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarially-slicing-generative-networks#ran","syntology_url":"https://syntology.ai/paper/2301.12811","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.12811"}},"official":{"repos":["sony/san"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-lsun-bedroom-1","slug":"image-generation-on-lsun-bedroom-1","dataset":"LSUN Bedroom","dataset_url":"/dataset/lsun","rows_in_archive":3,"metrics":["FID-50k","clean-FID"],"first_row_in_archive_order":{"model":"StyleGAN","paper_title":"A Style-Based Generator Architecture for Generative Adversarial Networks","paper_url":"/paper/a-style-based-generator-architecture-for","paper_date":"2018-12-12","arxiv_id":"1812.04948","code_links":[{"title":"NVlabs/stylegan","url":"https://github.com/NVlabs/stylegan"},{"title":"NVlabs/ffhq-dataset","url":"https://github.com/NVlabs/ffhq-dataset"},{"title":"keras-team/keras-io","url":"https://github.com/keras-team/keras-io/blob/master/examples/generative/stylegan.py"},{"title":"open-mmlab/mmgeneration","url":"https://github.com/open-mmlab/mmgeneration"},{"title":"facebookresearch/pytorch_GAN_zoo","url":"https://github.com/facebookresearch/pytorch_GAN_zoo"},{"title":"ShenYujun/InterFaceGAN","url":"https://github.com/ShenYujun/InterFaceGAN"},{"title":"genforce/interfacegan","url":"https://github.com/genforce/interfacegan"},{"title":"rosinality/style-based-gan-pytorch","url":"https://github.com/rosinality/style-based-gan-pytorch"},{"title":"huangzh13/StyleGAN.pytorch","url":"https://github.com/huangzh13/StyleGAN.pytorch"},{"title":"woctezuma/stylegan2-projecting-images","url":"https://github.com/woctezuma/stylegan2-projecting-images"},{"title":"taki0112/StyleGAN-Tensorflow","url":"https://github.com/taki0112/StyleGAN-Tensorflow"},{"title":"cc-hpc-itwm/DeepFakeDetection","url":"https://github.com/cc-hpc-itwm/DeepFakeDetection"},{"title":"manicman1999/StyleGAN-Keras","url":"https://github.com/manicman1999/StyleGAN-Keras"},{"title":"SiskonEmilia/StyleGAN-PyTorch","url":"https://github.com/SiskonEmilia/StyleGAN-PyTorch"},{"title":"pfnet-research/chainer-stylegan","url":"https://github.com/pfnet-research/chainer-stylegan"},{"title":"Tejas-Nanaware/GAN-Anime-Characters","url":"https://github.com/Tejas-Nanaware/GAN-Anime-Characters"},{"title":"delta6189/Anime-Sketch-Colorizer","url":"https://github.com/delta6189/Anime-Sketch-Colorizer"},{"title":"manicman1999/StyleGAN-Tensorflow-2.0","url":"https://github.com/manicman1999/StyleGAN-Tensorflow-2.0"},{"title":"a514514772/hijackgan","url":"https://github.com/a514514772/hijackgan"},{"title":"hui-po-wang/hijackgan","url":"https://github.com/hui-po-wang/hijackgan"},{"title":"podgorskiy/StyleGAN_Blobless","url":"https://github.com/podgorskiy/StyleGAN_Blobless"},{"title":"woctezuma/steam-stylegan2","url":"https://github.com/woctezuma/steam-stylegan2"},{"title":"woctezuma/steam-stylegan2-ada","url":"https://github.com/woctezuma/steam-stylegan2-ada"},{"title":"ialhashim/StyleGAN-Tensorflow2","url":"https://github.com/ialhashim/StyleGAN-Tensorflow2"},{"title":"yaxingwang/DeepI2I","url":"https://github.com/yaxingwang/DeepI2I"},{"title":"akatigre/multi2one","url":"https://github.com/akatigre/multi2one"},{"title":"bit-ml/dolos","url":"https://github.com/bit-ml/dolos"},{"title":"hichoe95/Artifact-Detection-and-Sequential-Ablation","url":"https://github.com/hichoe95/Artifact-Detection-and-Sequential-Ablation"},{"title":"podgorskiy/StyleGan","url":"https://github.com/podgorskiy/StyleGan"},{"title":"sidward14/gan-lab","url":"https://github.com/sidward14/gan-lab"},{"title":"Ipsedo/MusicGAN","url":"https://github.com/Ipsedo/MusicGAN"},{"title":"ariel415el/ALAE","url":"https://github.com/ariel415el/ALAE"},{"title":"ariel415el/SimplePytorch-ALAE","url":"https://github.com/ariel415el/SimplePytorch-ALAE"},{"title":"comp-imaging-sci/pic-recon","url":"https://github.com/comp-imaging-sci/pic-recon"},{"title":"perplexingpegasus/EarthLandscapeGAN","url":"https://github.com/perplexingpegasus/EarthLandscapeGAN"},{"title":"mokeam/StatueStyleGAN","url":"https://github.com/mokeam/StatueStyleGAN"},{"title":"pierrickch/textureautoencoder","url":"https://github.com/pierrickch/textureautoencoder"},{"title":"santhtadi/AutoEncodersImageCompression","url":"https://github.com/santhtadi/AutoEncodersImageCompression"},{"title":"mgmk2/StyleGAN","url":"https://github.com/mgmk2/StyleGAN"},{"title":"yan-roo/FakeFace","url":"https://github.com/yan-roo/FakeFace"},{"title":"xiuyu0000/papers_with_examples","url":"https://github.com/xiuyu0000/papers_with_examples/tree/main/stylegan2"},{"title":"NariMo91/GANs-generative-art","url":"https://github.com/NariMo91/GANs-generative-art"},{"title":"ashutosh1919/FaceGenerationStyleGAN","url":"https://github.com/ashutosh1919/FaceGenerationStyleGAN"},{"title":"roberttwomey/machine-imagination-workshop","url":"https://github.com/roberttwomey/machine-imagination-workshop"},{"title":"freegyp/stylegan-keras-ece655","url":"https://github.com/freegyp/stylegan-keras-ece655"},{"title":"hejj16/Landscape-StyleGAN","url":"https://github.com/hejj16/Landscape-StyleGAN"},{"title":"jiazhi412/strong_attribute_bias","url":"https://github.com/jiazhi412/strong_attribute_bias"},{"title":"ravinderpayal/stylegan_fashion","url":"https://github.com/ravinderpayal/stylegan_fashion"},{"title":"bennyqp/artificial-inspiration","url":"https://github.com/bennyqp/artificial-inspiration"},{"title":"LeChangAlex/GAN-Metric","url":"https://github.com/LeChangAlex/GAN-Metric"},{"title":"UdbhavPrasad072300/GANs-Implementations","url":"https://github.com/UdbhavPrasad072300/GANs-Implementations"},{"title":"slee5777/StyleGAN","url":"https://github.com/slee5777/StyleGAN"},{"title":"sims-s/bird-gan","url":"https://github.com/sims-s/bird-gan"},{"title":"foamliu/StyleGAN-PyTorch","url":"https://github.com/foamliu/StyleGAN-PyTorch"},{"title":"stefkim/stylegan-batik","url":"https://github.com/stefkim/stylegan-batik"},{"title":"dhruvgrover1251/Playing_with_GANs","url":"https://github.com/dhruvgrover1251/Playing_with_GANs"},{"title":"QuangBK/cStyleGAN","url":"https://github.com/QuangBK/cStyleGAN"},{"title":"LignumResearch/stylewood-model-usage","url":"https://github.com/LignumResearch/stylewood-model-usage"},{"title":"VedantDere0104/StyleGAN","url":"https://github.com/VedantDere0104/StyleGAN"},{"title":"itsuki8914/stylegan-TensorFlow","url":"https://github.com/itsuki8914/stylegan-TensorFlow"},{"title":"yuzq97/starter_project","url":"https://github.com/yuzq97/starter_project"},{"title":"Aruie/Aru_StyleGAN","url":"https://github.com/Aruie/Aru_StyleGAN"},{"title":"casey-barr/generative-models-in-tensorflow","url":"https://github.com/casey-barr/generative-models-in-tensorflow"},{"title":"heavenstobetsy/ArtGenerationwithStyleGan","url":"https://github.com/heavenstobetsy/ArtGenerationwithStyleGan"},{"title":"BingkAI-B21CAP0161/C-Mask-Machine-Learning","url":"https://github.com/BingkAI-B21CAP0161/C-Mask-Machine-Learning"},{"title":"ayushgupta9198/gan","url":"https://github.com/ayushgupta9198/gan"},{"title":"HSabbar/Generation-lyrics-PNL","url":"https://github.com/HSabbar/Generation-lyrics-PNL"},{"title":"Meghraj-Webllisto/stylegan","url":"https://github.com/Meghraj-Webllisto/stylegan"},{"title":"irynakostyshyn/A-Style-Based-Generator-Architecture-for-GAN","url":"https://github.com/irynakostyshyn/A-Style-Based-Generator-Architecture-for-GAN"},{"title":"avakong/stylegan-test","url":"https://github.com/avakong/stylegan-test"},{"title":"khurram702/StyleBasedGAN","url":"https://github.com/khurram702/StyleBasedGAN"},{"title":"celdeldel/style_conditionnal_gan","url":"https://github.com/celdeldel/style_conditionnal_gan"},{"title":"jimzers/stylegan2-colabs","url":"https://github.com/jimzers/stylegan2-colabs"},{"title":"sergkuzn148/stg","url":"https://github.com/sergkuzn148/stg"},{"title":"sergkuzn148/lol3","url":"https://github.com/sergkuzn148/lol3"},{"title":"junaidwahid/Implementation-of-StyleGan_A-Style-Based-Generator-Architecture-for-Generative-Adversarial-Networks","url":"https://github.com/junaidwahid/Implementation-of-StyleGan_A-Style-Based-Generator-Architecture-for-Generative-Adversarial-Networks"},{"title":"RyanWu2233/Style_GAN2_FFHQ","url":"https://github.com/RyanWu2233/Style_GAN2_FFHQ"},{"title":"jooyae/NVIDIA_STYLEGAN","url":"https://github.com/jooyae/NVIDIA_STYLEGAN"},{"title":"ayushgupta9198/stylegan","url":"https://github.com/ayushgupta9198/stylegan"},{"title":"santhtadi/Colorize-Images-Pix2Pix-in-TensorflowJS","url":"https://github.com/santhtadi/Colorize-Images-Pix2Pix-in-TensorflowJS"},{"title":"mkulaczkowski/mixedstylegan","url":"https://github.com/mkulaczkowski/mixedstylegan"},{"title":"isaacschaal/SG_training","url":"https://github.com/isaacschaal/SG_training"},{"title":"ayiyoh/style-gan-pytorch","url":"https://github.com/ayiyoh/style-gan-pytorch"}],"syntology":{"n":396,"n_ran":244,"n_constructed":147,"n_ran_checked":217,"n_instrument":27,"n_unverified":152,"n_honours":17,"n_violates":3,"n_no_contract":197,"n_pointer_only":229,"phrase":"244 ran (of which 147 constructed an object rather than computing a result; 217 with no instrument failure: 17 honoured, 3 violated, 197 with no contract checked; 27 where Syntology's instrument failed) · 152 unverified","sample_list":"/paper/a-style-based-generator-architecture-for#ran","syntology_url":"https://syntology.ai/paper/1812.04948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.04948"}},"official":{"repos":["NVlabs/ffhq-dataset","NVlabs/stylegan"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/image-generation-on-lsun-bedroom-64-x-64","slug":"image-generation-on-lsun-bedroom-64-x-64","dataset":"LSUN Bedroom 64 x 64","dataset_url":"/dataset/lsun","rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"WGAN-GP + TTUR + Alex-Adam","paper_title":"Fundamental Benefit of Alternating Updates in Minimax Optimization","paper_url":"/paper/fundamental-benefit-of-alternating-updates-in","paper_date":"2024-02-16","arxiv_id":"2402.10475","code_links":[{"title":"hanseuljo/alex-gda","url":"https://github.com/hanseuljo/alex-gda"}],"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/fundamental-benefit-of-alternating-updates-in#ran","syntology_url":"https://syntology.ai/paper/2402.10475","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10475"}},"official":{"repos":["hanseuljo/alex-gda"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-metfaces","slug":"image-generation-on-metfaces","dataset":"MetFaces","dataset_url":"/dataset/metfaces","rows_in_archive":3,"metrics":["MAE Signature","MAE log-signature","RMSE Signature","RMSE log-signature"],"first_row_in_archive_order":{"model":"t-Stylegan3-ada (NVIDIA pre-trained)","paper_title":"Signature and Log-signature for the Study of Empirical Distributions Generated with GANs","paper_url":"/paper/signature-and-log-signature-for-the-study-of","paper_date":"2022-03-07","arxiv_id":"2203.03226","code_links":[{"title":"decurtoydiaz/signatures","url":"https://github.com/decurtoydiaz/signatures"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-metfaces-u","slug":"image-generation-on-metfaces-u","dataset":"MetFaces-U","dataset_url":"/dataset/metfaces","rows_in_archive":3,"metrics":["FID","EQ-T","EQ-R"],"first_row_in_archive_order":{"model":"Alias-Free-R","paper_title":"Alias-Free Generative Adversarial Networks","paper_url":"/paper/alias-free-generative-adversarial-networks","paper_date":"2021-06-23","arxiv_id":"2106.12423","code_links":[{"title":"NVlabs/stylegan3","url":"https://github.com/NVlabs/stylegan3"},{"title":"rosinality/alias-free-gan-pytorch","url":"https://github.com/rosinality/alias-free-gan-pytorch"},{"title":"kunheek/style-aware-discriminator","url":"https://github.com/kunheek/style-aware-discriminator"},{"title":"jychoi118/toward_spatial_unbiased","url":"https://github.com/jychoi118/toward_spatial_unbiased"},{"title":"duskvirkus/alias-free-gan-pytorch-lightning","url":"https://github.com/duskvirkus/alias-free-gan-pytorch-lightning"},{"title":"duskvirkus/alias-free-gan","url":"https://github.com/duskvirkus/alias-free-gan"},{"title":"lzhbrian/alias-free-gan-explanation","url":"https://github.com/lzhbrian/alias-free-gan-explanation"}],"syntology":{"n":31,"n_ran":30,"n_constructed":0,"n_ran_checked":20,"n_instrument":10,"n_unverified":1,"n_honours":5,"n_violates":4,"n_no_contract":11,"n_pointer_only":12,"phrase":"30 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 4 violated, 11 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/alias-free-generative-adversarial-networks#ran","syntology_url":"https://syntology.ai/paper/2106.12423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12423"}},"official":{"repos":["NVlabs/stylegan3"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-objectsroom","slug":"image-generation-on-objectsroom","dataset":"ObjectsRoom","dataset_url":"/dataset/objectsroom","rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"GENESIS-V2","paper_title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","paper_url":"/paper/genesis-v2-inferring-unordered-object","paper_date":"2021-04-20","arxiv_id":"2104.09958","code_links":[{"title":"applied-ai-lab/genesis","url":"https://github.com/applied-ai-lab/genesis"},{"title":"jinyangyuan/genesis","url":"https://github.com/jinyangyuan/genesis"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-pokemon-1024x1024","slug":"image-generation-on-pokemon-1024x1024","dataset":"Pokemon 1024x1024","dataset_url":null,"rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"StyleGAN-XL","paper_title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","paper_url":"/paper/stylegan-xl-scaling-stylegan-to-large-diverse","paper_date":"2022-02-01","arxiv_id":"2202.00273","code_links":[{"title":"autonomousvision/stylegan-xl","url":"https://github.com/autonomousvision/stylegan-xl"},{"title":"autonomousvision/stylegan_xl","url":"https://github.com/autonomousvision/stylegan_xl"}],"syntology":{"n":19,"n_ran":16,"n_constructed":0,"n_ran_checked":5,"n_instrument":11,"n_unverified":3,"n_honours":5,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 11 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/stylegan-xl-scaling-stylegan-to-large-diverse#ran","syntology_url":"https://syntology.ai/paper/2202.00273","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.00273"}},"official":{"repos":["autonomousvision/stylegan_xl"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-shapestacks","slug":"image-generation-on-shapestacks","dataset":"ShapeStacks","dataset_url":"/dataset/shapestacks","rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"GENESIS-V2","paper_title":"GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement","paper_url":"/paper/genesis-v2-inferring-unordered-object","paper_date":"2021-04-20","arxiv_id":"2104.09958","code_links":[{"title":"applied-ai-lab/genesis","url":"https://github.com/applied-ai-lab/genesis"},{"title":"jinyangyuan/genesis","url":"https://github.com/jinyangyuan/genesis"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-stacked-mnist","slug":"image-generation-on-stacked-mnist","dataset":"Stacked MNIST","dataset_url":"/dataset/stacked-mnist","rows_in_archive":3,"metrics":["FID","Inception score"],"first_row_in_archive_order":{"model":"VAEBM","paper_title":"VAEBM: A Symbiosis between Variational Autoencoders and Energy-based Models","paper_url":"/paper/vaebm-a-symbiosis-between-variational","paper_date":"2020-10-01","arxiv_id":"2010.00654","code_links":[{"title":"NVlabs/VAEBM","url":"https://github.com/NVlabs/VAEBM"}],"syntology":{"n":9,"n_ran":6,"n_constructed":2,"n_ran_checked":3,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"6 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/vaebm-a-symbiosis-between-variational#ran","syntology_url":"https://syntology.ai/paper/2010.00654","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.00654"}},"official":{"repos":["NVlabs/VAEBM"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-tio-2-nanoparticle","slug":"image-generation-on-tio-2-nanoparticle","dataset":"TiO_2 nanoparticle","dataset_url":null,"rows_in_archive":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"F-ANcGAN","paper_title":"F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative Adversarial Architecture for Synthetic Image Generation of Nanoparticles","paper_url":"/paper/f-ancgan-an-attention-enhanced-cycle","paper_date":"2025-05-23","arxiv_id":"2505.18106","code_links":[{"title":"Pal-kid404/F-ANcGAN","url":"https://github.com/Pal-kid404/F-ANcGAN"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-afhq-v2-64x64","slug":"image-generation-on-afhq-v2-64x64","dataset":"AFHQ-v2 64x64","dataset_url":null,"rows_in_archive":2,"metrics":["FID","NFE"],"first_row_in_archive_order":{"model":"SiDA-EDM","paper_title":"Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step","paper_url":"/paper/adversarial-score-identity-distillation","paper_date":"2024-10-19","arxiv_id":"2410.14919","code_links":[{"title":"mingyuanzhou/sid","url":"https://github.com/mingyuanzhou/sid"},{"title":"mingyuanzhou/sid-lsg","url":"https://github.com/mingyuanzhou/sid-lsg"}],"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adversarial-score-identity-distillation#ran","syntology_url":"https://syntology.ai/paper/2410.14919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14919"}},"official":{"repos":["mingyuanzhou/sid"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-ffhq-64x64","slug":"image-generation-on-ffhq-64x64","dataset":"FFHQ 64x64","dataset_url":null,"rows_in_archive":2,"metrics":["FID","NFE"],"first_row_in_archive_order":{"model":"SiDA-EDM","paper_title":"Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step","paper_url":"/paper/adversarial-score-identity-distillation","paper_date":"2024-10-19","arxiv_id":"2410.14919","code_links":[{"title":"mingyuanzhou/sid","url":"https://github.com/mingyuanzhou/sid"},{"title":"mingyuanzhou/sid-lsg","url":"https://github.com/mingyuanzhou/sid-lsg"}],"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adversarial-score-identity-distillation#ran","syntology_url":"https://syntology.ai/paper/2410.14919","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.14919"}},"official":{"repos":["mingyuanzhou/sid"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/image-generation-on-inaturalist-2019","slug":"image-generation-on-inaturalist-2019","dataset":"iNaturalist 2019","dataset_url":"/dataset/inaturalist","rows_in_archive":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"StyeGAN2 + NoisyTwins","paper_title":"NoisyTwins: Class-Consistent and Diverse Image Generation through StyleGANs","paper_url":"/paper/noisytwins-class-consistent-and-diverse-image","paper_date":"2023-04-12","arxiv_id":"2304.05866","code_links":[{"title":"val-iisc/NoisyTwins","url":"https://github.com/val-iisc/NoisyTwins"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-lsun-bedroom-128-x-128","slug":"image-generation-on-lsun-bedroom-128-x-128","dataset":"LSUN Bedroom 128 x 128","dataset_url":"/dataset/lsun","rows_in_archive":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"LadaGAN","paper_title":"Efficient generative adversarial networks using linear additive-attention Transformers","paper_url":"/paper/efficient-generative-adversarial-networks","paper_date":"2024-01-17","arxiv_id":"2401.09596","code_links":[{"title":"milmor/ladagan","url":"https://github.com/milmor/ladagan"},{"title":"milmor/LadaGAN-pytorch","url":"https://github.com/milmor/LadaGAN-pytorch"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-lsun-car-512-x-384","slug":"image-generation-on-lsun-car-512-x-384","dataset":"LSUN Car 512 x 384","dataset_url":"/dataset/lsun","rows_in_archive":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"Polarity-StyleGAN2","paper_title":"Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values","paper_url":"/paper/polarity-sampling-quality-and-diversity","paper_date":"2022-03-03","arxiv_id":"2203.01993","code_links":[{"title":"AhmedImtiazPrio/magnet-polarity","url":"https://github.com/AhmedImtiazPrio/magnet-polarity"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-oxford-102-flowers-256-x","slug":"image-generation-on-oxford-102-flowers-256-x","dataset":"Oxford 102 Flowers 256 x 256","dataset_url":"/dataset/oxford-102-flower","rows_in_archive":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"Projected GAN","paper_title":"Projected GANs Converge Faster","paper_url":"/paper/projected-gans-converge-faster","paper_date":"2021-11-01","arxiv_id":"2111.01007","code_links":[{"title":"autonomousvision/projected_gan","url":"https://github.com/autonomousvision/projected_gan"},{"title":"dome272/ProjectedGAN-pytorch","url":"https://github.com/dome272/ProjectedGAN-pytorch"},{"title":"tsubota-kouga/ProjectedGAN","url":"https://github.com/tsubota-kouga/ProjectedGAN"}],"syntology":{"n":49,"n_ran":38,"n_constructed":14,"n_ran_checked":20,"n_instrument":18,"n_unverified":11,"n_honours":3,"n_violates":0,"n_no_contract":17,"n_pointer_only":6,"phrase":"38 ran (of which 14 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 18 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/projected-gans-converge-faster#ran","syntology_url":"https://syntology.ai/paper/2111.01007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01007"}},"official":{"repos":["autonomousvision/projected_gan"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-rc-49","slug":"image-generation-on-rc-49","dataset":"RC-49","dataset_url":"/dataset/rc-49","rows_in_archive":2,"metrics":["Intra-FID"],"first_row_in_archive_order":{"model":"cDR-RS","paper_title":"Efficient Subsampling of Realistic Images From GANs Conditional on a Class or a Continuous Variable","paper_url":"/paper/efficient-subsampling-for-generating-high","paper_date":"2021-03-20","arxiv_id":"2103.11166","code_links":[{"title":"UBCDingXin/cDR-RS","url":"https://github.com/UBCDingXin/cDR-RS"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-1078-people-3d-faces","slug":"image-generation-on-1078-people-3d-faces","dataset":"1,078 People 3D Faces Collection Data","dataset_url":null,"rows_in_archive":1,"metrics":["10%"],"first_row_in_archive_order":{"model":"Sessiz çığlık","paper_title":"0-Hecke modules for row-strict dual immaculate functions","paper_url":null,"paper_date":"2022-02-01","arxiv_id":"2202.00708","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-generation-on-25-imagenet-128x128","slug":"image-generation-on-25-imagenet-128x128","dataset":"25% ImageNet 128x128","dataset_url":null,"rows_in_archive":1,"metrics":["FID","IS"],"first_row_in_archive_order":{"model":"LeCAM + DA","paper_title":"Regularizing Generative Adversarial Networks under Limited Data","paper_url":"/paper/regularizing-generative-adversarial-networks","paper_date":"2021-04-07","arxiv_id":"2104.03310","code_links":[{"title":"google/lecam-gan","url":"https://github.com/google/lecam-gan"}],"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/regularizing-generative-adversarial-networks#ran","syntology_url":"https://syntology.ai/paper/2104.03310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.03310"}},"official":{"repos":["google/lecam-gan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["found_in_text","official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-ai-ch-priichyaa","slug":"image-generation-on-ai-ch-priichyaa","dataset":"‘ไอซ์ ปรีชญา’ ลืมปิดไลฟ์สดตอนอาบน้ำ คลิปถูกคนดีแชร์ออนไลน์","dataset_url":null,"rows_in_archive":1,"metrics":["0-shot MRR"],"first_row_in_archive_order":{"model":"as","paper_title":"Image Generation From Small Datasets via Batch Statistics Adaptation","paper_url":"/paper/image-generation-from-small-datasets-via","paper_date":"2019-04-03","arxiv_id":"1904.01774","code_links":[{"title":"MiaoyunZhao/GANTransferLimitedData","url":"https://github.com/MiaoyunZhao/GANTransferLimitedData"},{"title":"nogu-atsu/small-dataset-image-generation","url":"https://github.com/nogu-atsu/small-dataset-image-generation"},{"title":"apple2373/PyTorch-SmallGAN","url":"https://github.com/apple2373/PyTorch-SmallGAN"},{"title":"mevius6/smallgan","url":"https://github.com/mevius6/smallgan"}],"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/image-generation-from-small-datasets-via#ran","syntology_url":"https://syntology.ai/paper/1904.01774","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.01774"}},"official":{"repos":["nogu-atsu/small-dataset-image-generation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/image-generation-on-celeba-3","slug":"image-generation-on-celeba-3","dataset":"CelebA","dataset_url":"/dataset/celeba","rows_in_archive":1,"metrics":["bpd (8-bits)"],"first_row_in_archive_order":{"model":"FInCFlow","paper_title":"FInC Flow: Fast and Invertible $k \\times k$ Convolutions for Normalizing Flows","paper_url":"/paper/finc-flow-fast-and-invertible-k-times-k","paper_date":"2023-01-23","arxiv_id":"2301.09266","code_links":[],"syntology":null}},{"leaderboard":"/sota/image-generation-on-celeba-hq","slug":"image-generation-on-celeba-hq","dataset":"CelebA-HQ","dataset_url":"/dataset/celeba-hq","rows_in_archive":1,"metrics":["FLD"],"first_row_in_archive_order":{"model":"DDPM","paper_title":"Normalizing Flow-Based Metric for Image Generation","paper_url":"/paper/normalizing-flow-based-metric-for-image","paper_date":"2024-10-02","arxiv_id":"2410.02004","code_links":[{"title":"pranavphoenix/FLD","url":"https://github.com/pranavphoenix/FLD"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-celeba-hq-512x512","slug":"image-generation-on-celeba-hq-512x512","dataset":"CelebA-HQ 512x512","dataset_url":"/dataset/celeba-hq","rows_in_archive":1,"metrics":["FID","NFE","Recall"],"first_row_in_archive_order":{"model":"WaveDiff","paper_title":"Wavelet Diffusion Models are fast and scalable Image Generators","paper_url":"/paper/wavelet-diffusion-models-are-fast-and","paper_date":"2022-11-29","arxiv_id":"2211.16152","code_links":[{"title":"vinairesearch/wavediff","url":"https://github.com/vinairesearch/wavediff"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-cityscapes-25k-256x512","slug":"image-generation-on-cityscapes-25k-256x512","dataset":"Cityscapes-25K 256x512","dataset_url":"/dataset/cityscapes","rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"SB-GAN","paper_title":"Semantic Bottleneck Scene Generation","paper_url":"/paper/semantic-bottleneck-scene-generation","paper_date":"2019-11-26","arxiv_id":"1911.11357","code_links":[{"title":"azadis/SB-GAN","url":"https://github.com/azadis/SB-GAN"},{"title":"liorfrenkel1992/SB-GAN","url":"https://github.com/liorfrenkel1992/SB-GAN"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-cityscapes-5k-256x512","slug":"image-generation-on-cityscapes-5k-256x512","dataset":"Cityscapes-5K 256x512","dataset_url":"/dataset/cityscapes","rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"SB-GAN","paper_title":"Semantic Bottleneck Scene Generation","paper_url":"/paper/semantic-bottleneck-scene-generation","paper_date":"2019-11-26","arxiv_id":"1911.11357","code_links":[{"title":"azadis/SB-GAN","url":"https://github.com/azadis/SB-GAN"},{"title":"liorfrenkel1992/SB-GAN","url":"https://github.com/liorfrenkel1992/SB-GAN"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-emnist-letters","slug":"image-generation-on-emnist-letters","dataset":"EMNIST-Letters","dataset_url":"/dataset/emnist","rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"Spiking-Diffusion","paper_title":"Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks","paper_url":"/paper/spiking-diffusion-vector-quantized-discrete","paper_date":"2023-08-20","arxiv_id":"2308.10187","code_links":[{"title":"Arktis2022/Spiking-Diffusion","url":"https://github.com/Arktis2022/Spiking-Diffusion"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-ffhq-64x64-4x-upscaling","slug":"image-generation-on-ffhq-64x64-4x-upscaling","dataset":"FFHQ 64x64 - 4x upscaling","dataset_url":"/dataset/ffhq","rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"PFGM++","paper_title":"PFGM++: Unlocking the Potential of Physics-Inspired Generative Models","paper_url":"/paper/pfgm-unlocking-the-potential-of-physics","paper_date":"2023-02-08","arxiv_id":"2302.04265","code_links":[{"title":"newbeeer/pfgmpp","url":"https://github.com/newbeeer/pfgmpp"}],"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pfgm-unlocking-the-potential-of-physics#ran","syntology_url":"https://syntology.ai/paper/2302.04265","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.04265"}},"official":{"repos":["newbeeer/pfgmpp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-gqn","slug":"image-generation-on-gqn","dataset":"GQN","dataset_url":null,"rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"GENESIS","paper_title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","paper_url":"/paper/genesis-generative-scene-inference-and","paper_date":"2019-07-30","arxiv_id":"1907.13052","code_links":[{"title":"applied-ai-lab/genesis","url":"https://github.com/applied-ai-lab/genesis"},{"title":"jinyangyuan/genesis","url":"https://github.com/jinyangyuan/genesis"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-imagenet-256x256-1","slug":"image-generation-on-imagenet-256x256-1","dataset":"ImageNet 256x256 - 1 labeled data per class","dataset_url":null,"rows_in_archive":1,"metrics":["FID-50k","sFID","IS","Precision","Recall"],"first_row_in_archive_order":{"model":"DPT","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/image-generation-on-imagenet-256x256-1-1","slug":"image-generation-on-imagenet-256x256-1-1","dataset":"ImageNet 256x256 - 1% labeled data","dataset_url":null,"rows_in_archive":1,"metrics":["FID-50k","sFID","IS","Precision","Recall"],"first_row_in_archive_order":{"model":"DPT","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/image-generation-on-imagenet-256x256-2","slug":"image-generation-on-imagenet-256x256-2","dataset":"ImageNet 256x256 - 2 labeled data per class","dataset_url":null,"rows_in_archive":1,"metrics":["FID-50k","sFID","IS","Precision","Recall"],"first_row_in_archive_order":{"model":"DPT","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/image-generation-on-imagenet-256x256-5","slug":"image-generation-on-imagenet-256x256-5","dataset":"ImageNet 256x256 - 5 labeled data per class","dataset_url":null,"rows_in_archive":1,"metrics":["FID-50k","sFID","IS","Precision","Recall"],"first_row_in_archive_order":{"model":"DPT","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/image-generation-on-indian-celebs-256-x-256","slug":"image-generation-on-indian-celebs-256-x-256","dataset":"Indian Celebs 256 x 256","dataset_url":null,"rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"MSG-StyleGAN","paper_title":"MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks","paper_url":"/paper/msg-gan-multi-scale-gradients-gan-for-more","paper_date":"2019-03-14","arxiv_id":"1903.06048","code_links":[{"title":"akanimax/BMSG-GAN","url":"https://github.com/akanimax/BMSG-GAN"},{"title":"akanimax/msg-stylegan-tf","url":"https://github.com/akanimax/msg-stylegan-tf"},{"title":"manicman1999/StyleGAN-Tensorflow-2.0","url":"https://github.com/manicman1999/StyleGAN-Tensorflow-2.0"},{"title":"Iceland-Leo/Style-MSG-GAN","url":"https://github.com/Iceland-Leo/Style-MSG-GAN"},{"title":"denizalperacar/MSG-GAN","url":"https://github.com/denizalperacar/MSG-GAN"}],"syntology":{"n":15,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/msg-gan-multi-scale-gradients-gan-for-more#ran","syntology_url":"https://syntology.ai/paper/1903.06048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.06048"}},"official":{"repos":["akanimax/msg-stylegan-tf"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/image-generation-on-kmnist","slug":"image-generation-on-kmnist","dataset":"KMNIST","dataset_url":"/dataset/kmnist","rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"Spiking-Diffusion","paper_title":"Spiking-Diffusion: Vector Quantized Discrete Diffusion Model with Spiking Neural Networks","paper_url":"/paper/spiking-diffusion-vector-quantized-discrete","paper_date":"2023-08-20","arxiv_id":"2308.10187","code_links":[{"title":"Arktis2022/Spiking-Diffusion","url":"https://github.com/Arktis2022/Spiking-Diffusion"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-landscapes-256-x-256","slug":"image-generation-on-landscapes-256-x-256","dataset":"Landscapes 256 x 256","dataset_url":null,"rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"CIPS","paper_title":"Image Generators with Conditionally-Independent Pixel Synthesis","paper_url":"/paper/image-generators-with-conditionally","paper_date":"2020-11-27","arxiv_id":"2011.13775","code_links":[{"title":"saic-mdal/CIPS","url":"https://github.com/saic-mdal/CIPS"},{"title":"taki0112/CIPS-Tensorflow","url":"https://github.com/taki0112/CIPS-Tensorflow"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-llvip","slug":"image-generation-on-llvip","dataset":"LLVIP","dataset_url":"/dataset/llvip","rows_in_archive":1,"metrics":["PSNR","SSIM"],"first_row_in_archive_order":{"model":"pix2pix","paper_title":"LLVIP: A Visible-infrared Paired Dataset for Low-light Vision","paper_url":"/paper/llvip-a-visible-infrared-paired-dataset-for","paper_date":"2021-08-24","arxiv_id":"2108.10831","code_links":[{"title":"bupt-ai-cz/LLVIP","url":"https://github.com/bupt-ai-cz/LLVIP"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-lsun","slug":"image-generation-on-lsun","dataset":"LSUN","dataset_url":"/dataset/lsun","rows_in_archive":1,"metrics":["Average FID"],"first_row_in_archive_order":{"model":"BigGAN + gSR","paper_title":"Improving GANs for Long-Tailed Data through Group Spectral Regularization","paper_url":"/paper/improving-gans-for-long-tailed-data-through","paper_date":"2022-08-21","arxiv_id":"2208.09932","code_links":[{"title":"val-iisc/gSRGAN","url":"https://github.com/val-iisc/gSRGAN"}],"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/improving-gans-for-long-tailed-data-through#ran","syntology_url":"https://syntology.ai/paper/2208.09932","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.09932"}},"official":{"repos":["val-iisc/gSRGAN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}}},{"leaderboard":"/sota/image-generation-on-lsun-car-256-x-256","slug":"image-generation-on-lsun-car-256-x-256","dataset":"LSUN Car 256 x 256","dataset_url":"/dataset/lsun","rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"StyleGAN2","paper_title":"Analyzing and Improving the Image Quality of StyleGAN","paper_url":"/paper/analyzing-and-improving-the-image-quality-of","paper_date":"2019-12-03","arxiv_id":"1912.04958","code_links":[{"title":"labmlai/annotated_deep_learning_paper_implementations","url":"https://github.com/labmlai/annotated_deep_learning_paper_implementations"},{"title":"NVlabs/stylegan2","url":"https://github.com/NVlabs/stylegan2"},{"title":"lucidrains/stylegan2-pytorch","url":"https://github.com/lucidrains/stylegan2-pytorch"},{"title":"rosinality/stylegan2-pytorch","url":"https://github.com/rosinality/stylegan2-pytorch"},{"title":"open-mmlab/mmgeneration","url":"https://github.com/open-mmlab/mmgeneration"},{"title":"toshas/torch-fidelity","url":"https://github.com/toshas/torch-fidelity"},{"title":"manicman1999/StyleGAN2-Tensorflow-2.0","url":"https://github.com/manicman1999/StyleGAN2-Tensorflow-2.0"},{"title":"e4s2022/e4s","url":"https://github.com/e4s2022/e4s"},{"title":"rolux/stylegan2encoder","url":"https://github.com/rolux/stylegan2encoder"},{"title":"woctezuma/stylegan2-projecting-images","url":"https://github.com/woctezuma/stylegan2-projecting-images"},{"title":"minyoungg/pix2latent","url":"https://github.com/minyoungg/pix2latent"},{"title":"JCBrouwer/maua-stylegan2","url":"https://github.com/JCBrouwer/maua-stylegan2"},{"title":"eps696/stylegan2","url":"https://github.com/eps696/stylegan2"},{"title":"rosasalberto/StyleGAN2-TensorFlow-2.x","url":"https://github.com/rosasalberto/StyleGAN2-TensorFlow-2.x"},{"title":"aydao/stylegan2-surgery","url":"https://github.com/aydao/stylegan2-surgery"},{"title":"kunheek/style-aware-discriminator","url":"https://github.com/kunheek/style-aware-discriminator"},{"title":"tomguluson92/StyleGAN2_PyTorch","url":"https://github.com/tomguluson92/StyleGAN2_PyTorch"},{"title":"dzld00/pytorch-manifold-matching","url":"https://github.com/dzld00/pytorch-manifold-matching"},{"title":"lukemelas/unsupervised-image-segmentation","url":"https://github.com/lukemelas/unsupervised-image-segmentation"},{"title":"robertluxemburg/stylegan2encoder","url":"https://github.com/robertluxemburg/stylegan2encoder"},{"title":"huangzh13/StyleGAN2.pytorch","url":"https://github.com/huangzh13/StyleGAN2.pytorch"},{"title":"autonomousvision/frequency_bias","url":"https://github.com/autonomousvision/frequency_bias"},{"title":"cyrilzakka/stylegan2-tpu","url":"https://github.com/cyrilzakka/stylegan2-tpu"},{"title":"EmptySamurai/pytorch-reconet","url":"https://github.com/EmptySamurai/pytorch-reconet"},{"title":"woctezuma/steam-stylegan2-ada","url":"https://github.com/woctezuma/steam-stylegan2-ada"},{"title":"Di-Is/stylegan2-ada-pytorch","url":"https://github.com/Di-Is/stylegan2-ada-pytorch"},{"title":"safi842/Microstructure-GAN","url":"https://github.com/safi842/Microstructure-GAN"},{"title":"phymhan/stylegan2-pytorch","url":"https://github.com/phymhan/stylegan2-pytorch"},{"title":"sidward14/gan-lab","url":"https://github.com/sidward14/gan-lab"},{"title":"amirhb29/StyleGAN2_Style-Mixing","url":"https://github.com/amirhb29/StyleGAN2_Style-Mixing"},{"title":"christophmeyer/stylegan2-tf2","url":"https://github.com/christophmeyer/stylegan2-tf2"},{"title":"Ajasra/TattooStyleGAN2","url":"https://github.com/Ajasra/TattooStyleGAN2"},{"title":"Ajasra/tattoo","url":"https://github.com/Ajasra/tattoo"},{"title":"Xiaomao136/stylegan2-faceswap","url":"https://github.com/Xiaomao136/stylegan2-faceswap"},{"title":"Takuya-Shuto-engineer/PokemonGAN","url":"https://github.com/Takuya-Shuto-engineer/PokemonGAN"},{"title":"philcryer/randota","url":"https://github.com/philcryer/randota"},{"title":"rolux/stylegan2tpu","url":"https://github.com/rolux/stylegan2tpu"},{"title":"NariMo91/GANs-generative-art","url":"https://github.com/NariMo91/GANs-generative-art"},{"title":"nekitmm/StyleGan2","url":"https://github.com/nekitmm/StyleGan2"},{"title":"hussain18804/toonify-poc","url":"https://github.com/hussain18804/toonify-poc"},{"title":"chenqiguo/gan_replication","url":"https://github.com/chenqiguo/gan_replication"},{"title":"spacegoing/stylegan2","url":"https://github.com/spacegoing/stylegan2"},{"title":"xunings/styleganime2","url":"https://github.com/xunings/styleganime2"},{"title":"armaank/archlectures","url":"https://github.com/armaank/archlectures"},{"title":"claim-berlin/3d_stylegan_circle_of_willis","url":"https://github.com/claim-berlin/3d_stylegan_circle_of_willis"},{"title":"HighCWu/stylegan2-paddle","url":"https://github.com/HighCWu/stylegan2-paddle"},{"title":"tjwei/stylegan2_workshop","url":"https://github.com/tjwei/stylegan2_workshop"},{"title":"SpikeKing/stylegan2encoder-my","url":"https://github.com/SpikeKing/stylegan2encoder-my"},{"title":"LightNormal/StyleGAN2withGUI","url":"https://github.com/LightNormal/StyleGAN2withGUI"},{"title":"RyanWu2233/Style_GAN2_TWDNE","url":"https://github.com/RyanWu2233/Style_GAN2_TWDNE"},{"title":"yangyucheng000/StyleGAN-V2","url":"https://github.com/yangyucheng000/StyleGAN-V2"},{"title":"ch10tang/stylegan2-based-face-frontalization","url":"https://github.com/ch10tang/stylegan2-based-face-frontalization"},{"title":"alekseynp/stylegan2-pytorch","url":"https://github.com/alekseynp/stylegan2-pytorch"},{"title":"tr1pzz/stylegan2-pytorch","url":"https://github.com/tr1pzz/stylegan2-pytorch"},{"title":"mhuse/StyleGAN2LatentspaceInterpolation","url":"https://github.com/mhuse/StyleGAN2LatentspaceInterpolation"},{"title":"minyoungg/GAN-Transform-and-Project","url":"https://github.com/minyoungg/GAN-Transform-and-Project"},{"title":"simplerick/stylegan2_pytorch","url":"https://github.com/simplerick/stylegan2_pytorch"},{"title":"akashgit/stylegan2_wt","url":"https://github.com/akashgit/stylegan2_wt"},{"title":"mahbouldom/StyleGAN2","url":"https://github.com/mahbouldom/StyleGAN2"},{"title":"cwvisuals/FleshDigressions","url":"https://github.com/cwvisuals/FleshDigressions"},{"title":"cto300/stylegan2","url":"https://github.com/cto300/stylegan2"},{"title":"thwin0923/kjhij","url":"https://github.com/thwin0923/kjhij"},{"title":"hiroyasuakada/StyleGAN2-PyTorch","url":"https://github.com/hiroyasuakada/StyleGAN2-PyTorch"},{"title":"kerryvernebegeman/Kerry-Verne-Begeman","url":"https://github.com/kerryvernebegeman/Kerry-Verne-Begeman"},{"title":"Kate589/gan","url":"https://github.com/Kate589/gan"},{"title":"SzuPc/MindSpore-StyleGAN2","url":"https://github.com/SzuPc/MindSpore-StyleGAN2"},{"title":"Ajasra/stylegan2","url":"https://github.com/Ajasra/stylegan2"},{"title":"Error-code404/Random-Unreal-Face","url":"https://github.com/Error-code404/Random-Unreal-Face"},{"title":"cffo/stylegan2-encoder","url":"https://github.com/cffo/stylegan2-encoder"},{"title":"b4nn3d/stylegan2encoder","url":"https://github.com/b4nn3d/stylegan2encoder"},{"title":"jdbugs/stylegan2encoder","url":"https://github.com/jdbugs/stylegan2encoder"},{"title":"yuzq97/starter_project","url":"https://github.com/yuzq97/starter_project"},{"title":"mbbrodie/stylegan2","url":"https://github.com/mbbrodie/stylegan2"},{"title":"tompaperspaceio/stylegan3","url":"https://github.com/tompaperspaceio/stylegan3"},{"title":"cbhower/style-gan-music-video","url":"https://github.com/cbhower/style-gan-music-video"},{"title":"ShreyasArthur/StyleGAN-2-with-Urban-Plans","url":"https://github.com/ShreyasArthur/StyleGAN-2-with-Urban-Plans"},{"title":"Bakikii/stylegan2-pytorch23","url":"https://github.com/Bakikii/stylegan2-pytorch23"},{"title":"RuiLiFeng/invGAN","url":"https://github.com/RuiLiFeng/invGAN"},{"title":"DaVran369/face","url":"https://github.com/DaVran369/face"},{"title":"RyanWu2233/Style_GAN2_FFHQ","url":"https://github.com/RyanWu2233/Style_GAN2_FFHQ"},{"title":"Herge/GAN2","url":"https://github.com/Herge/GAN2"},{"title":"Uemuet/imet2","url":"https://github.com/Uemuet/imet2"},{"title":"Uemuet/gan2","url":"https://github.com/Uemuet/gan2"},{"title":"Uemuet/stylegan2","url":"https://github.com/Uemuet/stylegan2"},{"title":"Uemuet/imet","url":"https://github.com/Uemuet/imet"},{"title":"cbritom/GAN","url":"https://github.com/cbritom/GAN"},{"title":"Uemuet/-gan","url":"https://github.com/Uemuet/-gan"},{"title":"xx88xx/stylegan2ky","url":"https://github.com/xx88xx/stylegan2ky"},{"title":"bgtripp/stylegan2glacier","url":"https://github.com/bgtripp/stylegan2glacier"},{"title":"NawafAlsuwailem/artathon_code","url":"https://github.com/NawafAlsuwailem/artathon_code"},{"title":"kh12lee/kh_lee","url":"https://github.com/kh12lee/kh_lee"},{"title":"Heliang-Zheng/Style2","url":"https://github.com/Heliang-Zheng/Style2"},{"title":"ohomburg/stylegan","url":"https://github.com/ohomburg/stylegan"},{"title":"jdbugs/stylegan2","url":"https://github.com/jdbugs/stylegan2"},{"title":"Uemuet/stylegan22","url":"https://github.com/Uemuet/stylegan22"},{"title":"Bakikii/stylegan2","url":"https://github.com/Bakikii/stylegan2"},{"title":"santoshchaurasiyacs/StyleGANv2","url":"https://github.com/santoshchaurasiyacs/StyleGANv2"},{"title":"srinivas1857-ton/toonify-poc","url":"https://github.com/srinivas1857-ton/toonify-poc"},{"title":"yyusuf3d/StyleGAN2","url":"https://github.com/yyusuf3d/StyleGAN2"},{"title":"amberkboulton/StyleGAN3","url":"https://github.com/amberkboulton/StyleGAN3"},{"title":"dkn16/stylegan2-pytorch","url":"https://github.com/dkn16/stylegan2-pytorch"},{"title":"erikakaeri/asdf","url":"https://github.com/erikakaeri/asdf"},{"title":"SiavashCS/sgan_simple","url":"https://github.com/SiavashCS/sgan_simple"},{"title":"erikakaeri/StyleGAN2","url":"https://github.com/erikakaeri/StyleGAN2"},{"title":"XieBaoshi/stylegan2","url":"https://github.com/XieBaoshi/stylegan2"},{"title":"Ichi-Mark-Kate/Cowboy-StyleGAN-2","url":"https://github.com/Ichi-Mark-Kate/Cowboy-StyleGAN-2"},{"title":"b4nn3d/stylegan2","url":"https://github.com/b4nn3d/stylegan2"},{"title":"jimzers/stylegan2-colabs","url":"https://github.com/jimzers/stylegan2-colabs"},{"title":"mmetaa/stylegan2","url":"https://github.com/mmetaa/stylegan2"},{"title":"a-mcego/stylegannish","url":"https://github.com/a-mcego/stylegannish"},{"title":"babyboy201/StyleGAN2","url":"https://github.com/babyboy201/StyleGAN2"},{"title":"adelliax/StyleGAN2","url":"https://github.com/adelliax/StyleGAN2"},{"title":"hanehein921/StyleGAN2","url":"https://github.com/hanehein921/StyleGAN2"},{"title":"RuiLiFeng/noise","url":"https://github.com/RuiLiFeng/noise"},{"title":"thomaspool97/StyleGAN2","url":"https://github.com/thomaspool97/StyleGAN2"},{"title":"sahidrahmanxx12/TEMPEK","url":"https://github.com/sahidrahmanxx12/TEMPEK"},{"title":"luckyfarnon/StyleGAN22","url":"https://github.com/luckyfarnon/StyleGAN22"},{"title":"gori1x62/StyleGAN2","url":"https://github.com/gori1x62/StyleGAN2"},{"title":"benguk46/StyleGAN2","url":"https://github.com/benguk46/StyleGAN2"},{"title":"RuiLiFeng/LAE","url":"https://github.com/RuiLiFeng/LAE"},{"title":"jazzup6176/StyleGAN1","url":"https://github.com/jazzup6176/StyleGAN1"},{"title":"grunnery/StyleGAN2","url":"https://github.com/grunnery/StyleGAN2"},{"title":"lucasgb98/StyleGAN2","url":"https://github.com/lucasgb98/StyleGAN2"},{"title":"cwvisuals/StyleGAN2","url":"https://github.com/cwvisuals/StyleGAN2"},{"title":"Nirav-Agarwal/GANs","url":"https://github.com/Nirav-Agarwal/GANs"},{"title":"ps-dban/Gradient-Workflows-Tutorial","url":"https://github.com/ps-dban/Gradient-Workflows-Tutorial"}],"syntology":{"n":92,"n_ran":68,"n_constructed":0,"n_ran_checked":48,"n_instrument":20,"n_unverified":24,"n_honours":4,"n_violates":6,"n_no_contract":38,"n_pointer_only":25,"phrase":"68 ran (of which 0 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 6 violated, 38 with no contract checked; 20 where Syntology's instrument failed) · 24 unverified","sample_list":"/paper/analyzing-and-improving-the-image-quality-of#ran","syntology_url":"https://syntology.ai/paper/1912.04958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.04958"}},"official":{"repos":["NVlabs/stylegan2"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}}},{"leaderboard":"/sota/image-generation-on-lsun-tower-64x64","slug":"image-generation-on-lsun-tower-64x64","dataset":"LSUN tower 64x64","dataset_url":null,"rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"DDPM-IP","paper_title":"Input Perturbation Reduces Exposure Bias in Diffusion Models","paper_url":"/paper/input-perturbation-reduces-exposure-bias-in","paper_date":"2023-01-27","arxiv_id":"2301.11706","code_links":[{"title":"forever208/ddpm-ip","url":"https://github.com/forever208/ddpm-ip"}],"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/input-perturbation-reduces-exposure-bias-in#ran","syntology_url":"https://syntology.ai/paper/2301.11706","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.11706"}},"official":{"repos":["forever208/ddpm-ip"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}}},{"leaderboard":"/sota/image-generation-on-multi-dsprites","slug":"image-generation-on-multi-dsprites","dataset":"Multi-dSprites","dataset_url":"/dataset/multi-dsprites","rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"GENESIS","paper_title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","paper_url":"/paper/genesis-generative-scene-inference-and","paper_date":"2019-07-30","arxiv_id":"1907.13052","code_links":[{"title":"applied-ai-lab/genesis","url":"https://github.com/applied-ai-lab/genesis"},{"title":"jinyangyuan/genesis","url":"https://github.com/jinyangyuan/genesis"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-nasa-perseverance","slug":"image-generation-on-nasa-perseverance","dataset":"NASA Perseverance","dataset_url":"/dataset/nasa-perseverance","rows_in_archive":1,"metrics":["MAE Signature","MAE log-signature","RMSE Signature","RMSE log-signature"],"first_row_in_archive_order":{"model":"Stylegan2-ada","paper_title":"Signature and Log-signature for the Study of Empirical Distributions Generated with GANs","paper_url":"/paper/signature-and-log-signature-for-the-study-of","paper_date":"2022-03-07","arxiv_id":"2203.03226","code_links":[{"title":"decurtoydiaz/signatures","url":"https://github.com/decurtoydiaz/signatures"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-oxford-102-flowers-1","slug":"image-generation-on-oxford-102-flowers-1","dataset":"Oxford 102 Flowers 128x128","dataset_url":null,"rows_in_archive":1,"metrics":["FID","IS"],"first_row_in_archive_order":{"model":"QSNGAN","paper_title":"Quaternion Generative Adversarial Networks","paper_url":"/paper/quaternion-generative-adversarial-networks","paper_date":"2021-04-19","arxiv_id":"2104.09630","code_links":[{"title":"eleGAN23/QVAE","url":"https://github.com/eleGAN23/QVAE"},{"title":"ispamm/hi2i","url":"https://github.com/ispamm/hi2i"},{"title":"eleGAN23/QGAN","url":"https://github.com/eleGAN23/QGAN"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-satellite-buildings-256-x","slug":"image-generation-on-satellite-buildings-256-x","dataset":"Satellite-Buildings 256 x 256","dataset_url":null,"rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"CIPS","paper_title":"Image Generators with Conditionally-Independent Pixel Synthesis","paper_url":"/paper/image-generators-with-conditionally","paper_date":"2020-11-27","arxiv_id":"2011.13775","code_links":[{"title":"saic-mdal/CIPS","url":"https://github.com/saic-mdal/CIPS"},{"title":"taki0112/CIPS-Tensorflow","url":"https://github.com/taki0112/CIPS-Tensorflow"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-satellite-landscapes-256","slug":"image-generation-on-satellite-landscapes-256","dataset":"Satellite-Landscapes 256 x 256","dataset_url":null,"rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"CIPS","paper_title":"Image Generators with Conditionally-Independent Pixel Synthesis","paper_url":"/paper/image-generators-with-conditionally","paper_date":"2020-11-27","arxiv_id":"2011.13775","code_links":[{"title":"saic-mdal/CIPS","url":"https://github.com/saic-mdal/CIPS"},{"title":"taki0112/CIPS-Tensorflow","url":"https://github.com/taki0112/CIPS-Tensorflow"}],"syntology":null}},{"leaderboard":"/sota/image-generation-on-sdss-galaxies","slug":"image-generation-on-sdss-galaxies","dataset":"SDSS Galaxies","dataset_url":"/dataset/sdss-galaxies","rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"AstroDDPM","paper_title":"Realistic galaxy image simulation via score-based generative models","paper_url":"/paper/realistic-galaxy-image-simulation-via-score","paper_date":"2021-11-02","arxiv_id":"2111.01713","code_links":[{"title":"Smith42/astroddpm","url":"https://github.com/Smith42/astroddpm"},{"title":"smith42/synthetic-galaxy-distance","url":"https://github.com/smith42/synthetic-galaxy-distance"}],"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":2,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/realistic-galaxy-image-simulation-via-score#ran","syntology_url":"https://syntology.ai/paper/2111.01713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.01713"}},"official":{"repos":["Smith42/astroddpm","smith42/synthetic-galaxy-distance"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/imagenet","name":"ImageNet","full_name":"","num_papers_in_archive":15430},{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/cityscapes","name":"Cityscapes","full_name":"","num_papers_in_archive":3702},{"url":"/dataset/celeba","name":"CelebA","full_name":"CelebFaces Attributes Dataset","num_papers_in_archive":3477},{"url":"/dataset/fashion-mnist","name":"Fashion-MNIST","full_name":"","num_papers_in_archive":3202},{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/ffhq","name":"FFHQ","full_name":"Flickr-Faces-HQ","num_papers_in_archive":1468},{"url":"/dataset/oxford-102-flower","name":"Oxford 102 Flower","full_name":"102 Category Flower Dataset","num_papers_in_archive":1307},{"url":"/dataset/stl-10","name":"STL-10","full_name":"Self-Taught Learning 10","num_papers_in_archive":1092},{"url":"/dataset/celeba-hq","name":"CelebA-HQ","full_name":"CelebA-HQ","num_papers_in_archive":954},{"url":"/dataset/lsun","name":"LSUN","full_name":"Large-scale Scene UNderstanding Challenge","num_papers_in_archive":867},{"url":"/dataset/stanford-cars","name":"Stanford Cars","full_name":"","num_papers_in_archive":790},{"url":"/dataset/clevr","name":"CLEVR","full_name":"Compositional Language and Elementary Visual Reasoning","num_papers_in_archive":657},{"url":"/dataset/inaturalist","name":"iNaturalist","full_name":"","num_papers_in_archive":603},{"url":"/dataset/perceptual-similarity","name":"Perceptual Similarity","full_name":"","num_papers_in_archive":452},{"url":"/dataset/replica","name":"Replica","full_name":"","num_papers_in_archive":414},{"url":"/dataset/faceforensics-1","name":"FaceForensics++","full_name":"","num_papers_in_archive":368},{"url":"/dataset/afhq","name":"AFHQ","full_name":"Animal Faces-HQ","num_papers_in_archive":327},{"url":"/dataset/densepose","name":"DensePose","full_name":"DensePose-COCO","num_papers_in_archive":265},{"url":"/dataset/emnist","name":"EMNIST","full_name":"Extended MNIST","num_papers_in_archive":264},{"url":"/dataset/celebamask-hq","name":"CelebAMask-HQ","full_name":"","num_papers_in_archive":164},{"url":"/dataset/vizdoom","name":"VizDoom","full_name":"VizDoom","num_papers_in_archive":156},{"url":"/dataset/llvip","name":"LLVIP","full_name":"A Visible-infrared Paired Dataset for Low-light Vision","num_papers_in_archive":116},{"url":"/dataset/structured3d","name":"Structured3D","full_name":"","num_papers_in_archive":85},{"url":"/dataset/arkitscenes","name":"ARKitScenes","full_name":"","num_papers_in_archive":75},{"url":"/dataset/metfaces","name":"MetFaces","full_name":"","num_papers_in_archive":75},{"url":"/dataset/recipe1m-1","name":"Recipe1M+","full_name":"Recipe1M+","num_papers_in_archive":68},{"url":"/dataset/stanford-dogs","name":"Stanford Dogs","full_name":"Stanford Dogs","num_papers_in_archive":57},{"url":"/dataset/vln-ce","name":"VLN-CE","full_name":"Vision-and-Language Navigation in Continuous Environments","num_papers_in_archive":55},{"url":"/dataset/stacked-mnist","name":"Stacked MNIST","full_name":"Stacked MNIST","num_papers_in_archive":43},{"url":"/dataset/fashion-gen","name":"Fashion-Gen","full_name":"","num_papers_in_archive":36},{"url":"/dataset/gvgai","name":"GVGAI","full_name":"General Video Game AI","num_papers_in_archive":36},{"url":"/dataset/ut-zappos50k","name":"UT Zappos50K","full_name":"","num_papers_in_archive":32},{"url":"/dataset/multi-dsprites","name":"Multi-dSprites","full_name":"","num_papers_in_archive":31},{"url":"/dataset/lhq","name":"LHQ","full_name":"Landscapes High-Quality","num_papers_in_archive":27},{"url":"/dataset/multi-modal-celeba-hq-1","name":"Multi-Modal CelebA-HQ","full_name":"","num_papers_in_archive":27},{"url":"/dataset/mmact","name":"MMAct","full_name":"","num_papers_in_archive":23},{"url":"/dataset/shapestacks","name":"ShapeStacks","full_name":"","num_papers_in_archive":22},{"url":"/dataset/wise","name":"WISE","full_name":"","num_papers_in_archive":22},{"url":"/dataset/bci","name":"BCI","full_name":"Breast Cancer Immunohistochemical Image Generation","num_papers_in_archive":19},{"url":"/dataset/activitynet-entities-1","name":"ActivityNet Entities","full_name":null,"num_papers_in_archive":18},{"url":"/dataset/whoops","name":"WHOOPS!","full_name":"","num_papers_in_archive":14},{"url":"/dataset/binarized-mnist","name":"Binarized MNIST","full_name":"","num_papers_in_archive":10},{"url":"/dataset/stylegan-human","name":"StyleGAN-Human","full_name":"","num_papers_in_archive":10},{"url":"/dataset/kmnist","name":"KMNIST","full_name":"","num_papers_in_archive":9},{"url":"/dataset/artbench-10","name":"ArtBench-10 (32x32)","full_name":"","num_papers_in_archive":7},{"url":"/dataset/stylegallery","name":"StyleGallery","full_name":"","num_papers_in_archive":7},{"url":"/dataset/chinesefoodnet","name":"ChineseFoodNet","full_name":"","num_papers_in_archive":6},{"url":"/dataset/youtube-driving","name":"YouTube Driving","full_name":"","num_papers_in_archive":6},{"url":"/dataset/matsynth","name":"MatSynth","full_name":"","num_papers_in_archive":5},{"url":"/dataset/objectsroom","name":"ObjectsRoom","full_name":"","num_papers_in_archive":5},{"url":"/dataset/rc-49","name":"RC-49","full_name":"","num_papers_in_archive":5},{"url":"/dataset/streetstyle","name":"StreetStyle","full_name":"","num_papers_in_archive":5},{"url":"/dataset/textatlaseval","name":"TextAtlasEval","full_name":"","num_papers_in_archive":5},{"url":"/dataset/figr-8","name":"FIGR-8","full_name":"","num_papers_in_archive":4},{"url":"/dataset/kvasir-vqa","name":"Kvasir-VQA","full_name":"A Text-Image Pair GI Tract Dataset","num_papers_in_archive":3},{"url":"/dataset/qst","name":"QST","full_name":"Quick Sky Time","num_papers_in_archive":3},{"url":"/dataset/gpscap","name":"SCapRepo","full_name":"Google Play Screenshot Caption","num_papers_in_archive":3},{"url":"/dataset/sketchhairsalon","name":"SketchHairSalon","full_name":"","num_papers_in_archive":3},{"url":"/dataset/entigen","name":"ENTIGEN","full_name":"Ethical NaTural Language Interventions in Text-to-Image GENeration","num_papers_in_archive":2},{"url":"/dataset/evalmuse-40k","name":"Evalmuse-40k","full_name":"","num_papers_in_archive":2},{"url":"/dataset/boombox","name":"Boombox","full_name":"","num_papers_in_archive":1},{"url":"/dataset/colorsvg-100k","name":"ColorSVG-100K","full_name":"","num_papers_in_archive":1},{"url":"/dataset/dataset-for-annotated-hands","name":"Dataset for Annotated Hands","full_name":"","num_papers_in_archive":1},{"url":"/dataset/geometricshapes14k","name":"geometricShapes14k","full_name":"Images made up of geometric shapes - ControlNet","num_papers_in_archive":1},{"url":"/dataset/hri","name":"HRI","full_name":"High-resolution Rainy Image","num_papers_in_archive":1},{"url":"/dataset/instructpix2pix-image-editing-dataset","name":"InstructPix2Pix Image Editing Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/large-labelled-logo-dataset-l3d","name":"Large Labelled Logo Dataset (L3D)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/nasa-perseverance","name":"NASA Perseverance","full_name":"","num_papers_in_archive":1},{"url":"/dataset/pressurepose","name":"PressurePose","full_name":"","num_papers_in_archive":1},{"url":"/dataset/sdss-galaxies","name":"SDSS Galaxies","full_name":"SDSS galaxies as imaged by DESI","num_papers_in_archive":1},{"url":"/dataset/spot-10","name":"SPOT-10","full_name":"Animal Pattern Benchmark Dataset for Machine Learning Algorithms","num_papers_in_archive":1},{"url":"/dataset/textatlas5m","name":"TextAtlas5M","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vggface2-hq","name":"VGGFace2 HQ","full_name":"VGGFace2 HQ","num_papers_in_archive":1},{"url":"/dataset/wificam","name":"WiFiCam","full_name":"","num_papers_in_archive":1},{"url":"/dataset/corn-seeds-dataset","name":"Corn Seeds Dataset","full_name":"","num_papers_in_archive":0},{"url":"/dataset/lemons-quality-control-dataset","name":"Lemons quality control dataset","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/3d-aware-image-synthesis","name":"3D-Aware Image Synthesis"},{"url":"/task/3d-generation","name":"3D Generation"},{"url":"/task/chinese-landscape-painting-generation","name":"Chinese Landscape Painting Generation"},{"url":"/task/conditional-image-generation","name":"Conditional Image Generation"},{"url":"/task/face-generation","name":"Face Generation"},{"url":"/task/handwritten-word-generation","name":"Handwritten Word Generation"},{"url":"/task/image-generation-from-scene-graphs","name":"Image Generation from Scene Graphs"},{"url":"/task/image-harmonization","name":"Image Harmonization"},{"url":"/task/image-inpainting","name":"Image Inpainting"},{"url":"/task/image-manipulation","name":"Image Manipulation"},{"url":"/task/image-to-image-translation","name":"Image-to-Image Translation"},{"url":"/task/infinite-image-generation","name":"Infinite Image Generation"},{"url":"/task/layout-to-image-generation","name":"Layout-to-Image Generation"},{"url":"/task/multi-class-one-shot-image-synthesis","name":"Multi class one-shot image synthesis"},{"url":"/task/person-reposing","name":"person reposing"},{"url":"/task/pose-guided-image-generation","name":"Pose-Guided Image Generation"},{"url":"/task/pose-transfer","name":"Pose Transfer"},{"url":"/task/roi-based-image-generation","name":"ROI-based image generation"},{"url":"/task/single-class-few-shot-image-synthesis","name":"Single class few-shot image synthesis"},{"url":"/task/text-to-image-generation","name":"Text-to-Image Generation"},{"url":"/task/text-within-image-generation","name":"Text within image generation"},{"url":"/task/user-constrained-thumbnail-generation","name":"User Constrained Thumbnail Generation"},{"url":"/task/virtual-staining","name":"Virtual Staining"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":67,"rows_per_page":100,"shown":100,"of":6689,"of_with_code":3102,"tagged_in_all":6689,"counts":{"archive_papers_tagged":6689,"with_a_code_link":3102,"where_syntology_ran_a_sample":1223,"not_listed_spam_title":0,"listed":6689,"listed_where_code_ran":1223,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1036,"every_run_a_failure_of_syntologys_instrument":187,"listed_with_a_run_with_no_instrument_failure":1036,"listed_every_run_a_failure_of_syntologys_instrument":187,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/analyzing-and-improving-the-image-quality-of","slug":"analyzing-and-improving-the-image-quality-of","title":"Analyzing and Improving the Image Quality of StyleGAN","date":"2019-12-03","arxiv_id":"1912.04958","repositories_listed":126,"syntology":{"n":92,"n_ran":68,"n_constructed":0,"n_ran_checked":48,"n_instrument":20,"n_unverified":24,"n_honours":4,"n_violates":6,"n_no_contract":38,"n_pointer_only":25,"phrase":"68 ran (of which 0 constructed an object rather than computing a result; 48 with no instrument failure: 4 honoured, 6 violated, 38 with no contract checked; 20 where Syntology's instrument failed) · 24 unverified","sample_list":"/paper/analyzing-and-improving-the-image-quality-of#ran","syntology_url":"https://syntology.ai/paper/1912.04958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.04958"}},"official":{"repos":["NVlabs/stylegan2"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/wasserstein-gan","slug":"wasserstein-gan","title":"Wasserstein GAN","date":"2017-01-26","arxiv_id":"1701.07875","repositories_listed":120,"syntology":{"n":22,"n_ran":16,"n_constructed":0,"n_ran_checked":4,"n_instrument":12,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":13,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/wasserstein-gan#ran","syntology_url":"https://syntology.ai/paper/1701.07875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.07875"}},"official":null}},{"url":"/paper/progressive-growing-of-gans-for-improved","slug":"progressive-growing-of-gans-for-improved","title":"Progressive Growing of GANs for Improved Quality, Stability, and Variation","date":"2017-10-27","arxiv_id":"1710.10196","repositories_listed":115,"syntology":{"n":89,"n_ran":58,"n_constructed":0,"n_ran_checked":41,"n_instrument":17,"n_unverified":31,"n_honours":6,"n_violates":1,"n_no_contract":34,"n_pointer_only":23,"phrase":"58 ran (of which 0 constructed an object rather than computing a result; 41 with no instrument failure: 6 honoured, 1 violated, 34 with no contract checked; 17 where Syntology's instrument failed) · 31 unverified","sample_list":"/paper/progressive-growing-of-gans-for-improved#ran","syntology_url":"https://syntology.ai/paper/1710.10196","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10196"}},"official":{"repos":["tkarras/progressive_growing_of_gans"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/improved-training-of-wasserstein-gans","slug":"improved-training-of-wasserstein-gans","title":"Improved Training of Wasserstein GANs","date":"2017-03-31","arxiv_id":"1704.00028","repositories_listed":110,"syntology":{"n":49,"n_ran":27,"n_constructed":10,"n_ran_checked":19,"n_instrument":8,"n_unverified":22,"n_honours":1,"n_violates":0,"n_no_contract":18,"n_pointer_only":20,"phrase":"27 ran (of which 10 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified","sample_list":"/paper/improved-training-of-wasserstein-gans#ran","syntology_url":"https://syntology.ai/paper/1704.00028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.00028"}},"official":{"repos":["igul222/improved_wgan_training"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/a-style-based-generator-architecture-for","slug":"a-style-based-generator-architecture-for","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","date":"2018-12-12","arxiv_id":"1812.04948","repositories_listed":83,"syntology":{"n":396,"n_ran":244,"n_constructed":147,"n_ran_checked":217,"n_instrument":27,"n_unverified":152,"n_honours":17,"n_violates":3,"n_no_contract":197,"n_pointer_only":229,"phrase":"244 ran (of which 147 constructed an object rather than computing a result; 217 with no instrument failure: 17 honoured, 3 violated, 197 with no contract checked; 27 where Syntology's instrument failed) · 152 unverified","sample_list":"/paper/a-style-based-generator-architecture-for#ran","syntology_url":"https://syntology.ai/paper/1812.04948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.04948"}},"official":{"repos":["NVlabs/ffhq-dataset","NVlabs/stylegan"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/gans-trained-by-a-two-time-scale-update-rule","slug":"gans-trained-by-a-two-time-scale-update-rule","title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","date":"2017-06-26","arxiv_id":"1706.08500","repositories_listed":71,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gans-trained-by-a-two-time-scale-update-rule#ran","syntology_url":"https://syntology.ai/paper/1706.08500","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.08500"}},"official":{"repos":["bioinf-jku/TTUR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/denoising-diffusion-probabilistic-models","slug":"denoising-diffusion-probabilistic-models","title":"Denoising Diffusion Probabilistic Models","date":"2020-06-19","arxiv_id":"2006.11239","repositories_listed":70,"syntology":{"n":253,"n_ran":186,"n_constructed":81,"n_ran_checked":142,"n_instrument":44,"n_unverified":67,"n_honours":20,"n_violates":8,"n_no_contract":114,"n_pointer_only":67,"phrase":"186 ran (of which 81 constructed an object rather than computing a result; 142 with no instrument failure: 20 honoured, 8 violated, 114 with no contract checked; 44 where Syntology's instrument failed) · 67 unverified","sample_list":"/paper/denoising-diffusion-probabilistic-models#ran","syntology_url":"https://syntology.ai/paper/2006.11239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.11239"}},"official":{"repos":["hojonathanho/diffusion"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/self-attention-generative-adversarial","slug":"self-attention-generative-adversarial","title":"Self-Attention Generative Adversarial Networks","date":"2018-05-21","arxiv_id":"1805.08318","repositories_listed":48,"syntology":{"n":81,"n_ran":46,"n_constructed":0,"n_ran_checked":40,"n_instrument":6,"n_unverified":35,"n_honours":4,"n_violates":1,"n_no_contract":35,"n_pointer_only":3,"phrase":"46 ran (of which 0 constructed an object rather than computing a result; 40 with no instrument failure: 4 honoured, 1 violated, 35 with no contract checked; 6 where Syntology's instrument failed) · 35 unverified","sample_list":"/paper/self-attention-generative-adversarial#ran","syntology_url":"https://syntology.ai/paper/1805.08318","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.08318"}},"official":{"repos":["brain-research/self-attention-gan"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/singan-learning-a-generative-model-from-a","slug":"singan-learning-a-generative-model-from-a","title":"SinGAN: Learning a Generative Model from a Single Natural Image","date":"2019-05-02","arxiv_id":"1905.01164","repositories_listed":47,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/singan-learning-a-generative-model-from-a#ran","syntology_url":"https://syntology.ai/paper/1905.01164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.01164"}},"official":{"repos":["tamarott/SinGAN"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/improved-techniques-for-training-gans","slug":"improved-techniques-for-training-gans","title":"Improved Techniques for Training GANs","date":"2016-06-10","arxiv_id":"1606.03498","repositories_listed":46,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improved-techniques-for-training-gans#ran","syntology_url":"https://syntology.ai/paper/1606.03498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.03498"}},"official":{"repos":["openai/improved-gan","openai/improved_gan"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/high-resolution-image-synthesis-with-latent","slug":"high-resolution-image-synthesis-with-latent","title":"High-Resolution Image Synthesis with Latent Diffusion Models","date":"2021-12-20","arxiv_id":"2112.10752","repositories_listed":41,"syntology":{"n":28,"n_ran":22,"n_constructed":0,"n_ran_checked":8,"n_instrument":14,"n_unverified":6,"n_honours":1,"n_violates":4,"n_no_contract":3,"n_pointer_only":10,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 4 violated, 3 with no contract checked; 14 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/high-resolution-image-synthesis-with-latent#ran","syntology_url":"https://syntology.ai/paper/2112.10752","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.10752"}},"official":null}},{"url":"/paper/generative-adversarial-text-to-image","slug":"generative-adversarial-text-to-image","title":"Generative Adversarial Text to Image Synthesis","date":"2016-05-17","arxiv_id":"1605.05396","repositories_listed":39,"syntology":{"n":19,"n_ran":15,"n_constructed":0,"n_ran_checked":8,"n_instrument":7,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":6,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/generative-adversarial-text-to-image#ran","syntology_url":"https://syntology.ai/paper/1605.05396","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.05396"}},"official":{"repos":["reedscot/icml2016"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/spectral-normalization-for-generative","slug":"spectral-normalization-for-generative","title":"Spectral Normalization for Generative Adversarial Networks","date":"2018-02-16","arxiv_id":"1802.05957","repositories_listed":38,"syntology":{"n":31,"n_ran":25,"n_constructed":9,"n_ran_checked":21,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":20,"n_pointer_only":15,"phrase":"25 ran (of which 9 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/spectral-normalization-for-generative#ran","syntology_url":"https://syntology.ai/paper/1802.05957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05957"}},"official":{"repos":["pfnet-research/sngan_projection"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","named_in_paper"]}}},{"url":"/paper/infogan-interpretable-representation-learning","slug":"infogan-interpretable-representation-learning","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","date":"2016-06-12","arxiv_id":"1606.03657","repositories_listed":38,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/infogan-interpretable-representation-learning#ran","syntology_url":"https://syntology.ai/paper/1606.03657","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.03657"}},"official":null}},{"url":"/paper/conditional-image-synthesis-with-auxiliary","slug":"conditional-image-synthesis-with-auxiliary","title":"Conditional Image Synthesis With Auxiliary Classifier GANs","date":"2016-10-30","arxiv_id":"1610.09585","repositories_listed":37,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/conditional-image-synthesis-with-auxiliary#ran","syntology_url":"https://syntology.ai/paper/1610.09585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1610.09585"}},"official":null}},{"url":"/paper/large-scale-gan-training-for-high-fidelity","slug":"large-scale-gan-training-for-high-fidelity","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","date":"2018-09-28","arxiv_id":"1809.11096","repositories_listed":35,"syntology":{"n":41,"n_ran":28,"n_constructed":0,"n_ran_checked":14,"n_instrument":14,"n_unverified":13,"n_honours":1,"n_violates":3,"n_no_contract":10,"n_pointer_only":14,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 3 violated, 10 with no contract checked; 14 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/large-scale-gan-training-for-high-fidelity#ran","syntology_url":"https://syntology.ai/paper/1809.11096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1809.11096"}},"official":null}},{"url":"/paper/density-estimation-using-real-nvp","slug":"density-estimation-using-real-nvp","title":"Density estimation using Real NVP","date":"2016-05-27","arxiv_id":"1605.08803","repositories_listed":35,"syntology":{"n":70,"n_ran":48,"n_constructed":26,"n_ran_checked":38,"n_instrument":10,"n_unverified":22,"n_honours":2,"n_violates":0,"n_no_contract":36,"n_pointer_only":33,"phrase":"48 ran (of which 26 constructed an object rather than computing a result; 38 with no instrument failure: 2 honoured, 0 violated, 36 with no contract checked; 10 where Syntology's instrument failed) · 22 unverified","sample_list":"/paper/density-estimation-using-real-nvp#ran","syntology_url":"https://syntology.ai/paper/1605.08803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.08803"}},"official":null}},{"url":"/paper/denoising-diffusion-implicit-models-1","slug":"denoising-diffusion-implicit-models-1","title":"Denoising Diffusion Implicit Models","date":"2020-10-06","arxiv_id":"2010.02502","repositories_listed":29,"syntology":{"n":50,"n_ran":33,"n_constructed":6,"n_ran_checked":15,"n_instrument":18,"n_unverified":17,"n_honours":6,"n_violates":1,"n_no_contract":8,"n_pointer_only":16,"phrase":"33 ran (of which 6 constructed an object rather than computing a result; 15 with no instrument failure: 6 honoured, 1 violated, 8 with no contract checked; 18 where Syntology's instrument failed) · 17 unverified","sample_list":"/paper/denoising-diffusion-implicit-models-1#ran","syntology_url":"https://syntology.ai/paper/2010.02502","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02502"}},"official":{"repos":["ermongroup/ddim"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/training-generative-adversarial-networks-with-2","slug":"training-generative-adversarial-networks-with-2","title":"Training Generative Adversarial Networks with Limited Data","date":"2020-06-11","arxiv_id":"2006.06676","repositories_listed":28,"syntology":{"n":29,"n_ran":21,"n_constructed":0,"n_ran_checked":19,"n_instrument":2,"n_unverified":8,"n_honours":2,"n_violates":1,"n_no_contract":16,"n_pointer_only":5,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 2 honoured, 1 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/training-generative-adversarial-networks-with-2#ran","syntology_url":"https://syntology.ai/paper/2006.06676","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.06676"}},"official":{"repos":["NVlabs/stylegan2-ada"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/glow-generative-flow-with-invertible-1x1","slug":"glow-generative-flow-with-invertible-1x1","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","date":"2018-07-09","arxiv_id":"1807.03039","repositories_listed":27,"syntology":{"n":129,"n_ran":85,"n_constructed":47,"n_ran_checked":73,"n_instrument":12,"n_unverified":44,"n_honours":3,"n_violates":0,"n_no_contract":70,"n_pointer_only":44,"phrase":"85 ran (of which 47 constructed an object rather than computing a result; 73 with no instrument failure: 3 honoured, 0 violated, 70 with no contract checked; 12 where Syntology's instrument failed) · 44 unverified","sample_list":"/paper/glow-generative-flow-with-invertible-1x1#ran","syntology_url":"https://syntology.ai/paper/1807.03039","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.03039"}},"official":{"repos":["openai/glow"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/semantic-image-synthesis-with-spatially","slug":"semantic-image-synthesis-with-spatially","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","date":"2019-03-18","arxiv_id":"1903.07291","repositories_listed":24,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":6,"n_instrument":3,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/semantic-image-synthesis-with-spatially#ran","syntology_url":"https://syntology.ai/paper/1903.07291","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.07291"}},"official":{"repos":["NVlabs/SPADE"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/adversarial-audio-synthesis","slug":"adversarial-audio-synthesis","title":"Adversarial Audio Synthesis","date":"2018-02-12","arxiv_id":"1802.04208","repositories_listed":22,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/adversarial-audio-synthesis#ran","syntology_url":"https://syntology.ai/paper/1802.04208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04208"}},"official":{"repos":["chrisdonahue/wavegan"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/instance-normalization-the-missing-ingredient","slug":"instance-normalization-the-missing-ingredient","title":"Instance Normalization: The Missing Ingredient for Fast Stylization","date":"2016-07-27","arxiv_id":"1607.08022","repositories_listed":22,"syntology":{"n":18,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":15,"n_pointer_only":1,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/instance-normalization-the-missing-ingredient#ran","syntology_url":"https://syntology.ai/paper/1607.08022","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1607.08022"}},"official":{"repos":["DmitryUlyanov/texture_nets"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/diffusion-models-beat-gans-on-image-synthesis","slug":"diffusion-models-beat-gans-on-image-synthesis","title":"Diffusion Models Beat GANs on Image Synthesis","date":"2021-05-11","arxiv_id":"2105.05233","repositories_listed":21,"syntology":{"n":50,"n_ran":33,"n_constructed":13,"n_ran_checked":29,"n_instrument":4,"n_unverified":17,"n_honours":4,"n_violates":0,"n_no_contract":25,"n_pointer_only":19,"phrase":"33 ran (of which 13 constructed an object rather than computing a result; 29 with no instrument failure: 4 honoured, 0 violated, 25 with no contract checked; 4 where Syntology's instrument failed) · 17 unverified","sample_list":"/paper/diffusion-models-beat-gans-on-image-synthesis#ran","syntology_url":"https://syntology.ai/paper/2105.05233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.05233"}},"official":{"repos":["openai/guided-diffusion"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/high-resolution-image-synthesis-and-semantic","slug":"high-resolution-image-synthesis-and-semantic","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","date":"2017-11-30","arxiv_id":"1711.11585","repositories_listed":21,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/high-resolution-image-synthesis-and-semantic#ran","syntology_url":"https://syntology.ai/paper/1711.11585","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.11585"}},"official":{"repos":["NVIDIA/pix2pixHD"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/stackgan-text-to-photo-realistic-image","slug":"stackgan-text-to-photo-realistic-image","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","date":"2016-12-10","arxiv_id":"1612.03242","repositories_listed":21,"syntology":{"n":31,"n_ran":22,"n_constructed":0,"n_ran_checked":15,"n_instrument":7,"n_unverified":9,"n_honours":2,"n_violates":1,"n_no_contract":12,"n_pointer_only":3,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 1 violated, 12 with no contract checked; 7 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/stackgan-text-to-photo-realistic-image#ran","syntology_url":"https://syntology.ai/paper/1612.03242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1612.03242"}},"official":{"repos":["hanzhanggit/StackGAN"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/elucidating-the-design-space-of-diffusion","slug":"elucidating-the-design-space-of-diffusion","title":"Elucidating the Design Space of Diffusion-Based Generative Models","date":"2022-06-01","arxiv_id":"2206.00364","repositories_listed":20,"syntology":{"n":21,"n_ran":16,"n_constructed":0,"n_ran_checked":12,"n_instrument":4,"n_unverified":5,"n_honours":7,"n_violates":0,"n_no_contract":5,"n_pointer_only":13,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 7 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/elucidating-the-design-space-of-diffusion#ran","syntology_url":"https://syntology.ai/paper/2206.00364","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.00364"}},"official":{"repos":["nvlabs/edm"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/attngan-fine-grained-text-to-image-generation","slug":"attngan-fine-grained-text-to-image-generation","title":"AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks","date":"2017-11-28","arxiv_id":"1711.10485","repositories_listed":20,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/attngan-fine-grained-text-to-image-generation#ran","syntology_url":"https://syntology.ai/paper/1711.10485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10485"}},"official":null}},{"url":"/paper/pixel-recurrent-neural-networks","slug":"pixel-recurrent-neural-networks","title":"Pixel Recurrent Neural Networks","date":"2016-01-25","arxiv_id":"1601.06759","repositories_listed":20,"syntology":{"n":29,"n_ran":19,"n_constructed":8,"n_ran_checked":17,"n_instrument":2,"n_unverified":10,"n_honours":1,"n_violates":0,"n_no_contract":16,"n_pointer_only":18,"phrase":"19 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 10 unverified","sample_list":"/paper/pixel-recurrent-neural-networks#ran","syntology_url":"https://syntology.ai/paper/1601.06759","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1601.06759"}},"official":null}},{"url":"/paper/draw-a-recurrent-neural-network-for-image","slug":"draw-a-recurrent-neural-network-for-image","title":"DRAW: A Recurrent Neural Network For Image Generation","date":"2015-02-16","arxiv_id":"1502.04623","repositories_listed":20,"syntology":{"n":18,"n_ran":9,"n_constructed":0,"n_ran_checked":3,"n_instrument":6,"n_unverified":9,"n_honours":0,"n_violates":1,"n_no_contract":2,"n_pointer_only":9,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 1 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/draw-a-recurrent-neural-network-for-image#ran","syntology_url":"https://syntology.ai/paper/1502.04623","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1502.04623"}},"official":null}},{"url":"/paper/nice-non-linear-independent-components","slug":"nice-non-linear-independent-components","title":"NICE: Non-linear Independent Components Estimation","date":"2014-10-30","arxiv_id":"1410.8516","repositories_listed":19,"syntology":{"n":27,"n_ran":24,"n_constructed":16,"n_ran_checked":19,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"24 ran (of which 16 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/nice-non-linear-independent-components#ran","syntology_url":"https://syntology.ai/paper/1410.8516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1410.8516"}},"official":null}},{"url":"/paper/improved-denoising-diffusion-probabilistic-1","slug":"improved-denoising-diffusion-probabilistic-1","title":"Improved Denoising Diffusion Probabilistic Models","date":"2021-02-18","arxiv_id":"2102.09672","repositories_listed":18,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":2,"n_honours":4,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/improved-denoising-diffusion-probabilistic-1#ran","syntology_url":"https://syntology.ai/paper/2102.09672","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.09672"}},"official":{"repos":["openai/improved-diffusion"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/began-boundary-equilibrium-generative","slug":"began-boundary-equilibrium-generative","title":"BEGAN: Boundary Equilibrium Generative Adversarial Networks","date":"2017-03-31","arxiv_id":"1703.10717","repositories_listed":18,"syntology":null},{"url":"/paper/made-masked-autoencoder-for-distribution","slug":"made-masked-autoencoder-for-distribution","title":"MADE: Masked Autoencoder for Distribution Estimation","date":"2015-02-12","arxiv_id":"1502.03509","repositories_listed":18,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":4,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/made-masked-autoencoder-for-distribution#ran","syntology_url":"https://syntology.ai/paper/1502.03509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1502.03509"}},"official":{"repos":["mgermain/MADE"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/stackgan-realistic-image-synthesis-with","slug":"stackgan-realistic-image-synthesis-with","title":"StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks","date":"2017-10-19","arxiv_id":"1710.10916","repositories_listed":16,"syntology":{"n":31,"n_ran":22,"n_constructed":0,"n_ran_checked":13,"n_instrument":9,"n_unverified":9,"n_honours":0,"n_violates":1,"n_no_contract":12,"n_pointer_only":3,"phrase":"22 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 1 violated, 12 with no contract checked; 9 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/stackgan-realistic-image-synthesis-with#ran","syntology_url":"https://syntology.ai/paper/1710.10916","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.10916"}},"official":{"repos":["hanzhanggit/StackGAN","hanzhanggit/StackGAN-v2"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/consistency-models","slug":"consistency-models","title":"Consistency Models","date":"2023-03-02","arxiv_id":"2303.01469","repositories_listed":15,"syntology":{"n":57,"n_ran":32,"n_constructed":5,"n_ran_checked":16,"n_instrument":16,"n_unverified":25,"n_honours":5,"n_violates":3,"n_no_contract":8,"n_pointer_only":18,"phrase":"32 ran (of which 5 constructed an object rather than computing a result; 16 with no instrument failure: 5 honoured, 3 violated, 8 with no contract checked; 16 where Syntology's instrument failed) · 25 unverified","sample_list":"/paper/consistency-models#ran","syntology_url":"https://syntology.ai/paper/2303.01469","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.01469"}},"official":{"repos":["openai/consistency_models"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":9,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/score-based-generative-modeling-through-1","slug":"score-based-generative-modeling-through-1","title":"Score-Based Generative Modeling through Stochastic Differential Equations","date":"2020-11-26","arxiv_id":"2011.13456","repositories_listed":15,"syntology":{"n":23,"n_ran":15,"n_constructed":4,"n_ran_checked":8,"n_instrument":7,"n_unverified":8,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":4,"phrase":"15 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 7 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/score-based-generative-modeling-through-1#ran","syntology_url":"https://syntology.ai/paper/2011.13456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.13456"}},"official":{"repos":["yang-song/score_sde"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/190600446","slug":"190600446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","date":"2019-06-02","arxiv_id":"1906.00446","repositories_listed":15,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":4,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/190600446#ran","syntology_url":"https://syntology.ai/paper/1906.00446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.00446"}},"official":{"repos":["deepmind/sonnet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/stargan-v2-diverse-image-synthesis-for","slug":"stargan-v2-diverse-image-synthesis-for","title":"StarGAN v2: Diverse Image Synthesis for Multiple Domains","date":"2019-12-04","arxiv_id":"1912.01865","repositories_listed":14,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/stargan-v2-diverse-image-synthesis-for#ran","syntology_url":"https://syntology.ai/paper/1912.01865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.01865"}},"official":{"repos":["clovaai/stargan-v2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/faceforensics-learning-to-detect-manipulated","slug":"faceforensics-learning-to-detect-manipulated","title":"FaceForensics++: Learning to Detect Manipulated Facial Images","date":"2019-01-25","arxiv_id":"1901.08971","repositories_listed":14,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":4,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 4 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/faceforensics-learning-to-detect-manipulated#ran","syntology_url":"https://syntology.ai/paper/1901.08971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.08971"}},"official":{"repos":["ondyari/FaceForensics"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/deep-image-prior","slug":"deep-image-prior","title":"Deep Image Prior","date":"2017-11-29","arxiv_id":"1711.10925","repositories_listed":14,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deep-image-prior#ran","syntology_url":"https://syntology.ai/paper/1711.10925","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.10925"}},"official":null}},{"url":"/paper/conditional-image-generation-with-pixelcnn","slug":"conditional-image-generation-with-pixelcnn","title":"Conditional Image Generation with PixelCNN Decoders","date":"2016-06-16","arxiv_id":"1606.05328","repositories_listed":14,"syntology":{"n":14,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":6,"n_honours":2,"n_violates":0,"n_no_contract":4,"n_pointer_only":3,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 2 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/conditional-image-generation-with-pixelcnn#ran","syntology_url":"https://syntology.ai/paper/1606.05328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.05328"}},"official":null}},{"url":"/paper/scalable-diffusion-models-with-transformers","slug":"scalable-diffusion-models-with-transformers","title":"Scalable Diffusion Models with Transformers","date":"2022-12-19","arxiv_id":"2212.09748","repositories_listed":13,"syntology":{"n":20,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":10,"n_pointer_only":4,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 2 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/scalable-diffusion-models-with-transformers#ran","syntology_url":"https://syntology.ai/paper/2212.09748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.09748"}},"official":{"repos":["facebookresearch/DiT"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/taming-transformers-for-high-resolution-image","slug":"taming-transformers-for-high-resolution-image","title":"Taming Transformers for High-Resolution Image Synthesis","date":"2020-12-17","arxiv_id":"2012.09841","repositories_listed":13,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":2,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":4,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/taming-transformers-for-high-resolution-image#ran","syntology_url":"https://syntology.ai/paper/2012.09841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.09841"}},"official":{"repos":["CompVis/taming-transformers"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/differentiable-augmentation-for-data","slug":"differentiable-augmentation-for-data","title":"Differentiable Augmentation for Data-Efficient GAN Training","date":"2020-06-18","arxiv_id":"2006.10738","repositories_listed":13,"syntology":{"n":58,"n_ran":49,"n_constructed":0,"n_ran_checked":17,"n_instrument":32,"n_unverified":9,"n_honours":3,"n_violates":1,"n_no_contract":13,"n_pointer_only":15,"phrase":"49 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 3 honoured, 1 violated, 13 with no contract checked; 32 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/differentiable-augmentation-for-data#ran","syntology_url":"https://syntology.ai/paper/2006.10738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10738"}},"official":{"repos":["mit-han-lab/data-efficient-gans"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/generative-modeling-by-estimating-gradients","slug":"generative-modeling-by-estimating-gradients","title":"Generative Modeling by Estimating Gradients of the Data Distribution","date":"2019-07-12","arxiv_id":"1907.05600","repositories_listed":13,"syntology":{"n":22,"n_ran":14,"n_constructed":9,"n_ran_checked":11,"n_instrument":3,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":10,"n_pointer_only":9,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/generative-modeling-by-estimating-gradients#ran","syntology_url":"https://syntology.ai/paper/1907.05600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.05600"}},"official":{"repos":["ermongroup/ncsn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/adding-conditional-control-to-text-to-image","slug":"adding-conditional-control-to-text-to-image","title":"Adding Conditional Control to Text-to-Image Diffusion Models","date":"2023-02-10","arxiv_id":"2302.05543","repositories_listed":12,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adding-conditional-control-to-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2302.05543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.05543"}},"official":{"repos":["lllyasviel/controlnet"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/dreambooth-fine-tuning-text-to-image","slug":"dreambooth-fine-tuning-text-to-image","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","date":"2022-08-25","arxiv_id":"2208.12242","repositories_listed":12,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":2,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":8,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/dreambooth-fine-tuning-text-to-image#ran","syntology_url":"https://syntology.ai/paper/2208.12242","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.12242"}},"official":null}},{"url":"/paper/progressive-distillation-for-fast-sampling-of-1","slug":"progressive-distillation-for-fast-sampling-of-1","title":"Progressive Distillation for Fast Sampling of Diffusion Models","date":"2022-02-01","arxiv_id":"2202.00512","repositories_listed":12,"syntology":{"n":27,"n_ran":10,"n_constructed":4,"n_ran_checked":7,"n_instrument":3,"n_unverified":17,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":10,"phrase":"10 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 17 unverified","sample_list":"/paper/progressive-distillation-for-fast-sampling-of-1#ran","syntology_url":"https://syntology.ai/paper/2202.00512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.00512"}},"official":{"repos":["google-research/google-research"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/zero-shot-text-to-image-generation","slug":"zero-shot-text-to-image-generation","title":"Zero-Shot Text-to-Image Generation","date":"2021-02-24","arxiv_id":"2102.12092","repositories_listed":12,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zero-shot-text-to-image-generation#ran","syntology_url":"https://syntology.ai/paper/2102.12092","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.12092"}},"official":{"repos":["openai/DALL-E"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/adversarial-latent-autoencoders","slug":"adversarial-latent-autoencoders","title":"Adversarial Latent Autoencoders","date":"2020-04-09","arxiv_id":"2004.04467","repositories_listed":12,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-latent-autoencoders#ran","syntology_url":"https://syntology.ai/paper/2004.04467","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.04467"}},"official":{"repos":["podgorskiy/ALAE"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/joint-discriminative-and-generative-learning","slug":"joint-discriminative-and-generative-learning","title":"Joint Discriminative and Generative Learning for Person Re-identification","date":"2019-04-15","arxiv_id":"1904.07223","repositories_listed":12,"syntology":{"n":19,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/joint-discriminative-and-generative-learning#ran","syntology_url":"https://syntology.ai/paper/1904.07223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.07223"}},"official":null}},{"url":"/paper/cgans-with-projection-discriminator","slug":"cgans-with-projection-discriminator","title":"cGANs with Projection Discriminator","date":"2018-02-15","arxiv_id":"1802.05637","repositories_listed":12,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cgans-with-projection-discriminator#ran","syntology_url":"https://syntology.ai/paper/1802.05637","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.05637"}},"official":{"repos":["crcrpar/pytorch.sngan_projection","pfnet-research/sngan_projection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/closed-form-factorization-of-latent-semantics","slug":"closed-form-factorization-of-latent-semantics","title":"Closed-Form Factorization of Latent Semantics in GANs","date":"2020-07-13","arxiv_id":"2007.06600","repositories_listed":11,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":7,"n_instrument":6,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/closed-form-factorization-of-latent-semantics#ran","syntology_url":"https://syntology.ai/paper/2007.06600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.06600"}},"official":null}},{"url":"/paper/transgan-two-transformers-can-make-one-strong","slug":"transgan-two-transformers-can-make-one-strong","title":"TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up","date":"2021-02-14","arxiv_id":"2102.07074","repositories_listed":10,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":0,"n_honours":0,"n_violates":2,"n_no_contract":0,"n_pointer_only":7,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transgan-two-transformers-can-make-one-strong#ran","syntology_url":"https://syntology.ai/paper/2102.07074","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2102.07074"}},"official":{"repos":["VITA-Group/TransGAN"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/contrastive-learning-for-unpaired-image-to","slug":"contrastive-learning-for-unpaired-image-to","title":"Contrastive Learning for Unpaired Image-to-Image Translation","date":"2020-07-30","arxiv_id":"2007.15651","repositories_listed":10,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":2,"n_instrument":7,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/contrastive-learning-for-unpaired-image-to#ran","syntology_url":"https://syntology.ai/paper/2007.15651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.15651"}},"official":{"repos":["taesungp/contrastive-unpaired-translation"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/nvae-a-deep-hierarchical-variational","slug":"nvae-a-deep-hierarchical-variational","title":"NVAE: A Deep Hierarchical Variational Autoencoder","date":"2020-07-08","arxiv_id":"2007.03898","repositories_listed":10,"syntology":{"n":41,"n_ran":26,"n_constructed":15,"n_ran_checked":21,"n_instrument":5,"n_unverified":15,"n_honours":3,"n_violates":0,"n_no_contract":18,"n_pointer_only":23,"phrase":"26 ran (of which 15 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 0 violated, 18 with no contract checked; 5 where Syntology's instrument failed) · 15 unverified","sample_list":"/paper/nvae-a-deep-hierarchical-variational#ran","syntology_url":"https://syntology.ai/paper/2007.03898","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.03898"}},"official":{"repos":["NVlabs/NVAE"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":3,"n_ran_no_instrument_failure":6,"n_unverified":14,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/reformer-the-efficient-transformer-1","slug":"reformer-the-efficient-transformer-1","title":"Reformer: The Efficient Transformer","date":"2020-01-13","arxiv_id":"2001.04451","repositories_listed":10,"syntology":{"n":8,"n_ran":6,"n_constructed":1,"n_ran_checked":1,"n_instrument":5,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/reformer-the-efficient-transformer-1#ran","syntology_url":"https://syntology.ai/paper/2001.04451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.04451"}},"official":{"repos":["google/trax"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/zero-memory-optimization-towards-training-a","slug":"zero-memory-optimization-towards-training-a","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","date":"2019-10-04","arxiv_id":"1910.02054","repositories_listed":10,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/zero-memory-optimization-towards-training-a#ran","syntology_url":"https://syntology.ai/paper/1910.02054","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.02054"}},"official":{"repos":["NVIDIA/Megatron-LM","microsoft/DeepSpeed"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/improved-precision-and-recall-metric-for","slug":"improved-precision-and-recall-metric-for","title":"Improved Precision and Recall Metric for Assessing Generative Models","date":"2019-04-15","arxiv_id":"1904.06991","repositories_listed":10,"syntology":{"n":42,"n_ran":30,"n_constructed":12,"n_ran_checked":20,"n_instrument":10,"n_unverified":12,"n_honours":5,"n_violates":1,"n_no_contract":14,"n_pointer_only":25,"phrase":"30 ran (of which 12 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 1 violated, 14 with no contract checked; 10 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/improved-precision-and-recall-metric-for#ran","syntology_url":"https://syntology.ai/paper/1904.06991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.06991"}},"official":{"repos":["kynkaat/improved-precision-and-recall-metric"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/the-relativistic-discriminator-a-key-element","slug":"the-relativistic-discriminator-a-key-element","title":"The relativistic discriminator: a key element missing from standard GAN","date":"2018-07-02","arxiv_id":"1807.00734","repositories_listed":10,"syntology":{"n":9,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/the-relativistic-discriminator-a-key-element#ran","syntology_url":"https://syntology.ai/paper/1807.00734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.00734"}},"official":{"repos":["AlexiaJM/RelativisticGAN"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/niftynet-a-deep-learning-platform-for-medical","slug":"niftynet-a-deep-learning-platform-for-medical","title":"NiftyNet: a deep-learning platform for medical imaging","date":"2017-09-11","arxiv_id":"1709.03485","repositories_listed":10,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/niftynet-a-deep-learning-platform-for-medical#ran","syntology_url":"https://syntology.ai/paper/1709.03485","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.03485"}},"official":{"repos":["NifTK/NiftyNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/generating-images-with-perceptual-similarity","slug":"generating-images-with-perceptual-similarity","title":"Generating Images with Perceptual Similarity Metrics based on Deep Networks","date":"2016-02-08","arxiv_id":"1602.02644","repositories_listed":10,"syntology":{"n":11,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":8,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/generating-images-with-perceptual-similarity#ran","syntology_url":"https://syntology.ai/paper/1602.02644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.02644"}},"official":null}},{"url":"/paper/sdxl-improving-latent-diffusion-models-for","slug":"sdxl-improving-latent-diffusion-models-for","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","date":"2023-07-04","arxiv_id":"2307.01952","repositories_listed":9,"syntology":{"n":27,"n_ran":14,"n_constructed":0,"n_ran_checked":14,"n_instrument":0,"n_unverified":13,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 13 unverified","sample_list":"/paper/sdxl-improving-latent-diffusion-models-for#ran","syntology_url":"https://syntology.ai/paper/2307.01952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.01952"}},"official":{"repos":["stability-ai/generative-models"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":10,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/an-image-is-worth-one-word-personalizing-text","slug":"an-image-is-worth-one-word-personalizing-text","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","date":"2022-08-02","arxiv_id":"2208.01618","repositories_listed":9,"syntology":{"n":13,"n_ran":10,"n_constructed":3,"n_ran_checked":7,"n_instrument":3,"n_unverified":3,"n_honours":3,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/an-image-is-worth-one-word-personalizing-text#ran","syntology_url":"https://syntology.ai/paper/2208.01618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.01618"}},"official":{"repos":["rinongal/textual_inversion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/pseudo-numerical-methods-for-diffusion-models-1","slug":"pseudo-numerical-methods-for-diffusion-models-1","title":"Pseudo Numerical Methods for Diffusion Models on Manifolds","date":"2022-02-20","arxiv_id":"2202.09778","repositories_listed":9,"syntology":{"n":14,"n_ran":10,"n_constructed":4,"n_ran_checked":4,"n_instrument":6,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":2,"phrase":"10 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/pseudo-numerical-methods-for-diffusion-models-1#ran","syntology_url":"https://syntology.ai/paper/2202.09778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.09778"}},"official":{"repos":["luping-liu/PNDM"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/maskgit-masked-generative-image-transformer","slug":"maskgit-masked-generative-image-transformer","title":"MaskGIT: Masked Generative Image Transformer","date":"2022-02-08","arxiv_id":"2202.04200","repositories_listed":9,"syntology":{"n":21,"n_ran":14,"n_constructed":9,"n_ran_checked":10,"n_instrument":4,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":4,"phrase":"14 ran (of which 9 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/maskgit-masked-generative-image-transformer#ran","syntology_url":"https://syntology.ai/paper/2202.04200","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.04200"}},"official":{"repos":["google-research/maskgit"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/improved-techniques-for-training-score-based","slug":"improved-techniques-for-training-score-based","title":"Improved Techniques for Training Score-Based Generative Models","date":"2020-06-16","arxiv_id":"2006.09011","repositories_listed":9,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improved-techniques-for-training-score-based#ran","syntology_url":"https://syntology.ai/paper/2006.09011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.09011"}},"official":{"repos":["ermongroup/ncsnv2"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/adversarially-learned-inference","slug":"adversarially-learned-inference","title":"Adversarially Learned Inference","date":"2016-06-02","arxiv_id":"1606.00704","repositories_listed":9,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/adversarially-learned-inference#ran","syntology_url":"https://syntology.ai/paper/1606.00704","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1606.00704"}},"official":{"repos":["IshmaelBelghazi/ALI"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/hierarchical-text-conditional-image","slug":"hierarchical-text-conditional-image","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","date":"2022-04-13","arxiv_id":"2204.06125","repositories_listed":8,"syntology":{"n":38,"n_ran":33,"n_constructed":7,"n_ran_checked":23,"n_instrument":10,"n_unverified":5,"n_honours":3,"n_violates":6,"n_no_contract":14,"n_pointer_only":4,"phrase":"33 ran (of which 7 constructed an object rather than computing a result; 23 with no instrument failure: 3 honoured, 6 violated, 14 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/hierarchical-text-conditional-image#ran","syntology_url":"https://syntology.ai/paper/2204.06125","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.06125"}},"official":null}},{"url":"/paper/very-deep-vaes-generalize-autoregressive-1","slug":"very-deep-vaes-generalize-autoregressive-1","title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","date":"2020-11-20","arxiv_id":"2011.10650","repositories_listed":8,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":2,"n_instrument":6,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/very-deep-vaes-generalize-autoregressive-1#ran","syntology_url":"https://syntology.ai/paper/2011.10650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.10650"}},"official":{"repos":["openai/vdvae"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/evolving-normalization-activation-layers","slug":"evolving-normalization-activation-layers","title":"Evolving Normalization-Activation Layers","date":"2020-04-06","arxiv_id":"2004.02967","repositories_listed":8,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/evolving-normalization-activation-layers#ran","syntology_url":"https://syntology.ai/paper/2004.02967","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.02967"}},"official":null}},{"url":"/paper/gan-dissection-visualizing-and-understanding","slug":"gan-dissection-visualizing-and-understanding","title":"GAN Dissection: Visualizing and Understanding Generative Adversarial Networks","date":"2018-11-26","arxiv_id":"1811.10597","repositories_listed":8,"syntology":{"n":34,"n_ran":25,"n_constructed":0,"n_ran_checked":23,"n_instrument":2,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":23,"n_pointer_only":3,"phrase":"25 ran (of which 0 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 2 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/gan-dissection-visualizing-and-understanding#ran","syntology_url":"https://syntology.ai/paper/1811.10597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.10597"}},"official":{"repos":["CSAILVision/gandissect"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/pixelcnn-improving-the-pixelcnn-with","slug":"pixelcnn-improving-the-pixelcnn-with","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","date":"2017-01-19","arxiv_id":"1701.05517","repositories_listed":8,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pixelcnn-improving-the-pixelcnn-with#ran","syntology_url":"https://syntology.ai/paper/1701.05517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.05517"}},"official":{"repos":["openai/pixel-cnn"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/fine-tuning-large-language-models-for-domain-1","slug":"fine-tuning-large-language-models-for-domain-1","title":"Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities","date":"2024-09-05","arxiv_id":"2409.03444","repositories_listed":7,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":5,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fine-tuning-large-language-models-for-domain-1#ran","syntology_url":"https://syntology.ai/paper/2409.03444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.03444"}},"official":{"repos":["lamm-mit/llm-finetuning"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/analyzing-and-improving-the-training-dynamics","slug":"analyzing-and-improving-the-training-dynamics","title":"Analyzing and Improving the Training Dynamics of Diffusion Models","date":"2023-12-05","arxiv_id":"2312.02696","repositories_listed":7,"syntology":{"n":18,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":6,"n_no_contract":6,"n_pointer_only":6,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 1 honoured, 6 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/analyzing-and-improving-the-training-dynamics#ran","syntology_url":"https://syntology.ai/paper/2312.02696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02696"}},"official":{"repos":["nvlabs/edm2"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/analog-bits-generating-discrete-data-using","slug":"analog-bits-generating-discrete-data-using","title":"Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning","date":"2022-08-08","arxiv_id":"2208.04202","repositories_listed":7,"syntology":{"n":20,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":7,"n_honours":1,"n_violates":3,"n_no_contract":0,"n_pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 3 violated, 0 with no contract checked; 9 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/analog-bits-generating-discrete-data-using#ran","syntology_url":"https://syntology.ai/paper/2208.04202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.04202"}},"official":{"repos":["google-research/pix2seq"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/prompt-to-prompt-image-editing-with-cross","slug":"prompt-to-prompt-image-editing-with-cross","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","date":"2022-08-02","arxiv_id":"2208.01626","repositories_listed":7,"syntology":{"n":15,"n_ran":9,"n_constructed":2,"n_ran_checked":7,"n_instrument":2,"n_unverified":6,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":4,"phrase":"9 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/prompt-to-prompt-image-editing-with-cross#ran","syntology_url":"https://syntology.ai/paper/2208.01626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.01626"}},"official":{"repos":["google/prompt-to-prompt"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/alias-free-generative-adversarial-networks","slug":"alias-free-generative-adversarial-networks","title":"Alias-Free Generative Adversarial Networks","date":"2021-06-23","arxiv_id":"2106.12423","repositories_listed":7,"syntology":{"n":31,"n_ran":30,"n_constructed":0,"n_ran_checked":20,"n_instrument":10,"n_unverified":1,"n_honours":5,"n_violates":4,"n_no_contract":11,"n_pointer_only":12,"phrase":"30 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 5 honoured, 4 violated, 11 with no contract checked; 10 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/alias-free-generative-adversarial-networks#ran","syntology_url":"https://syntology.ai/paper/2106.12423","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.12423"}},"official":{"repos":["NVlabs/stylegan3"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/beyond-self-attention-external-attention","slug":"beyond-self-attention-external-attention","title":"Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks","date":"2021-05-05","arxiv_id":"2105.02358","repositories_listed":7,"syntology":null},{"url":"/paper/towards-faster-and-stabilized-gan-training-1","slug":"towards-faster-and-stabilized-gan-training-1","title":"Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis","date":"2021-01-12","arxiv_id":"2101.04775","repositories_listed":7,"syntology":{"n":9,"n_ran":9,"n_constructed":7,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":9,"phrase":"9 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/towards-faster-and-stabilized-gan-training-1#ran","syntology_url":"https://syntology.ai/paper/2101.04775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.04775"}},"official":{"repos":["odegeasslbc/FastGAN-pytorch"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/rethinking-attention-with-performers","slug":"rethinking-attention-with-performers","title":"Rethinking Attention with Performers","date":"2020-09-30","arxiv_id":"2009.14794","repositories_listed":7,"syntology":{"n":16,"n_ran":11,"n_constructed":3,"n_ran_checked":7,"n_instrument":4,"n_unverified":5,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":6,"phrase":"11 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/rethinking-attention-with-performers#ran","syntology_url":"https://syntology.ai/paper/2009.14794","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.14794"}},"official":{"repos":["google-research/google-research"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/guided-image-generation-with-conditional","slug":"guided-image-generation-with-conditional","title":"Guided Image Generation with Conditional Invertible Neural Networks","date":"2019-07-04","arxiv_id":"1907.02392","repositories_listed":7,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/guided-image-generation-with-conditional#ran","syntology_url":"https://syntology.ai/paper/1907.02392","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.02392"}},"official":{"repos":["VLL-HD/FrEIA"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/190411486","slug":"190411486","title":"Making Convolutional Networks Shift-Invariant Again","date":"2019-04-25","arxiv_id":"1904.11486","repositories_listed":7,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/190411486#ran","syntology_url":"https://syntology.ai/paper/1904.11486","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.11486"}},"official":{"repos":["adobe/antialiased-cnns"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/190410509","slug":"190410509","title":"Generating Long Sequences with Sparse Transformers","date":"2019-04-23","arxiv_id":"1904.10509","repositories_listed":7,"syntology":{"n":6,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/190410509#ran","syntology_url":"https://syntology.ai/paper/1904.10509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.10509"}},"official":{"repos":["openai/sparse_attention"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/ffjord-free-form-continuous-dynamics-for","slug":"ffjord-free-form-continuous-dynamics-for","title":"FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models","date":"2018-10-02","arxiv_id":"1810.01367","repositories_listed":7,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ffjord-free-form-continuous-dynamics-for#ran","syntology_url":"https://syntology.ai/paper/1810.01367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.01367"}},"official":null}},{"url":"/paper/towards-the-automatic-anime-characters","slug":"towards-the-automatic-anime-characters","title":"Towards the Automatic Anime Characters Creation with Generative Adversarial Networks","date":"2017-08-18","arxiv_id":"1708.05509","repositories_listed":7,"syntology":null},{"url":"/paper/learning-texture-manifolds-with-the-periodic","slug":"learning-texture-manifolds-with-the-periodic","title":"Learning Texture Manifolds with the Periodic Spatial GAN","date":"2017-05-18","arxiv_id":"1705.06566","repositories_listed":7,"syntology":null},{"url":"/paper/semantic-style-transfer-and-turning-two-bit","slug":"semantic-style-transfer-and-turning-two-bit","title":"Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks","date":"2016-03-05","arxiv_id":"1603.01768","repositories_listed":7,"syntology":null},{"url":"/paper/iterative-gaussianization-from-ica-to-random","slug":"iterative-gaussianization-from-ica-to-random","title":"Iterative Gaussianization: from ICA to Random Rotations","date":"2016-01-31","arxiv_id":"1602.00229","repositories_listed":7,"syntology":{"n":25,"n_ran":21,"n_constructed":0,"n_ran_checked":21,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":21,"n_pointer_only":0,"phrase":"21 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/iterative-gaussianization-from-ica-to-random#ran","syntology_url":"https://syntology.ai/paper/1602.00229","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1602.00229"}},"official":{"repos":["IPL-UV/rbig_jax"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/combining-markov-random-fields-and","slug":"combining-markov-random-fields-and","title":"Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis","date":"2016-01-18","arxiv_id":"1601.04589","repositories_listed":7,"syntology":{"n":18,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":11,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified","sample_list":"/paper/combining-markov-random-fields-and#ran","syntology_url":"https://syntology.ai/paper/1601.04589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1601.04589"}},"official":{"repos":["chuanli11/CNNMRF"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/adversarial-diffusion-distillation","slug":"adversarial-diffusion-distillation","title":"Adversarial Diffusion Distillation","date":"2023-11-28","arxiv_id":"2311.17042","repositories_listed":6,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/adversarial-diffusion-distillation#ran","syntology_url":"https://syntology.ai/paper/2311.17042","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17042"}},"official":{"repos":["stability-ai/generative-models"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/composer-creative-and-controllable-image","slug":"composer-creative-and-controllable-image","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","date":"2023-02-20","arxiv_id":"2302.09778","repositories_listed":6,"syntology":null},{"url":"/paper/flow-straight-and-fast-learning-to-generate","slug":"flow-straight-and-fast-learning-to-generate","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","date":"2022-09-07","arxiv_id":"2209.03003","repositories_listed":6,"syntology":{"n":8,"n_ran":6,"n_constructed":3,"n_ran_checked":6,"n_instrument":0,"n_unverified":2,"n_honours":3,"n_violates":0,"n_no_contract":3,"n_pointer_only":6,"phrase":"6 ran (of which 3 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flow-straight-and-fast-learning-to-generate#ran","syntology_url":"https://syntology.ai/paper/2209.03003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.03003"}},"official":{"repos":["gnobitab/RectifiedFlow"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/do-neural-optimal-transport-solvers-work-a","slug":"do-neural-optimal-transport-solvers-work-a","title":"Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark","date":"2021-06-03","arxiv_id":"2106.01954","repositories_listed":6,"syntology":{"n":19,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":8,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":3,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/do-neural-optimal-transport-solvers-work-a#ran","syntology_url":"https://syntology.ai/paper/2106.01954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.01954"}},"official":{"repos":["iamalexkorotin/Wasserstein2Benchmark","iamalexkorotin/Wasserstein2GenerativeNetworks"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/aggregating-nested-transformers","slug":"aggregating-nested-transformers","title":"Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding","date":"2021-05-26","arxiv_id":"2105.12723","repositories_listed":6,"syntology":{"n":26,"n_ran":19,"n_constructed":0,"n_ran_checked":16,"n_instrument":3,"n_unverified":7,"n_honours":3,"n_violates":1,"n_no_contract":12,"n_pointer_only":6,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 1 violated, 12 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/aggregating-nested-transformers#ran","syntology_url":"https://syntology.ai/paper/2105.12723","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.12723"}},"official":{"repos":["google-research/nested-transformer"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/improved-contrastive-divergence-training-of-1","slug":"improved-contrastive-divergence-training-of-1","title":"Improved Contrastive Divergence Training of Energy Based Models","date":"2020-12-02","arxiv_id":"2012.01316","repositories_listed":6,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improved-contrastive-divergence-training-of-1#ran","syntology_url":"https://syntology.ai/paper/2012.01316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2012.01316"}},"official":null}},{"url":"/paper/stylespace-analysis-disentangled-controls-for","slug":"stylespace-analysis-disentangled-controls-for","title":"StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation","date":"2020-11-25","arxiv_id":"2011.12799","repositories_listed":6,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":1,"n_instrument":4,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/stylespace-analysis-disentangled-controls-for#ran","syntology_url":"https://syntology.ai/paper/2011.12799","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12799"}},"official":{"repos":["betterze/StyleSpace"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/training-language-gans-from-scratch","slug":"training-language-gans-from-scratch","title":"Training language GANs from Scratch","date":"2019-05-23","arxiv_id":"1905.09922","repositories_listed":6,"syntology":null},{"url":"/paper/pixelsnail-an-improved-autoregressive","slug":"pixelsnail-an-improved-autoregressive","title":"PixelSNAIL: An Improved Autoregressive Generative Model","date":"2017-12-28","arxiv_id":"1712.09763","repositories_listed":6,"syntology":{"n":7,"n_ran":6,"n_constructed":0,"n_ran_checked":1,"n_instrument":5,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/pixelsnail-an-improved-autoregressive#ran","syntology_url":"https://syntology.ai/paper/1712.09763","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1712.09763"}},"official":{"repos":["neocxi/pixelsnail-public"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}}],"syntology_records":93,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":54,"papers_placed":1,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/image-generation-on-imagenet-256x256","since_archive":"/sota/image-generation-on-imagenet-256x256#since-judged","papers_judged":2,"placed":0},{"leaderboard":"/sota/image-generation-on-cifar-10","since_archive":"/sota/image-generation-on-cifar-10#since-judged","papers_judged":28,"placed":0},{"leaderboard":"/sota/image-generation-on-ffhq-256-x-256","since_archive":"/sota/image-generation-on-ffhq-256-x-256#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/image-generation-on-celeba-64x64","since_archive":"/sota/image-generation-on-celeba-64x64#since-judged","papers_judged":9,"placed":0},{"leaderboard":"/sota/image-generation-on-lsun-bedroom-256-x-256","since_archive":"/sota/image-generation-on-lsun-bedroom-256-x-256#since-judged","papers_judged":6,"placed":1},{"leaderboard":"/sota/image-generation-on-lsun-churches-256-x-256","since_archive":"/sota/image-generation-on-lsun-churches-256-x-256#since-judged","papers_judged":2,"placed":1},{"leaderboard":"/sota/image-generation-on-celeba-hq-256x256","since_archive":"/sota/image-generation-on-celeba-hq-256x256#since-judged","papers_judged":3,"placed":0},{"leaderboard":"/sota/image-generation-on-celeba-256x256","since_archive":"/sota/image-generation-on-celeba-256x256#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/image-generation-on-mnist","since_archive":"/sota/image-generation-on-mnist#since-judged","papers_judged":12,"placed":0},{"leaderboard":"/sota/image-generation-on-wise","since_archive":"/sota/image-generation-on-wise#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/image-generation-on-ffhq","since_archive":"/sota/image-generation-on-ffhq#since-judged","papers_judged":4,"placed":0},{"leaderboard":"/sota/image-generation-on-celeba-hq-1024x1024","since_archive":"/sota/image-generation-on-celeba-hq-1024x1024#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/image-generation-on-afhq-cat","since_archive":"/sota/image-generation-on-afhq-cat#since-judged","papers_judged":1,"placed":1},{"leaderboard":"/sota/image-generation-on-afhqv2","since_archive":"/sota/image-generation-on-afhqv2#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/image-generation-on-fashion-mnist","since_archive":"/sota/image-generation-on-fashion-mnist#since-judged","papers_judged":2,"placed":0}]},"papers_where_code_ran":1223,"papers_where_code_ran_first_page":"/task/image-generation/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":67,"url":"/task/image-generation/papers/2","json":"/task/image-generation/papers/2.json","rows":100},{"order":"archive","page":3,"of":67,"url":"/task/image-generation/papers/3","json":"/task/image-generation/papers/3.json","rows":100},{"order":"archive","page":4,"of":67,"url":"/task/image-generation/papers/4","json":"/task/image-generation/papers/4.json","rows":100},{"order":"archive","page":5,"of":67,"url":"/task/image-generation/papers/5","json":"/task/image-generation/papers/5.json","rows":100},{"order":"archive","page":6,"of":67,"url":"/task/image-generation/papers/6","json":"/task/image-generation/papers/6.json","rows":100},{"order":"archive","page":7,"of":67,"url":"/task/image-generation/papers/7","json":"/task/image-generation/papers/7.json","rows":100},{"order":"archive","page":8,"of":67,"url":"/task/image-generation/papers/8","json":"/task/image-generation/papers/8.json","rows":100},{"order":"archive","page":9,"of":67,"url":"/task/image-generation/papers/9","json":"/task/image-generation/papers/9.json","rows":100},{"order":"archive","page":10,"of":67,"url":"/task/image-generation/papers/10","json":"/task/image-generation/papers/10.json","rows":100},{"order":"archive","page":11,"of":67,"url":"/task/image-generation/papers/11","json":"/task/image-generation/papers/11.json","rows":100},{"order":"archive","page":12,"of":67,"url":"/task/image-generation/papers/12","json":"/task/image-generation/papers/12.json","rows":100},{"order":"archive","page":13,"of":67,"url":"/task/image-generation/papers/13","json":"/task/image-generation/papers/13.json","rows":100},{"order":"archive","page":14,"of":67,"url":"/task/image-generation/papers/14","json":"/task/image-generation/papers/14.json","rows":100},{"order":"archive","page":15,"of":67,"url":"/task/image-generation/papers/15","json":"/task/image-generation/papers/15.json","rows":100},{"order":"archive","page":16,"of":67,"url":"/task/image-generation/papers/16","json":"/task/image-generation/papers/16.json","rows":100},{"order":"archive","page":17,"of":67,"url":"/task/image-generation/papers/17","json":"/task/image-generation/papers/17.json","rows":100},{"order":"archive","page":18,"of":67,"url":"/task/image-generation/papers/18","json":"/task/image-generation/papers/18.json","rows":100},{"order":"archive","page":19,"of":67,"url":"/task/image-generation/papers/19","json":"/task/image-generation/papers/19.json","rows":100},{"order":"archive","page":20,"of":67,"url":"/task/image-generation/papers/20","json":"/task/image-generation/papers/20.json","rows":100},{"order":"archive","page":21,"of":67,"url":"/task/image-generation/papers/21","json":"/task/image-generation/papers/21.json","rows":100},{"order":"archive","page":22,"of":67,"url":"/task/image-generation/papers/22","json":"/task/image-generation/papers/22.json","rows":100},{"order":"archive","page":23,"of":67,"url":"/task/image-generation/papers/23","json":"/task/image-generation/papers/23.json","rows":100},{"order":"archive","page":24,"of":67,"url":"/task/image-generation/papers/24","json":"/task/image-generation/papers/24.json","rows":100},{"order":"archive","page":25,"of":67,"url":"/task/image-generation/papers/25","json":"/task/image-generation/papers/25.json","rows":100},{"order":"archive","page":26,"of":67,"url":"/task/image-generation/papers/26","json":"/task/image-generation/papers/26.json","rows":100},{"order":"archive","page":27,"of":67,"url":"/task/image-generation/papers/27","json":"/task/image-generation/papers/27.json","rows":100},{"order":"archive","page":28,"of":67,"url":"/task/image-generation/papers/28","json":"/task/image-generation/papers/28.json","rows":100},{"order":"archive","page":29,"of":67,"url":"/task/image-generation/papers/29","json":"/task/image-generation/papers/29.json","rows":100},{"order":"archive","page":30,"of":67,"url":"/task/image-generation/papers/30","json":"/task/image-generation/papers/30.json","rows":100},{"order":"archive","page":31,"of":67,"url":"/task/image-generation/papers/31","json":"/task/image-generation/papers/31.json","rows":100},{"order":"archive","page":32,"of":67,"url":"/task/image-generation/papers/32","json":"/task/image-generation/papers/32.json","rows":100},{"order":"archive","page":33,"of":67,"url":"/task/image-generation/papers/33","json":"/task/image-generation/papers/33.json","rows":100},{"order":"archive","page":34,"of":67,"url":"/task/image-generation/papers/34","json":"/task/image-generation/papers/34.json","rows":100},{"order":"archive","page":35,"of":67,"url":"/task/image-generation/papers/35","json":"/task/image-generation/papers/35.json","rows":100},{"order":"archive","page":36,"of":67,"url":"/task/image-generation/papers/36","json":"/task/image-generation/papers/36.json","rows":100},{"order":"archive","page":37,"of":67,"url":"/task/image-generation/papers/37","json":"/task/image-generation/papers/37.json","rows":100},{"order":"archive","page":38,"of":67,"url":"/task/image-generation/papers/38","json":"/task/image-generation/papers/38.json","rows":100},{"order":"archive","page":39,"of":67,"url":"/task/image-generation/papers/39","json":"/task/image-generation/papers/39.json","rows":100},{"order":"archive","page":40,"of":67,"url":"/task/image-generation/papers/40","json":"/task/image-generation/papers/40.json","rows":100},{"order":"archive","page":41,"of":67,"url":"/task/image-generation/papers/41","json":"/task/image-generation/papers/41.json","rows":100},{"order":"archive","page":42,"of":67,"url":"/task/image-generation/papers/42","json":"/task/image-generation/papers/42.json","rows":100},{"order":"archive","page":43,"of":67,"url":"/task/image-generation/papers/43","json":"/task/image-generation/papers/43.json","rows":100},{"order":"archive","page":44,"of":67,"url":"/task/image-generation/papers/44","json":"/task/image-generation/papers/44.json","rows":100},{"order":"archive","page":45,"of":67,"url":"/task/image-generation/papers/45","json":"/task/image-generation/papers/45.json","rows":100},{"order":"archive","page":46,"of":67,"url":"/task/image-generation/papers/46","json":"/task/image-generation/papers/46.json","rows":100},{"order":"archive","page":47,"of":67,"url":"/task/image-generation/papers/47","json":"/task/image-generation/papers/47.json","rows":100},{"order":"archive","page":48,"of":67,"url":"/task/image-generation/papers/48","json":"/task/image-generation/papers/48.json","rows":100},{"order":"archive","page":49,"of":67,"url":"/task/image-generation/papers/49","json":"/task/image-generation/papers/49.json","rows":100},{"order":"archive","page":50,"of":67,"url":"/task/image-generation/papers/50","json":"/task/image-generation/papers/50.json","rows":100},{"order":"archive","page":51,"of":67,"url":"/task/image-generation/papers/51","json":"/task/image-generation/papers/51.json","rows":100},{"order":"archive","page":52,"of":67,"url":"/task/image-generation/papers/52","json":"/task/image-generation/papers/52.json","rows":100},{"order":"archive","page":53,"of":67,"url":"/task/image-generation/papers/53","json":"/task/image-generation/papers/53.json","rows":100},{"order":"archive","page":54,"of":67,"url":"/task/image-generation/papers/54","json":"/task/image-generation/papers/54.json","rows":100},{"order":"archive","page":55,"of":67,"url":"/task/image-generation/papers/55","json":"/task/image-generation/papers/55.json","rows":100},{"order":"archive","page":56,"of":67,"url":"/task/image-generation/papers/56","json":"/task/image-generation/papers/56.json","rows":100},{"order":"archive","page":57,"of":67,"url":"/task/image-generation/papers/57","json":"/task/image-generation/papers/57.json","rows":100},{"order":"archive","page":58,"of":67,"url":"/task/image-generation/papers/58","json":"/task/image-generation/papers/58.json","rows":100},{"order":"archive","page":59,"of":67,"url":"/task/image-generation/papers/59","json":"/task/image-generation/papers/59.json","rows":100},{"order":"archive","page":60,"of":67,"url":"/task/image-generation/papers/60","json":"/task/image-generation/papers/60.json","rows":100},{"order":"archive","page":61,"of":67,"url":"/task/image-generation/papers/61","json":"/task/image-generation/papers/61.json","rows":100},{"order":"archive","page":62,"of":67,"url":"/task/image-generation/papers/62","json":"/task/image-generation/papers/62.json","rows":100},{"order":"archive","page":63,"of":67,"url":"/task/image-generation/papers/63","json":"/task/image-generation/papers/63.json","rows":100},{"order":"archive","page":64,"of":67,"url":"/task/image-generation/papers/64","json":"/task/image-generation/papers/64.json","rows":100},{"order":"archive","page":65,"of":67,"url":"/task/image-generation/papers/65","json":"/task/image-generation/papers/65.json","rows":100},{"order":"archive","page":66,"of":67,"url":"/task/image-generation/papers/66","json":"/task/image-generation/papers/66.json","rows":100},{"order":"archive","page":67,"of":67,"url":"/task/image-generation/papers/67","json":"/task/image-generation/papers/67.json","rows":89},{"order":"ran","page":1,"of":13,"url":"/task/image-generation/papers/ran/1","json":"/task/image-generation/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":13,"url":"/task/image-generation/papers/ran/2","json":"/task/image-generation/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":13,"url":"/task/image-generation/papers/ran/3","json":"/task/image-generation/papers/ran/3.json","rows":100},{"order":"ran","page":4,"of":13,"url":"/task/image-generation/papers/ran/4","json":"/task/image-generation/papers/ran/4.json","rows":100},{"order":"ran","page":5,"of":13,"url":"/task/image-generation/papers/ran/5","json":"/task/image-generation/papers/ran/5.json","rows":100},{"order":"ran","page":6,"of":13,"url":"/task/image-generation/papers/ran/6","json":"/task/image-generation/papers/ran/6.json","rows":100},{"order":"ran","page":7,"of":13,"url":"/task/image-generation/papers/ran/7","json":"/task/image-generation/papers/ran/7.json","rows":100},{"order":"ran","page":8,"of":13,"url":"/task/image-generation/papers/ran/8","json":"/task/image-generation/papers/ran/8.json","rows":100},{"order":"ran","page":9,"of":13,"url":"/task/image-generation/papers/ran/9","json":"/task/image-generation/papers/ran/9.json","rows":100},{"order":"ran","page":10,"of":13,"url":"/task/image-generation/papers/ran/10","json":"/task/image-generation/papers/ran/10.json","rows":100},{"order":"ran","page":11,"of":13,"url":"/task/image-generation/papers/ran/11","json":"/task/image-generation/papers/ran/11.json","rows":100},{"order":"ran","page":12,"of":13,"url":"/task/image-generation/papers/ran/12","json":"/task/image-generation/papers/ran/12.json","rows":100},{"order":"ran","page":13,"of":13,"url":"/task/image-generation/papers/ran/13","json":"/task/image-generation/papers/ran/13.json","rows":23}],"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"eb34a5731f66459313ad8e85b2267957785ed0d9d91f07f7474fe362cfc77f30","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}