{"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/video-generation","name":"Video Generation","slug":"video-generation","description_markdown":"<span style=\"color:grey; opacity: 0.6\">( Various Video Generation Tasks.\r\nGif credit: [MaGViT](https://paperswithcode.com/paper/magvit-masked-generative-video-transformer) )</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"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":1466,"papers_with_code":609,"benchmarks":16,"benchmark_tables_in_archive":16,"benchmark_tables_shown":16,"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":24,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-generation-on-ucf-101","slug":"video-generation-on-ucf-101","dataset":"UCF-101","dataset_url":"/dataset/ucf101","rows_in_archive":48,"metrics":["FVD16","FVD128","Inception Score","KVD16"],"first_row_in_archive_order":{"model":"W.A.L.T-XL (class-conditional)","paper_title":"Photorealistic Video Generation with Diffusion Models","paper_url":"/paper/photorealistic-video-generation-with","paper_date":"2023-12-11","arxiv_id":"2312.06662","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-generation-on-bair-robot-pushing","slug":"video-generation-on-bair-robot-pushing","dataset":"BAIR Robot Pushing","dataset_url":"/dataset/bair-robot-pushing","rows_in_archive":31,"metrics":["FVD score","SSIM","PSNR","LPIPS","Cond","Train","Pred","Notes"],"first_row_in_archive_order":{"model":"MAGVIT","paper_title":"MAGVIT: Masked Generative Video Transformer","paper_url":"/paper/magvit-masked-generative-video-transformer","paper_date":"2022-12-10","arxiv_id":"2212.05199","code_links":[{"title":"google-research/magvit","url":"https://github.com/google-research/magvit"}],"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":1,"phrase":"10 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/magvit-masked-generative-video-transformer#ran","syntology_url":"https://syntology.ai/paper/2212.05199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.05199"}},"official":{"repos":["google-research/magvit"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-generation-on-sky-time-lapse","slug":"video-generation-on-sky-time-lapse","dataset":"Sky Time-lapse","dataset_url":null,"rows_in_archive":9,"metrics":["FVD 16","KVD16"],"first_row_in_archive_order":{"model":"StyleSV (256x256)","paper_title":"Towards Smooth Video Composition","paper_url":"/paper/towards-smooth-video-composition","paper_date":"2022-12-14","arxiv_id":"2212.07413","code_links":[{"title":"genforce/StyleSV","url":"https://github.com/genforce/StyleSV"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames","slug":"video-generation-on-ucf-101-16-frames","dataset":"UCF-101 16 frames, Unconditional, Single GPU","dataset_url":"/dataset/ucf101","rows_in_archive":7,"metrics":["Inception Score"],"first_row_in_archive_order":{"model":"TGAN-F","paper_title":"Lower Dimensional Kernels for Video Discriminators","paper_url":"/paper/lower-dimensional-kernels-for-video","paper_date":"2019-12-18","arxiv_id":"1912.08860","code_links":[{"title":"HappyBahman/ldvdGAN","url":"https://github.com/HappyBahman/ldvdGAN"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames-64x64","slug":"video-generation-on-ucf-101-16-frames-64x64","dataset":"UCF-101 16 frames, 64x64, Unconditional","dataset_url":"/dataset/ucf101","rows_in_archive":7,"metrics":["Inception Score","FID","FVD"],"first_row_in_archive_order":{"model":"Video Diffusion Model","paper_title":"Video Diffusion Models","paper_url":"/paper/video-diffusion-models","paper_date":"2022-04-07","arxiv_id":"2204.03458","code_links":[{"title":"lucidrains/make-a-video-pytorch","url":"https://github.com/lucidrains/make-a-video-pytorch"},{"title":"lucidrains/video-diffusion-pytorch","url":"https://github.com/lucidrains/video-diffusion-pytorch"},{"title":"coderpiaobozhe/classifier-free-diffusion-guidance-Pytorch","url":"https://github.com/coderpiaobozhe/classifier-free-diffusion-guidance-Pytorch"},{"title":"ndrwmlnk/awesome-video-diffusion-models","url":"https://github.com/ndrwmlnk/awesome-video-diffusion-models"},{"title":"eyeline-research/survey-video-diffusion","url":"https://github.com/eyeline-research/survey-video-diffusion"}],"syntology":{"n":2,"n_ran":2,"n_constructed":2,"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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/video-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2204.03458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03458"}},"official":null}}},{"leaderboard":"/sota/video-generation-on-laion-400m","slug":"video-generation-on-laion-400m","dataset":"LAION-400M","dataset_url":"/dataset/laion-400m","rows_in_archive":6,"metrics":["CLIP R-Precision","CLIP"],"first_row_in_archive_order":{"model":"Imagen original (constant=6)","paper_title":"Imagen Video: High Definition Video Generation with Diffusion Models","paper_url":"/paper/imagen-video-high-definition-video-generation","paper_date":"2022-10-05","arxiv_id":"2210.02303","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-generation-on-taichi","slug":"video-generation-on-taichi","dataset":"Taichi","dataset_url":null,"rows_in_archive":6,"metrics":["FVD16","KVD16"],"first_row_in_archive_order":{"model":"StyleSV (256x256)","paper_title":"Towards Smooth Video Composition","paper_url":"/paper/towards-smooth-video-composition","paper_date":"2022-12-14","arxiv_id":"2212.07413","code_links":[{"title":"genforce/StyleSV","url":"https://github.com/genforce/StyleSV"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames-128x128","slug":"video-generation-on-ucf-101-16-frames-128x128","dataset":"UCF-101 16 frames, 128x128, Unconditional","dataset_url":"/dataset/ucf101","rows_in_archive":6,"metrics":["Inception Score"],"first_row_in_archive_order":{"model":"TGANv2 (2020)","paper_title":"Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN","paper_url":"/paper/tganv2-efficient-training-of-large-models-for","paper_date":"2018-11-22","arxiv_id":"1811.09245","code_links":[{"title":"pfnet-research/tgan2","url":"https://github.com/pfnet-research/tgan2"},{"title":"Zasder3/Tganv2-PyTorch-Train-Sparsely--Generate-Densely","url":"https://github.com/Zasder3/Tganv2-PyTorch-Train-Sparsely--Generate-Densely"}],"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tganv2-efficient-training-of-large-models-for#ran","syntology_url":"https://syntology.ai/paper/1811.09245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.09245"}},"official":{"repos":["pfnet-research/tgan2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-generation-on-kinetics-600-12-frames","slug":"video-generation-on-kinetics-600-12-frames","dataset":"Kinetics-600 12 frames, 64x64","dataset_url":"/dataset/kinetics","rows_in_archive":4,"metrics":["FVD"],"first_row_in_archive_order":{"model":"W.A.L.T-L","paper_title":"Photorealistic Video Generation with Diffusion Models","paper_url":"/paper/photorealistic-video-generation-with","paper_date":"2023-12-11","arxiv_id":"2312.06662","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-generation-on-how2sign","slug":"video-generation-on-how2sign","dataset":"How2Sign","dataset_url":"/dataset/how2sign","rows_in_archive":1,"metrics":["FVD16"],"first_row_in_archive_order":{"model":"INR-V","paper_title":"INR-V: A Continuous Representation Space for Video-based Generative Tasks","paper_url":"/paper/inr-v-a-continuous-representation-space-for","paper_date":"2022-10-29","arxiv_id":"2210.16579","code_links":[{"title":"bipashasen/INRV","url":"https://github.com/bipashasen/INRV"},{"title":"MindSpore-scientific-2/code-5","url":"https://github.com/MindSpore-scientific-2/code-5/tree/main/INR-Implicit-Neural-Representations-with-Periodic-Activation-Functions"},{"title":"MindSpore-scientific/code-11","url":"https://github.com/MindSpore-scientific/code-11/tree/main/INR-Implicit-Neural-Representations-with-Periodic-Activation-Functions"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-kinetics-600-12-frames-1","slug":"video-generation-on-kinetics-600-12-frames-1","dataset":"Kinetics-600 12 frames, 128x128","dataset_url":"/dataset/kinetics","rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"DVD-GAN","paper_title":"Adversarial Video Generation on Complex Datasets","paper_url":"/paper/efficient-video-generation-on-complex","paper_date":"2019-07-15","arxiv_id":"1907.06571","code_links":[{"title":"Harrypotterrrr/DVD-GAN","url":"https://github.com/Harrypotterrrr/DVD-GAN"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-kinetics-600-48-frames","slug":"video-generation-on-kinetics-600-48-frames","dataset":"Kinetics-600 48 frames, 64x64","dataset_url":"/dataset/kinetics","rows_in_archive":1,"metrics":["FID","Inception Score"],"first_row_in_archive_order":{"model":"DVD-GAN","paper_title":"Adversarial Video Generation on Complex Datasets","paper_url":"/paper/efficient-video-generation-on-complex","paper_date":"2019-07-15","arxiv_id":"1907.06571","code_links":[{"title":"Harrypotterrrr/DVD-GAN","url":"https://github.com/Harrypotterrrr/DVD-GAN"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-kinetics-700","slug":"video-generation-on-kinetics-700","dataset":"Kinetics-700","dataset_url":"/dataset/kinetics-700","rows_in_archive":1,"metrics":["FID","FVD"],"first_row_in_archive_order":{"model":"DiT-XL/2 + CVAE-FT-SE","paper_title":"Improving the Diffusability of Autoencoders","paper_url":"/paper/improving-the-diffusability-of-autoencoders","paper_date":"2025-02-20","arxiv_id":"2502.14831","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-generation-on-msr-vtt","slug":"video-generation-on-msr-vtt","dataset":"MSR-VTT","dataset_url":"/dataset/msr-vtt","rows_in_archive":1,"metrics":["FVD16","Inception score"],"first_row_in_archive_order":{"model":"VideoAssembler (Zero-Shot, 256x256, class-conditional)","paper_title":"MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing","paper_url":"/paper/videoassembler-identity-consistent-video","paper_date":"2023-11-29","arxiv_id":"2311.17338","code_links":[{"title":"gulucaptain/videoassembler","url":"https://github.com/gulucaptain/videoassembler"}],"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":7,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 2 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videoassembler-identity-consistent-video#ran","syntology_url":"https://syntology.ai/paper/2311.17338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17338"}},"official":{"repos":["gulucaptain/videoassembler"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-generation-on-trailerfaces","slug":"video-generation-on-trailerfaces","dataset":"TrailerFaces","dataset_url":null,"rows_in_archive":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"PG-SWGAN-3D","paper_title":"Sliced Wasserstein Generative Models","paper_url":"/paper/sliced-wasserstein-generative-models-1","paper_date":"2019-04-10","arxiv_id":"1904.05408","code_links":[{"title":"musikisomorphie/swd","url":"https://github.com/musikisomorphie/swd"}],"syntology":null}},{"leaderboard":"/sota/video-generation-on-youtube-driving","slug":"video-generation-on-youtube-driving","dataset":"YouTube Driving","dataset_url":"/dataset/youtube-driving","rows_in_archive":1,"metrics":["FVD16"],"first_row_in_archive_order":{"model":"StyleSV","paper_title":"Towards Smooth Video Composition","paper_url":"/paper/towards-smooth-video-composition","paper_date":"2022-12-14","arxiv_id":"2212.07413","code_links":[{"title":"genforce/StyleSV","url":"https://github.com/genforce/StyleSV"}],"syntology":null}}],"datasets":[{"url":"/dataset/ucf101","name":"UCF101","full_name":"UCF101 Human Actions dataset","num_papers_in_archive":1863},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/msr-vtt","name":"MSR-VTT","full_name":"","num_papers_in_archive":640},{"url":"/dataset/webvid","name":"WebVid","full_name":"","num_papers_in_archive":257},{"url":"/dataset/laion-400m","name":"LAION-400M","full_name":"","num_papers_in_archive":169},{"url":"/dataset/kinetics-600","name":"Kinetics-600","full_name":"","num_papers_in_archive":148},{"url":"/dataset/kinetics-700","name":"Kinetics-700","full_name":"Kinetics-700","num_papers_in_archive":95},{"url":"/dataset/internvid","name":"InternVid","full_name":"","num_papers_in_archive":46},{"url":"/dataset/how2sign","name":"How2Sign","full_name":"A Large-scale Multimodal Dataset for Continuous American Sign Language","num_papers_in_archive":44},{"url":"/dataset/bair-robot-pushing","name":"BAIR Robot Pushing","full_name":"","num_papers_in_archive":27},{"url":"/dataset/celebv-text","name":"CelebV-Text","full_name":"","num_papers_in_archive":15},{"url":"/dataset/opens2v-eval","name":"OpenS2V-Eval","full_name":"","num_papers_in_archive":8},{"url":"/dataset/youtube-driving","name":"YouTube Driving","full_name":"","num_papers_in_archive":6},{"url":"/dataset/chronomagic","name":"ChronoMagic","full_name":"","num_papers_in_archive":5},{"url":"/dataset/deep-fakes-dataset","name":"Deep Fakes Dataset","full_name":"inamibora","num_papers_in_archive":3},{"url":"/dataset/qst","name":"QST","full_name":"Quick Sky Time","num_papers_in_archive":3},{"url":"/dataset/avsync15","name":"AVSync15","full_name":"","num_papers_in_archive":2},{"url":"/dataset/chronomagic-pro","name":"ChronoMagic-Pro","full_name":"","num_papers_in_archive":2},{"url":"/dataset/dropletvideo-10m","name":"DropletVideo-10M","full_name":"","num_papers_in_archive":2},{"url":"/dataset/chronomagic-proh","name":"ChronoMagic-ProH","full_name":"","num_papers_in_archive":1},{"url":"/dataset/consisid-preview-data","name":"ConsisID-preview-Data","full_name":"","num_papers_in_archive":1},{"url":"/dataset/open-hypermotionx","name":"Open-HypermotionX","full_name":"","num_papers_in_archive":1},{"url":"/dataset/opens2v-5m","name":"OpenS2V-5M","full_name":"","num_papers_in_archive":1},{"url":"/dataset/tlfm-dataset","name":"TLFM dataset","full_name":"TLFM dataset for microscopy image sequence generation","num_papers_in_archive":1}],"subtasks":[{"url":"/task/image-to-video","name":"Image to Video Generation"},{"url":"/task/unconditional-video-generation","name":"Unconditional Video Generation"}],"parent_tasks":[{"url":"/task/video","name":"Video"}],"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":15,"rows_per_page":100,"shown":100,"of":1466,"of_with_code":609,"tagged_in_all":1466,"counts":{"archive_papers_tagged":1466,"with_a_code_link":609,"where_syntology_ran_a_sample":257,"not_listed_spam_title":0,"listed":1466,"listed_where_code_ran":257,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":213,"every_run_a_failure_of_syntologys_instrument":44,"listed_with_a_run_with_no_instrument_failure":213,"listed_every_run_a_failure_of_syntologys_instrument":44,"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/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/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/everybody-dance-now","slug":"everybody-dance-now","title":"Everybody Dance Now","date":"2018-08-22","arxiv_id":"1808.07371","repositories_listed":14,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/everybody-dance-now#ran","syntology_url":"https://syntology.ai/paper/1808.07371","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1808.07371"}},"official":{"repos":["carolineec/EverybodyDanceNow"],"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/temporally-coherent-gans-for-video-super","slug":"temporally-coherent-gans-for-video-super","title":"Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation","date":"2018-11-23","arxiv_id":"1811.09393","repositories_listed":13,"syntology":{"n":25,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":14,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 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; 2 where Syntology's instrument failed) · 14 unverified","sample_list":"/paper/temporally-coherent-gans-for-video-super#ran","syntology_url":"https://syntology.ai/paper/1811.09393","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.09393"}},"official":{"repos":["thunil/TecoGAN"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":10,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/video-diffusion-models","slug":"video-diffusion-models","title":"Video Diffusion Models","date":"2022-04-07","arxiv_id":"2204.03458","repositories_listed":5,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"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 2 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; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/video-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2204.03458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03458"}},"official":null}},{"url":"/paper/mocogan-decomposing-motion-and-content-for","slug":"mocogan-decomposing-motion-and-content-for","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","date":"2017-07-17","arxiv_id":"1707.04993","repositories_listed":5,"syntology":null},{"url":"/paper/open-sora-plan-open-source-large-video","slug":"open-sora-plan-open-source-large-video","title":"Open-Sora Plan: Open-Source Large Video Generation Model","date":"2024-11-28","arxiv_id":"2412.00131","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/open-sora-plan-open-source-large-video#ran","syntology_url":"https://syntology.ai/paper/2412.00131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00131"}},"official":{"repos":["pku-yuangroup/open-sora-plan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/latte-latent-diffusion-transformer-for-video","slug":"latte-latent-diffusion-transformer-for-video","title":"Latte: Latent Diffusion Transformer for Video Generation","date":"2024-01-05","arxiv_id":"2401.03048","repositories_listed":4,"syntology":{"n":13,"n_ran":12,"n_constructed":0,"n_ran_checked":7,"n_instrument":5,"n_unverified":1,"n_honours":4,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/latte-latent-diffusion-transformer-for-video#ran","syntology_url":"https://syntology.ai/paper/2401.03048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.03048"}},"official":{"repos":["maxin-cn/Latte"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/align-your-latents-high-resolution-video","slug":"align-your-latents-high-resolution-video","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","date":"2023-04-18","arxiv_id":"2304.08818","repositories_listed":4,"syntology":{"n":26,"n_ran":18,"n_constructed":0,"n_ran_checked":9,"n_instrument":9,"n_unverified":8,"n_honours":2,"n_violates":4,"n_no_contract":3,"n_pointer_only":3,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 4 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/align-your-latents-high-resolution-video#ran","syntology_url":"https://syntology.ai/paper/2304.08818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.08818"}},"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":["found_in_text","listed","unlocated"]}}},{"url":"/paper/collaborative-neural-rendering-using-anime","slug":"collaborative-neural-rendering-using-anime","title":"Collaborative Neural Rendering using Anime Character Sheets","date":"2022-07-12","arxiv_id":"2207.05378","repositories_listed":4,"syntology":null},{"url":"/paper/stochastic-adversarial-video-prediction","slug":"stochastic-adversarial-video-prediction","title":"Stochastic Adversarial Video Prediction","date":"2018-04-04","arxiv_id":"1804.01523","repositories_listed":4,"syntology":{"n":16,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/stochastic-adversarial-video-prediction#ran","syntology_url":"https://syntology.ai/paper/1804.01523","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.01523"}},"official":{"repos":["alexlee-gk/video_prediction"],"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/temporal-generative-adversarial-nets-with","slug":"temporal-generative-adversarial-nets-with","title":"Temporal Generative Adversarial Nets with Singular Value Clipping","date":"2016-11-21","arxiv_id":"1611.06624","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/temporal-generative-adversarial-nets-with#ran","syntology_url":"https://syntology.ai/paper/1611.06624","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1611.06624"}},"official":null}},{"url":"/paper/step-video-t2v-technical-report-the-practice","slug":"step-video-t2v-technical-report-the-practice","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","date":"2025-02-14","arxiv_id":"2502.10248","repositories_listed":3,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/step-video-t2v-technical-report-the-practice#ran","syntology_url":"https://syntology.ai/paper/2502.10248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.10248"}},"official":{"repos":["stepfun-ai/step-video-t2v"],"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/benchmark-evaluations-applications-and","slug":"benchmark-evaluations-applications-and","title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges","date":"2025-01-04","arxiv_id":"2501.02189","repositories_listed":3,"syntology":null},{"url":"/paper/accelerating-diffusion-transformers-with-dual","slug":"accelerating-diffusion-transformers-with-dual","title":"Accelerating Diffusion Transformers with Dual Feature Caching","date":"2024-12-25","arxiv_id":"2412.18911","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/accelerating-diffusion-transformers-with-dual#ran","syntology_url":"https://syntology.ai/paper/2412.18911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18911"}},"official":{"repos":["shenyi-z/duca"],"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/evaluating-text-to-visual-generation-with","slug":"evaluating-text-to-visual-generation-with","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","date":"2024-04-01","arxiv_id":"2404.01291","repositories_listed":3,"syntology":null},{"url":"/paper/stylecrafter-enhancing-stylized-text-to-video","slug":"stylecrafter-enhancing-stylized-text-to-video","title":"StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter","date":"2023-12-01","arxiv_id":"2312.00330","repositories_listed":3,"syntology":{"n":23,"n_ran":17,"n_constructed":0,"n_ran_checked":10,"n_instrument":7,"n_unverified":6,"n_honours":3,"n_violates":3,"n_no_contract":4,"n_pointer_only":7,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 3 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/stylecrafter-enhancing-stylized-text-to-video#ran","syntology_url":"https://syntology.ai/paper/2312.00330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00330"}},"official":{"repos":["GongyeLiu/StyleCrafter"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":6,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/stable-video-diffusion-scaling-latent-video-1","slug":"stable-video-diffusion-scaling-latent-video-1","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","date":"2023-11-25","arxiv_id":"2311.15127","repositories_listed":3,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/stable-video-diffusion-scaling-latent-video-1#ran","syntology_url":"https://syntology.ai/paper/2311.15127","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.15127"}},"official":{"repos":["stability-ai/generative-models"],"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/videocrafter1-open-diffusion-models-for-high","slug":"videocrafter1-open-diffusion-models-for-high","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","date":"2023-10-30","arxiv_id":"2310.19512","repositories_listed":3,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":2,"n_honours":1,"n_violates":2,"n_no_contract":3,"n_pointer_only":7,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videocrafter1-open-diffusion-models-for-high#ran","syntology_url":"https://syntology.ai/paper/2310.19512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.19512"}},"official":{"repos":["ailab-cvc/videocrafter"],"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/freenoise-tuning-free-longer-video-diffusion","slug":"freenoise-tuning-free-longer-video-diffusion","title":"FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling","date":"2023-10-23","arxiv_id":"2310.15169","repositories_listed":3,"syntology":{"n":24,"n_ran":13,"n_constructed":1,"n_ran_checked":7,"n_instrument":6,"n_unverified":11,"n_honours":1,"n_violates":1,"n_no_contract":5,"n_pointer_only":3,"phrase":"13 ran (of which 1 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) · 11 unverified","sample_list":"/paper/freenoise-tuning-free-longer-video-diffusion#ran","syntology_url":"https://syntology.ai/paper/2310.15169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.15169"}},"official":{"repos":["arthur-qiu/freenoise-lavie","AILab-CVC/FreeNoise","arthur-qiu/FreeNoise-AnimateDiff"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":1,"n_ran_no_instrument_failure":7,"n_unverified":11,"ran_from_kinds":["official"]}}},{"url":"/paper/language-model-beats-diffusion-tokenizer-is","slug":"language-model-beats-diffusion-tokenizer-is","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","date":"2023-10-09","arxiv_id":"2310.05737","repositories_listed":3,"syntology":{"n":20,"n_ran":19,"n_constructed":0,"n_ran_checked":14,"n_instrument":5,"n_unverified":1,"n_honours":3,"n_violates":4,"n_no_contract":7,"n_pointer_only":5,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 4 violated, 7 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/language-model-beats-diffusion-tokenizer-is#ran","syntology_url":"https://syntology.ai/paper/2310.05737","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.05737"}},"official":null}},{"url":"/paper/tune-a-video-one-shot-tuning-of-image","slug":"tune-a-video-one-shot-tuning-of-image","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","date":"2022-12-22","arxiv_id":"2212.11565","repositories_listed":3,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 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; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tune-a-video-one-shot-tuning-of-image#ran","syntology_url":"https://syntology.ai/paper/2212.11565","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.11565"}},"official":{"repos":["showlab/Tune-A-Video"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/disentangling-aesthetic-and-technical-effects","slug":"disentangling-aesthetic-and-technical-effects","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","date":"2022-11-09","arxiv_id":"2211.04894","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/disentangling-aesthetic-and-technical-effects#ran","syntology_url":"https://syntology.ai/paper/2211.04894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.04894"}},"official":{"repos":["vqassessment/dover","QualityAssessment/DOVER"],"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":["official"]}}},{"url":"/paper/inr-v-a-continuous-representation-space-for","slug":"inr-v-a-continuous-representation-space-for","title":"INR-V: A Continuous Representation Space for Video-based Generative Tasks","date":"2022-10-29","arxiv_id":"2210.16579","repositories_listed":3,"syntology":null},{"url":"/paper/videogpt-video-generation-using-vq-vae-and","slug":"videogpt-video-generation-using-vq-vae-and","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","date":"2021-04-20","arxiv_id":"2104.10157","repositories_listed":3,"syntology":null},{"url":"/paper/hierarchical-patch-vae-gan-generating-diverse","slug":"hierarchical-patch-vae-gan-generating-diverse","title":"Hierarchical Patch VAE-GAN: Generating Diverse Videos from a Single Sample","date":"2020-06-22","arxiv_id":"2006.12226","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/hierarchical-patch-vae-gan-generating-diverse#ran","syntology_url":"https://syntology.ai/paper/2006.12226","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12226"}},"official":{"repos":["shirgur/hp-vae-gan"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dwnet-dense-warp-based-network-for-pose","slug":"dwnet-dense-warp-based-network-for-pose","title":"DwNet: Dense warp-based network for pose-guided human video generation","date":"2019-10-21","arxiv_id":"1910.09139","repositories_listed":3,"syntology":null},{"url":"/paper/point-to-point-video-generation","slug":"point-to-point-video-generation","title":"Point-to-Point Video Generation","date":"2019-04-05","arxiv_id":"1904.02912","repositories_listed":3,"syntology":null},{"url":"/paper/stochastic-video-generation-with-a-learned","slug":"stochastic-video-generation-with-a-learned","title":"Stochastic Video Generation with a Learned Prior","date":"2018-02-21","arxiv_id":"1802.07687","repositories_listed":3,"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":2,"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/stochastic-video-generation-with-a-learned#ran","syntology_url":"https://syntology.ai/paper/1802.07687","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.07687"}},"official":{"repos":["edenton/svg"],"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":["official"]}}},{"url":"/paper/hierarchical-video-generation-from-orthogonal","slug":"hierarchical-video-generation-from-orthogonal","title":"Hierarchical Video Generation from Orthogonal Information: Optical Flow and Texture","date":"2017-11-27","arxiv_id":"1711.09618","repositories_listed":3,"syntology":null},{"url":"/paper/stochastic-variational-video-prediction","slug":"stochastic-variational-video-prediction","title":"Stochastic Variational Video Prediction","date":"2017-10-30","arxiv_id":"1710.11252","repositories_listed":3,"syntology":null},{"url":"/paper/magcache-fast-video-generation-with-magnitude","slug":"magcache-fast-video-generation-with-magnitude","title":"MagCache: Fast Video Generation with Magnitude-Aware Cache","date":"2025-06-10","arxiv_id":"2506.09045","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/magcache-fast-video-generation-with-magnitude#ran","syntology_url":"https://syntology.ai/paper/2506.09045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09045"}},"official":{"repos":["zehong-ma/magcache","Zehong-Ma/ComfyUI-MagCache"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/sageattention2-a-more-efficient","slug":"sageattention2-a-more-efficient","title":"SageAttention2++: A More Efficient Implementation of SageAttention2","date":"2025-05-27","arxiv_id":"2505.21136","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 5 unverified","sample_list":"/paper/sageattention2-a-more-efficient#ran","syntology_url":"https://syntology.ai/paper/2505.21136","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.21136"}},"official":{"repos":["thu-ml/SageAttention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/opens2v-nexus-a-detailed-benchmark-and","slug":"opens2v-nexus-a-detailed-benchmark-and","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","date":"2025-05-26","arxiv_id":"2505.20292","repositories_listed":2,"syntology":{"n":38,"n_ran":35,"n_constructed":0,"n_ran_checked":31,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":31,"n_pointer_only":2,"phrase":"35 ran (of which 0 constructed an object rather than computing a result; 31 with no instrument failure: 0 honoured, 0 violated, 31 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/opens2v-nexus-a-detailed-benchmark-and#ran","syntology_url":"https://syntology.ai/paper/2505.20292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20292"}},"official":{"repos":["PKU-YuanGroup/ConsisID","PKU-YuanGroup/OpenS2V-Nexus"],"state":"official (archive's flag): 35 ran","n_ran":35,"n_constructed":0,"n_ran_no_instrument_failure":31,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/magi-1-autoregressive-video-generation-at","slug":"magi-1-autoregressive-video-generation-at","title":"MAGI-1: Autoregressive Video Generation at Scale","date":"2025-05-19","arxiv_id":"2505.13211","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/magi-1-autoregressive-video-generation-at#ran","syntology_url":"https://syntology.ai/paper/2505.13211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13211"}},"official":{"repos":["sandai-org/magi-1","sandai-org/magiattention"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vace-all-in-one-video-creation-and-editing","slug":"vace-all-in-one-video-creation-and-editing","title":"VACE: All-in-One Video Creation and Editing","date":"2025-03-10","arxiv_id":"2503.07598","repositories_listed":2,"syntology":{"n":19,"n_ran":11,"n_constructed":5,"n_ran_checked":9,"n_instrument":2,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/vace-all-in-one-video-creation-and-editing#ran","syntology_url":"https://syntology.ai/paper/2503.07598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07598"}},"official":null}},{"url":"/paper/triposg-high-fidelity-3d-shape-synthesis","slug":"triposg-high-fidelity-3d-shape-synthesis","title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","date":"2025-02-10","arxiv_id":"2502.06608","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/triposg-high-fidelity-3d-shape-synthesis#ran","syntology_url":"https://syntology.ai/paper/2502.06608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06608"}},"official":{"repos":["VAST-AI-Research/TripoSG"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/open-sora-democratizing-efficient-video","slug":"open-sora-democratizing-efficient-video","title":"Open-Sora: Democratizing Efficient Video Production for All","date":"2024-12-29","arxiv_id":"2412.20404","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/open-sora-democratizing-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2412.20404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.20404"}},"official":{"repos":["hpcaitech/open-sora"],"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/hunyuanvideo-a-systematic-framework-for-large","slug":"hunyuanvideo-a-systematic-framework-for-large","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","date":"2024-12-03","arxiv_id":"2412.03603","repositories_listed":2,"syntology":{"n":27,"n_ran":18,"n_constructed":6,"n_ran_checked":6,"n_instrument":12,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":27,"phrase":"18 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 12 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/hunyuanvideo-a-systematic-framework-for-large#ran","syntology_url":"https://syntology.ai/paper/2412.03603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03603"}},"official":{"repos":["tencent/hunyuanvideo"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/ca2-vdm-efficient-autoregressive-video","slug":"ca2-vdm-efficient-autoregressive-video","title":"Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing","date":"2024-11-25","arxiv_id":"2411.16375","repositories_listed":2,"syntology":{"n":21,"n_ran":15,"n_constructed":5,"n_ran_checked":9,"n_instrument":6,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":5,"phrase":"15 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/ca2-vdm-efficient-autoregressive-video#ran","syntology_url":"https://syntology.ai/paper/2411.16375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16375"}},"official":{"repos":["dawn-lx/causalcache-vdm"],"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":["found_in_text","listed"]}}},{"url":"/paper/sageattention2-technical-report-accurate-4","slug":"sageattention2-technical-report-accurate-4","title":"SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization","date":"2024-11-17","arxiv_id":"2411.10958","repositories_listed":2,"syntology":{"n":6,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"0 ran · 6 unverified","sample_list":"/paper/sageattention2-technical-report-accurate-4#ran","syntology_url":"https://syntology.ai/paper/2411.10958","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10958"}},"official":{"repos":["thu-ml/SageAttention"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":[]}}},{"url":"/paper/movie-gen-a-cast-of-media-foundation-models","slug":"movie-gen-a-cast-of-media-foundation-models","title":"Movie Gen: A Cast of Media Foundation Models","date":"2024-10-17","arxiv_id":"2410.13720","repositories_listed":2,"syntology":null},{"url":"/paper/accelerating-diffusion-transformers-with","slug":"accelerating-diffusion-transformers-with","title":"Accelerating Diffusion Transformers with Token-wise Feature Caching","date":"2024-10-05","arxiv_id":"2410.05317","repositories_listed":2,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":3,"n_honours":5,"n_violates":1,"n_no_contract":0,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/accelerating-diffusion-transformers-with#ran","syntology_url":"https://syntology.ai/paper/2410.05317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05317"}},"official":{"repos":["Shenyi-Z/ToCa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/cogvideox-text-to-video-diffusion-models-with","slug":"cogvideox-text-to-video-diffusion-models-with","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","date":"2024-08-12","arxiv_id":"2408.06072","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":2,"n_instrument":5,"n_unverified":0,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"7 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; 5 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/cogvideox-text-to-video-diffusion-models-with#ran","syntology_url":"https://syntology.ai/paper/2408.06072","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06072"}},"official":{"repos":["thudm/cogvideo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/segment-anything-for-videos-a-systematic","slug":"segment-anything-for-videos-a-systematic","title":"Segment Anything for Videos: A Systematic Survey","date":"2024-07-31","arxiv_id":"2408.08315","repositories_listed":2,"syntology":null},{"url":"/paper/frechet-video-motion-distance-a-metric-for","slug":"frechet-video-motion-distance-a-metric-for","title":"Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos","date":"2024-07-23","arxiv_id":"2407.16124","repositories_listed":2,"syntology":{"n":23,"n_ran":20,"n_constructed":0,"n_ran_checked":16,"n_instrument":4,"n_unverified":3,"n_honours":5,"n_violates":1,"n_no_contract":10,"n_pointer_only":1,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 5 honoured, 1 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/frechet-video-motion-distance-a-metric-for#ran","syntology_url":"https://syntology.ai/paper/2407.16124","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.16124"}},"official":{"repos":["ljh0v0/fmd-frechet-motion-distance"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/miradata-a-large-scale-video-dataset-with","slug":"miradata-a-large-scale-video-dataset-with","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","date":"2024-07-08","arxiv_id":"2407.06358","repositories_listed":2,"syntology":null},{"url":"/paper/chronomagic-bench-a-benchmark-for-metamorphic","slug":"chronomagic-bench-a-benchmark-for-metamorphic","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","date":"2024-06-26","arxiv_id":"2406.18522","repositories_listed":2,"syntology":{"n":27,"n_ran":24,"n_constructed":0,"n_ran_checked":7,"n_instrument":17,"n_unverified":3,"n_honours":2,"n_violates":3,"n_no_contract":2,"n_pointer_only":0,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 3 violated, 2 with no contract checked; 17 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/chronomagic-bench-a-benchmark-for-metamorphic#ran","syntology_url":"https://syntology.ai/paper/2406.18522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.18522"}},"official":{"repos":["pku-yuangroup/chronomagic-bench","pku-yuangroup/magictime"],"state":"official (archive's flag): 21 ran","n_ran":21,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["community","official"]}}},{"url":"/paper/genai-bench-evaluating-and-improving","slug":"genai-bench-evaluating-and-improving","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","date":"2024-06-19","arxiv_id":"2406.13743","repositories_listed":2,"syntology":null},{"url":"/paper/vane-bench-video-anomaly-evaluation-benchmark","slug":"vane-bench-video-anomaly-evaluation-benchmark","title":"VANE-Bench: Video Anomaly Evaluation Benchmark for Conversational LMMs","date":"2024-06-14","arxiv_id":"2406.10326","repositories_listed":2,"syntology":null},{"url":"/paper/motionclone-training-free-motion-cloning-for","slug":"motionclone-training-free-motion-cloning-for","title":"MotionClone: Training-Free Motion Cloning for Controllable Video Generation","date":"2024-06-08","arxiv_id":"2406.05338","repositories_listed":2,"syntology":{"n":15,"n_ran":10,"n_constructed":0,"n_ran_checked":3,"n_instrument":7,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":15,"phrase":"10 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; 7 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/motionclone-training-free-motion-cloning-for#ran","syntology_url":"https://syntology.ai/paper/2406.05338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.05338"}},"official":{"repos":["bujiazi/motionclone","lpengyang/motionclone"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/unianimate-taming-unified-video-diffusion","slug":"unianimate-taming-unified-video-diffusion","title":"UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation","date":"2024-06-03","arxiv_id":"2406.01188","repositories_listed":2,"syntology":null},{"url":"/paper/echonet-synthetic-privacy-preserving-video","slug":"echonet-synthetic-privacy-preserving-video","title":"EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing","date":"2024-06-02","arxiv_id":"2406.00808","repositories_listed":2,"syntology":null},{"url":"/paper/vista-a-generalizable-driving-world-model","slug":"vista-a-generalizable-driving-world-model","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","date":"2024-05-27","arxiv_id":"2405.17398","repositories_listed":2,"syntology":{"n":23,"n_ran":11,"n_constructed":0,"n_ran_checked":6,"n_instrument":5,"n_unverified":12,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 12 unverified","sample_list":"/paper/vista-a-generalizable-driving-world-model#ran","syntology_url":"https://syntology.ai/paper/2405.17398","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17398"}},"official":{"repos":["opendrivelab/vista"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":12,"ran_from_kinds":["official"]}}},{"url":"/paper/magictime-time-lapse-video-generation-models","slug":"magictime-time-lapse-video-generation-models","title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators","date":"2024-04-07","arxiv_id":"2404.05014","repositories_listed":2,"syntology":null},{"url":"/paper/dsp-dynamic-sequence-parallelism-for-multi","slug":"dsp-dynamic-sequence-parallelism-for-multi","title":"DSP: Dynamic Sequence Parallelism for Multi-Dimensional Transformers","date":"2024-03-15","arxiv_id":"2403.10266","repositories_listed":2,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":6,"n_honours":2,"n_violates":2,"n_no_contract":5,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 2 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/dsp-dynamic-sequence-parallelism-for-multi#ran","syntology_url":"https://syntology.ai/paper/2403.10266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.10266"}},"official":{"repos":["nus-hpc-ai-lab/opendit"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/draganything-motion-control-for-anything","slug":"draganything-motion-control-for-anything","title":"DragAnything: Motion Control for Anything using Entity Representation","date":"2024-03-12","arxiv_id":"2403.07420","repositories_listed":2,"syntology":{"n":15,"n_ran":13,"n_constructed":1,"n_ran_checked":7,"n_instrument":6,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":5,"n_pointer_only":13,"phrase":"13 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/draganything-motion-control-for-anything#ran","syntology_url":"https://syntology.ai/paper/2403.07420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07420"}},"official":{"repos":["showlab/draganything"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/videocrafter2-overcoming-data-limitations-for","slug":"videocrafter2-overcoming-data-limitations-for","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","date":"2024-01-17","arxiv_id":"2401.09047","repositories_listed":2,"syntology":{"n":21,"n_ran":15,"n_constructed":1,"n_ran_checked":8,"n_instrument":7,"n_unverified":6,"n_honours":3,"n_violates":3,"n_no_contract":2,"n_pointer_only":21,"phrase":"15 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 3 violated, 2 with no contract checked; 7 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/videocrafter2-overcoming-data-limitations-for#ran","syntology_url":"https://syntology.ai/paper/2401.09047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09047"}},"official":{"repos":["ailab-cvc/videocrafter"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/vlogger-make-your-dream-a-vlog","slug":"vlogger-make-your-dream-a-vlog","title":"Vlogger: Make Your Dream A Vlog","date":"2024-01-17","arxiv_id":"2401.09414","repositories_listed":2,"syntology":{"n":15,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":7,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vlogger-make-your-dream-a-vlog#ran","syntology_url":"https://syntology.ai/paper/2401.09414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.09414"}},"official":{"repos":["zhuangshaobin/vlogger"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/aigcbench-comprehensive-evaluation-of-image","slug":"aigcbench-comprehensive-evaluation-of-image","title":"AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI","date":"2024-01-03","arxiv_id":"2401.01651","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/aigcbench-comprehensive-evaluation-of-image#ran","syntology_url":"https://syntology.ai/paper/2401.01651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01651"}},"official":{"repos":["benchcouncil/aigcbench"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/moonshot-towards-controllable-video","slug":"moonshot-towards-controllable-video","title":"Moonshot: Towards Controllable Video Generation and Editing with Multimodal Conditions","date":"2024-01-03","arxiv_id":"2401.01827","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":0,"n_instrument":5,"n_unverified":2,"n_honours":0,"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; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/moonshot-towards-controllable-video#ran","syntology_url":"https://syntology.ai/paper/2401.01827","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01827"}},"official":{"repos":["salesforce/lavis"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/i2v-adapter-a-general-image-to-video-adapter","slug":"i2v-adapter-a-general-image-to-video-adapter","title":"I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models","date":"2023-12-27","arxiv_id":"2312.16693","repositories_listed":2,"syntology":{"n":29,"n_ran":20,"n_constructed":0,"n_ran_checked":8,"n_instrument":12,"n_unverified":9,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":18,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 12 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/i2v-adapter-a-general-image-to-video-adapter#ran","syntology_url":"https://syntology.ai/paper/2312.16693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.16693"}},"official":{"repos":["KwaiVGI/I2V-Adapter"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/videolcm-video-latent-consistency-model","slug":"videolcm-video-latent-consistency-model","title":"VideoLCM: Video Latent Consistency Model","date":"2023-12-14","arxiv_id":"2312.09109","repositories_listed":2,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":9,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videolcm-video-latent-consistency-model#ran","syntology_url":"https://syntology.ai/paper/2312.09109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.09109"}},"official":null}},{"url":"/paper/magicdance-realistic-human-dance-video","slug":"magicdance-realistic-human-dance-video","title":"MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion","date":"2023-11-18","arxiv_id":"2311.12052","repositories_listed":2,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":14,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":19,"phrase":"17 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/magicdance-realistic-human-dance-video#ran","syntology_url":"https://syntology.ai/paper/2311.12052","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12052"}},"official":{"repos":["boese0601/magicdance"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/lavie-high-quality-video-generation-with","slug":"lavie-high-quality-video-generation-with","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","date":"2023-09-26","arxiv_id":"2309.15103","repositories_listed":2,"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/lavie-high-quality-video-generation-with#ran","syntology_url":"https://syntology.ai/paper/2309.15103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15103"}},"official":{"repos":["Vchitect/LaVie"],"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":["official"]}}},{"url":"/paper/free-bloom-zero-shot-text-to-video-generator","slug":"free-bloom-zero-shot-text-to-video-generator","title":"Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator","date":"2023-09-25","arxiv_id":"2309.14494","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/free-bloom-zero-shot-text-to-video-generator#ran","syntology_url":"https://syntology.ai/paper/2309.14494","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.14494"}},"official":{"repos":["soolab/free-bloom"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/follow-your-pose-pose-guided-text-to-video","slug":"follow-your-pose-pose-guided-text-to-video","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","date":"2023-04-03","arxiv_id":"2304.01186","repositories_listed":2,"syntology":{"n":10,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 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; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/follow-your-pose-pose-guided-text-to-video#ran","syntology_url":"https://syntology.ai/paper/2304.01186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.01186"}},"official":{"repos":["mayuelala/followyourpose"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/decomposed-diffusion-models-for-high-quality","slug":"decomposed-diffusion-models-for-high-quality","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","date":"2023-03-15","arxiv_id":"2303.08320","repositories_listed":2,"syntology":null},{"url":"/paper/moso-decomposing-motion-scene-and-object-for","slug":"moso-decomposing-motion-scene-and-object-for","title":"MOSO: Decomposing MOtion, Scene and Object for Video Prediction","date":"2023-03-07","arxiv_id":"2303.03684","repositories_listed":2,"syntology":null},{"url":"/paper/scalable-adaptive-computation-for-iterative","slug":"scalable-adaptive-computation-for-iterative","title":"Scalable Adaptive Computation for Iterative Generation","date":"2022-12-22","arxiv_id":"2212.11972","repositories_listed":2,"syntology":{"n":29,"n_ran":21,"n_constructed":9,"n_ran_checked":18,"n_instrument":3,"n_unverified":8,"n_honours":8,"n_violates":0,"n_no_contract":10,"n_pointer_only":1,"phrase":"21 ran (of which 9 constructed an object rather than computing a result; 18 with no instrument failure: 8 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/scalable-adaptive-computation-for-iterative#ran","syntology_url":"https://syntology.ai/paper/2212.11972","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.11972"}},"official":{"repos":["google-research/pix2seq"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":2,"n_ran_no_instrument_failure":10,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/phenaki-variable-length-video-generation-from","slug":"phenaki-variable-length-video-generation-from","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","date":"2022-10-05","arxiv_id":"2210.02399","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":0,"n_pointer_only":2,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/phenaki-variable-length-video-generation-from#ran","syntology_url":"https://syntology.ai/paper/2210.02399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02399"}},"official":null}},{"url":"/paper/temporally-consistent-video-transformer-for","slug":"temporally-consistent-video-transformer-for","title":"Temporally Consistent Transformers for Video Generation","date":"2022-10-05","arxiv_id":"2210.02396","repositories_listed":2,"syntology":null},{"url":"/paper/make-a-video-text-to-video-generation-without","slug":"make-a-video-text-to-video-generation-without","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","date":"2022-09-29","arxiv_id":"2209.14792","repositories_listed":2,"syntology":null},{"url":"/paper/diffusion-models-a-comprehensive-survey-of","slug":"diffusion-models-a-comprehensive-survey-of","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","date":"2022-09-02","arxiv_id":"2209.00796","repositories_listed":2,"syntology":null},{"url":"/paper/masked-conditional-video-diffusion-for","slug":"masked-conditional-video-diffusion-for","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","date":"2022-05-19","arxiv_id":"2205.09853","repositories_listed":2,"syntology":{"n":16,"n_ran":7,"n_constructed":1,"n_ran_checked":4,"n_instrument":3,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"7 ran (of which 1 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) · 9 unverified","sample_list":"/paper/masked-conditional-video-diffusion-for#ran","syntology_url":"https://syntology.ai/paper/2205.09853","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09853"}},"official":{"repos":["voletiv/mcvd-pytorch"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/utilizing-evidence-spans-via-sequence-level","slug":"utilizing-evidence-spans-via-sequence-level","title":"Long Context Question Answering via Supervised Contrastive Learning","date":"2021-12-16","arxiv_id":"2112.08777","repositories_listed":2,"syntology":null},{"url":"/paper/virtualconductor-music-driven-conducting","slug":"virtualconductor-music-driven-conducting","title":"VirtualConductor: Music-driven Conducting Video Generation System","date":"2021-07-28","arxiv_id":"2108.04350","repositories_listed":2,"syntology":null},{"url":"/paper/video-generation-from-single-semantic-label","slug":"video-generation-from-single-semantic-label","title":"Video Generation from Single Semantic Label Map","date":"2019-03-11","arxiv_id":"1903.04480","repositories_listed":2,"syntology":null},{"url":"/paper/tganv2-efficient-training-of-large-models-for","slug":"tganv2-efficient-training-of-large-models-for","title":"Train Sparsely, Generate Densely: Memory-efficient Unsupervised Training of High-resolution Temporal GAN","date":"2018-11-22","arxiv_id":"1811.09245","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/tganv2-efficient-training-of-large-models-for#ran","syntology_url":"https://syntology.ai/paper/1811.09245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.09245"}},"official":{"repos":["pfnet-research/tgan2"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/unsupervised-learning-for-physical","slug":"unsupervised-learning-for-physical","title":"Unsupervised Learning for Physical Interaction through Video Prediction","date":"2016-05-23","arxiv_id":"1605.07157","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":1,"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; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/unsupervised-learning-for-physical#ran","syntology_url":"https://syntology.ai/paper/1605.07157","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.07157"}},"official":null}},{"url":"/paper/i-2-world-intra-inter-tokenization-for","slug":"i-2-world-intra-inter-tokenization-for","title":"$I^{2}$-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting","date":"2025-07-12","arxiv_id":"2507.09144","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-rl-to-long-videos","slug":"scaling-rl-to-long-videos","title":"Scaling RL to Long Videos","date":"2025-07-10","arxiv_id":"2507.07966","repositories_listed":1,"syntology":{"n":24,"n_ran":18,"n_constructed":1,"n_ran_checked":7,"n_instrument":11,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":1,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 11 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/scaling-rl-to-long-videos#ran","syntology_url":"https://syntology.ai/paper/2507.07966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.07966"}},"official":{"repos":["hiyouga/easyr1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/omni-video-democratizing-unified-video","slug":"omni-video-democratizing-unified-video","title":"Omni-Video: Democratizing Unified Video Understanding and Generation","date":"2025-07-08","arxiv_id":"2507.06119","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_constructed":0,"n_ran_checked":8,"n_instrument":6,"n_unverified":4,"n_honours":2,"n_violates":1,"n_no_contract":5,"n_pointer_only":18,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/omni-video-democratizing-unified-video#ran","syntology_url":"https://syntology.ai/paper/2507.06119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06119"}},"official":{"repos":["sais-fuxi/omni-video"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/presentagent-multimodal-agent-for","slug":"presentagent-multimodal-agent-for","title":"PresentAgent: Multimodal Agent for Presentation Video Generation","date":"2025-07-05","arxiv_id":"2507.04036","repositories_listed":1,"syntology":null},{"url":"/paper/lost-in-latent-space-an-empirical-study-of","slug":"lost-in-latent-space-an-empirical-study-of","title":"Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation","date":"2025-07-03","arxiv_id":"2507.02608","repositories_listed":1,"syntology":null},{"url":"/paper/epona-autoregressive-diffusion-world-model","slug":"epona-autoregressive-diffusion-world-model","title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving","date":"2025-06-30","arxiv_id":"2506.24113","repositories_listed":1,"syntology":null},{"url":"/paper/matrix-game-interactive-world-foundation","slug":"matrix-game-interactive-world-foundation","title":"Matrix-Game: Interactive World Foundation Model","date":"2025-06-23","arxiv_id":"2506.18701","repositories_listed":1,"syntology":null},{"url":"/paper/show-o2-improved-native-unified-multimodal","slug":"show-o2-improved-native-unified-multimodal","title":"Show-o2: Improved Native Unified Multimodal Models","date":"2025-06-18","arxiv_id":"2506.15564","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":4,"n_instrument":7,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":5,"phrase":"11 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; 7 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/show-o2-improved-native-unified-multimodal#ran","syntology_url":"https://syntology.ai/paper/2506.15564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.15564"}},"official":{"repos":["showlab/show-o"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/causally-steered-diffusion-for-automated","slug":"causally-steered-diffusion-for-automated","title":"Causally Steered Diffusion for Automated Video Counterfactual Generation","date":"2025-06-17","arxiv_id":"2506.14404","repositories_listed":1,"syntology":null},{"url":"/paper/2506-10540","slug":"2506-10540","title":"AniMaker: Automated Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation","date":"2025-06-12","arxiv_id":"2506.10540","repositories_listed":1,"syntology":null},{"url":"/paper/cosmos-drive-dreams-scalable-synthetic","slug":"cosmos-drive-dreams-scalable-synthetic","title":"Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models","date":"2025-06-10","arxiv_id":"2506.09042","repositories_listed":1,"syntology":null},{"url":"/paper/flagevalmm-a-flexible-framework-for","slug":"flagevalmm-a-flexible-framework-for","title":"FlagEvalMM: A Flexible Framework for Comprehensive Multimodal Model Evaluation","date":"2025-06-10","arxiv_id":"2506.09081","repositories_listed":1,"syntology":null},{"url":"/paper/generative-modeling-of-weights-generalization","slug":"generative-modeling-of-weights-generalization","title":"Generative Modeling of Weights: Generalization or Memorization?","date":"2025-06-09","arxiv_id":"2506.07998","repositories_listed":1,"syntology":null},{"url":"/paper/feat-full-dimensional-efficient-attention","slug":"feat-full-dimensional-efficient-attention","title":"FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation","date":"2025-06-05","arxiv_id":"2506.04956","repositories_listed":1,"syntology":null},{"url":"/paper/orv-4d-occupancy-centric-robot-video","slug":"orv-4d-occupancy-centric-robot-video","title":"ORV: 4D Occupancy-centric Robot Video Generation","date":"2025-06-03","arxiv_id":"2506.03079","repositories_listed":1,"syntology":{"n":18,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":12,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 2 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/orv-4d-occupancy-centric-robot-video#ran","syntology_url":"https://syntology.ai/paper/2506.03079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.03079"}},"official":{"repos":["orangesodahub/orv"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/svimo-synchronized-diffusion-for-video-and","slug":"svimo-synchronized-diffusion-for-video-and","title":"SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios","date":"2025-06-03","arxiv_id":"2506.02444","repositories_listed":1,"syntology":null},{"url":"/paper/omniv2v-versatile-video-generation-and","slug":"omniv2v-versatile-video-generation-and","title":"OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulation","date":"2025-06-02","arxiv_id":"2506.01801","repositories_listed":1,"syntology":null},{"url":"/paper/stork-improving-the-fidelity-of-mid-nfe","slug":"stork-improving-the-fidelity-of-mid-nfe","title":"STORK: Improving the Fidelity of Mid-NFE Sampling for Diffusion and Flow Matching Models","date":"2025-05-30","arxiv_id":"2505.24210","repositories_listed":1,"syntology":null},{"url":"/paper/hypermotion-dit-based-pose-guided-human-image","slug":"hypermotion-dit-based-pose-guided-human-image","title":"HyperMotion: DiT-Based Pose-Guided Human Image Animation of Complex Motions","date":"2025-05-29","arxiv_id":"2505.22977","repositories_listed":1,"syntology":null},{"url":"/paper/magref-masked-guidance-for-any-reference","slug":"magref-masked-guidance-for-any-reference","title":"MAGREF: Masked Guidance for Any-Reference Video Generation","date":"2025-05-29","arxiv_id":"2505.23742","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":4,"n_honours":1,"n_violates":2,"n_no_contract":2,"n_pointer_only":5,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 2 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/magref-masked-guidance-for-any-reference#ran","syntology_url":"https://syntology.ai/paper/2505.23742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23742"}},"official":{"repos":["magref-video/magref"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}}],"syntology_records":59,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":257,"papers_where_code_ran_first_page":"/task/video-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":15,"url":"/task/video-generation/papers/2","json":"/task/video-generation/papers/2.json","rows":100},{"order":"archive","page":3,"of":15,"url":"/task/video-generation/papers/3","json":"/task/video-generation/papers/3.json","rows":100},{"order":"archive","page":4,"of":15,"url":"/task/video-generation/papers/4","json":"/task/video-generation/papers/4.json","rows":100},{"order":"archive","page":5,"of":15,"url":"/task/video-generation/papers/5","json":"/task/video-generation/papers/5.json","rows":100},{"order":"archive","page":6,"of":15,"url":"/task/video-generation/papers/6","json":"/task/video-generation/papers/6.json","rows":100},{"order":"archive","page":7,"of":15,"url":"/task/video-generation/papers/7","json":"/task/video-generation/papers/7.json","rows":100},{"order":"archive","page":8,"of":15,"url":"/task/video-generation/papers/8","json":"/task/video-generation/papers/8.json","rows":100},{"order":"archive","page":9,"of":15,"url":"/task/video-generation/papers/9","json":"/task/video-generation/papers/9.json","rows":100},{"order":"archive","page":10,"of":15,"url":"/task/video-generation/papers/10","json":"/task/video-generation/papers/10.json","rows":100},{"order":"archive","page":11,"of":15,"url":"/task/video-generation/papers/11","json":"/task/video-generation/papers/11.json","rows":100},{"order":"archive","page":12,"of":15,"url":"/task/video-generation/papers/12","json":"/task/video-generation/papers/12.json","rows":100},{"order":"archive","page":13,"of":15,"url":"/task/video-generation/papers/13","json":"/task/video-generation/papers/13.json","rows":100},{"order":"archive","page":14,"of":15,"url":"/task/video-generation/papers/14","json":"/task/video-generation/papers/14.json","rows":100},{"order":"archive","page":15,"of":15,"url":"/task/video-generation/papers/15","json":"/task/video-generation/papers/15.json","rows":66},{"order":"ran","page":1,"of":3,"url":"/task/video-generation/papers/ran/1","json":"/task/video-generation/papers/ran/1.json","rows":100},{"order":"ran","page":2,"of":3,"url":"/task/video-generation/papers/ran/2","json":"/task/video-generation/papers/ran/2.json","rows":100},{"order":"ran","page":3,"of":3,"url":"/task/video-generation/papers/ran/3","json":"/task/video-generation/papers/ran/3.json","rows":57}],"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":"3f2768b0e24121035e7e0fe8b875b0acabf339e125189fce0261545f747f9e91","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}