{"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-prediction","name":"Video Prediction","slug":"video-prediction","description_markdown":null,"categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Time Series","url":"/area/time-series"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":394,"papers_with_code":208,"benchmarks":19,"benchmark_tables_in_archive":19,"benchmark_tables_shown":19,"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":25,"subtasks":2,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/video-prediction-on-kth","slug":"video-prediction-on-kth","dataset":"KTH","dataset_url":"/dataset/kth","rows_in_archive":31,"metrics":["FVD","SSIM","PSNR","LPIPS","Cond","Train","Pred","Params (M)","MSE","Diversity"],"first_row_in_archive_order":{"model":"Grid-keypoints","paper_title":"Accurate Grid Keypoint Learning for Efficient Video Prediction","paper_url":"/paper/accurate-grid-keypoint-learning-for-efficient","paper_date":"2021-07-28","arxiv_id":"2107.13170","code_links":[{"title":"xjgaocs/Grid-Keypoint-Learning","url":"https://github.com/xjgaocs/Grid-Keypoint-Learning"}],"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/accurate-grid-keypoint-learning-for-efficient#ran","syntology_url":"https://syntology.ai/paper/2107.13170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.13170"}},"official":{"repos":["xjgaocs/Grid-Keypoint-Learning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-prediction-on-moving-mnist","slug":"video-prediction-on-moving-mnist","dataset":"Moving MNIST","dataset_url":"/dataset/moving-mnist","rows_in_archive":31,"metrics":["MSE","MAE","SSIM","LPIPS","PSNR"],"first_row_in_archive_order":{"model":"PredFormer","paper_title":"Video Prediction Transformers without Recurrence or Convolution","paper_url":"/paper/predformer-transformers-are-effective-spatial","paper_date":"2024-10-07","arxiv_id":"2410.04733","code_links":[{"title":"yyyujintang/predformer","url":"https://github.com/yyyujintang/predformer"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-kinetics-600-12-frames","slug":"video-prediction-on-kinetics-600-12-frames","dataset":"Kinetics-600 12 frames, 64x64","dataset_url":"/dataset/kinetics","rows_in_archive":16,"metrics":["FVD","IS","Cond","Pred"],"first_row_in_archive_order":{"model":"SiD2","paper_title":"Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion","paper_url":"/paper/simpler-diffusion-sid2-1-5-fid-on-imagenet512","paper_date":"2024-10-25","arxiv_id":"2410.19324","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-human36m","slug":"video-prediction-on-human36m","dataset":"Human3.6M","dataset_url":"/dataset/human3-6m","rows_in_archive":9,"metrics":["SSIM","MSE","MAE"],"first_row_in_archive_order":{"model":"IAM4VP","paper_title":"Implicit Stacked Autoregressive Model for Video Prediction","paper_url":"/paper/implicit-stacked-autoregressive-model-for-1","paper_date":"2023-03-14","arxiv_id":"2303.07849","code_links":[{"title":"seominseok0429/Implicit-Stacked-Autoregressive-Model-for-Video-Prediction","url":"https://github.com/seominseok0429/Implicit-Stacked-Autoregressive-Model-for-Video-Prediction"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-bair-robot-pushing-1","slug":"video-prediction-on-bair-robot-pushing-1","dataset":"BAIR Robot Pushing","dataset_url":"/dataset/bair-robot-pushing","rows_in_archive":6,"metrics":["FVD"],"first_row_in_archive_order":{"model":"MAGVIT (-L-FP)","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-prediction-on-cityscapes-128x128","slug":"video-prediction-on-cityscapes-128x128","dataset":"Cityscapes 128x128","dataset_url":"/dataset/cityscapes","rows_in_archive":5,"metrics":["FVD","SSIM","PSNR","LPIPS","Cond.","Train","Pred"],"first_row_in_archive_order":{"model":"GHVAEs","paper_title":"Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction","paper_url":"/paper/greedy-hierarchical-variational-autoencoders","paper_date":"2021-03-06","arxiv_id":"2103.04174","code_links":[],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-synpickvp","slug":"video-prediction-on-synpickvp","dataset":"SynpickVP","dataset_url":"/dataset/synpick","rows_in_archive":5,"metrics":["LPIPS","MSE","PSNR","SSIM"],"first_row_in_archive_order":{"model":"MSPred","paper_title":"MSPred: Video Prediction at Multiple Spatio-Temporal Scales with Hierarchical Recurrent Networks","paper_url":"/paper/video-prediction-at-multiple-scales-with","paper_date":"2022-03-17","arxiv_id":"2203.09303","code_links":[{"title":"AIS-Bonn/MSPred","url":"https://github.com/AIS-Bonn/MSPred"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-cmu-mocap-2","slug":"video-prediction-on-cmu-mocap-2","dataset":"CMU Mocap-2","dataset_url":null,"rows_in_archive":4,"metrics":["Test Error"],"first_row_in_archive_order":{"model":"Latent SDE","paper_title":"Scalable Gradients for Stochastic Differential Equations","paper_url":"/paper/scalable-gradients-for-stochastic","paper_date":"2020-01-05","arxiv_id":"2001.01328","code_links":[{"title":"google-research/torchsde","url":"https://github.com/google-research/torchsde"},{"title":"xwinxu/bayesian-sde","url":"https://github.com/xwinxu/bayesian-sde"},{"title":"xwinxu/bayesde","url":"https://github.com/xwinxu/bayesde"},{"title":"JFagin/latent_SDE","url":"https://github.com/JFagin/latent_SDE"}],"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/scalable-gradients-for-stochastic#ran","syntology_url":"https://syntology.ai/paper/2001.01328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.01328"}},"official":{"repos":["google-research/torchsde"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-prediction-on-cityscapes-1","slug":"video-prediction-on-cityscapes-1","dataset":"Cityscapes","dataset_url":"/dataset/cityscapes","rows_in_archive":3,"metrics":["LPIPS","MS-SSIM"],"first_row_in_archive_order":{"model":"DMVFN","paper_title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","paper_url":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","paper_date":"2023-03-17","arxiv_id":"2303.09875","code_links":[{"title":"megvii-research/CVPR2023-DMVFN","url":"https://github.com/megvii-research/CVPR2023-DMVFN"}],"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-dynamic-multi-scale-voxel-flow-network-for#ran","syntology_url":"https://syntology.ai/paper/2303.09875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09875"}},"official":{"repos":["megvii-research/CVPR2023-DMVFN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-prediction-on-kitti","slug":"video-prediction-on-kitti","dataset":"KITTI","dataset_url":"/dataset/kitti","rows_in_archive":3,"metrics":["LPIPS","MS-SSIM"],"first_row_in_archive_order":{"model":"DMVFN","paper_title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","paper_url":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","paper_date":"2023-03-17","arxiv_id":"2303.09875","code_links":[{"title":"megvii-research/CVPR2023-DMVFN","url":"https://github.com/megvii-research/CVPR2023-DMVFN"}],"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-dynamic-multi-scale-voxel-flow-network-for#ran","syntology_url":"https://syntology.ai/paper/2303.09875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09875"}},"official":{"repos":["megvii-research/CVPR2023-DMVFN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-prediction-on-vimeo90k","slug":"video-prediction-on-vimeo90k","dataset":"Vimeo90K","dataset_url":"/dataset/vimeo90k-1","rows_in_archive":3,"metrics":["LPIPS","MS-SSIM"],"first_row_in_archive_order":{"model":"OPT","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-cmu-mocap-1","slug":"video-prediction-on-cmu-mocap-1","dataset":"CMU Mocap-1","dataset_url":null,"rows_in_archive":2,"metrics":["Test Error"],"first_row_in_archive_order":{"model":"ODE2VAE-KL","paper_title":"ODE$^2$VAE: Deep generative second order ODEs with Bayesian neural networks","paper_url":"/paper/ode2vae-deep-generative-second-order-odes","paper_date":"2019-05-27","arxiv_id":"1905.10994","code_links":[{"title":"cagatayyildiz/ODE2VAE","url":"https://github.com/cagatayyildiz/ODE2VAE"}],"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/ode2vae-deep-generative-second-order-odes#ran","syntology_url":"https://syntology.ai/paper/1905.10994","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.10994"}},"official":{"repos":["cagatayyildiz/ODE2VAE"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-prediction-on-davis-2017","slug":"video-prediction-on-davis-2017","dataset":"DAVIS 2017","dataset_url":"/dataset/davis-2017","rows_in_archive":2,"metrics":["LPIPS","MS-SSIM"],"first_row_in_archive_order":{"model":"DMVFN","paper_title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","paper_url":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","paper_date":"2023-03-17","arxiv_id":"2303.09875","code_links":[{"title":"megvii-research/CVPR2023-DMVFN","url":"https://github.com/megvii-research/CVPR2023-DMVFN"}],"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-dynamic-multi-scale-voxel-flow-network-for#ran","syntology_url":"https://syntology.ai/paper/2303.09875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09875"}},"official":{"repos":["megvii-research/CVPR2023-DMVFN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-prediction-on-colored-dsprites","slug":"video-prediction-on-colored-dsprites","dataset":"Colored dSprites","dataset_url":"/dataset/sprites","rows_in_archive":1,"metrics":["MSE"],"first_row_in_archive_order":{"model":"MGP-VAE (with geodesic loss)","paper_title":"Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders","paper_url":"/paper/disentangling-representations-using-gaussian","paper_date":"2020-01-08","arxiv_id":"2001.02408","code_links":[{"title":"SUTDBrainLab/MGP-VAE","url":"https://github.com/SUTDBrainLab/MGP-VAE"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-kth-64x64-cond10-pred30","slug":"video-prediction-on-kth-64x64-cond10-pred30","dataset":"KTH 64x64 cond10 pred30","dataset_url":null,"rows_in_archive":1,"metrics":["FVD"],"first_row_in_archive_order":{"model":"SRVP","paper_title":"Stochastic Latent Residual Video Prediction","paper_url":"/paper/stochastic-latent-residual-video-prediction-1","paper_date":"2020-02-21","arxiv_id":"2002.09219","code_links":[{"title":"edouardelasalles/srvp","url":"https://github.com/edouardelasalles/srvp"}],"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"10 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; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/stochastic-latent-residual-video-prediction-1#ran","syntology_url":"https://syntology.ai/paper/2002.09219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09219"}},"official":{"repos":["edouardelasalles/srvp"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}}},{"leaderboard":"/sota/video-prediction-on-mpi-sintel","slug":"video-prediction-on-mpi-sintel","dataset":"MPI Sintel","dataset_url":"/dataset/mpi-sintel","rows_in_archive":1,"metrics":["LPIPS","PSNR","SSIM","ST-RRED"],"first_row_in_archive_order":{"model":"MCnet [villegas2017mcnet]","paper_title":"Temporal View Synthesis of Dynamic Scenes through 3D Object Motion Estimation with Multi-Plane Images","paper_url":"/paper/temporal-view-synthesis-of-dynamic-scenes","paper_date":"2022-08-19","arxiv_id":"2208.09463","code_links":[{"title":"NagabhushanSN95/DeCOMPnet","url":"https://github.com/NagabhushanSN95/DeCOMPnet"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-something-something-v2","slug":"video-prediction-on-something-something-v2","dataset":"Something-Something V2","dataset_url":"/dataset/something-something-v2","rows_in_archive":1,"metrics":["FVD"],"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-prediction-on-sprites","slug":"video-prediction-on-sprites","dataset":"Sprites","dataset_url":"/dataset/sprites","rows_in_archive":1,"metrics":["MSE"],"first_row_in_archive_order":{"model":"MGP-VAE (with geodesic loss)","paper_title":"Disentangling Multiple Features in Video Sequences using Gaussian Processes in Variational Autoencoders","paper_url":"/paper/disentangling-representations-using-gaussian","paper_date":"2020-01-08","arxiv_id":"2001.02408","code_links":[{"title":"SUTDBrainLab/MGP-VAE","url":"https://github.com/SUTDBrainLab/MGP-VAE"}],"syntology":null}},{"leaderboard":"/sota/video-prediction-on-youtube-8m","slug":"video-prediction-on-youtube-8m","dataset":"YouTube-8M","dataset_url":"/dataset/youtube-8m","rows_in_archive":1,"metrics":["Average PSNR"],"first_row_in_archive_order":{"model":"SDCNet","paper_title":"SDC-Net: Video prediction using spatially-displaced convolution","paper_url":"/paper/sdc-net-video-prediction-using-spatially","paper_date":"2018-09-01","arxiv_id":null,"code_links":[{"title":"NVIDIA/semantic-segmentation","url":"https://github.com/NVIDIA/semantic-segmentation/tree/sdcnet/sdcnet"}],"syntology":null}}],"datasets":[{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/cityscapes","name":"Cityscapes","full_name":"","num_papers_in_archive":3702},{"url":"/dataset/kitti","name":"KITTI","full_name":"","num_papers_in_archive":3661},{"url":"/dataset/kinetics","name":"Kinetics","full_name":"Kinetics Human Action Video Dataset","num_papers_in_archive":1341},{"url":"/dataset/human3-6m","name":"Human3.6M","full_name":"","num_papers_in_archive":783},{"url":"/dataset/davis","name":"DAVIS","full_name":"Densely Annotated VIdeo Segmentation","num_papers_in_archive":734},{"url":"/dataset/davis-2017","name":"DAVIS 2017","full_name":"DAVIS 2017","num_papers_in_archive":308},{"url":"/dataset/something-something-v2","name":"Something-Something V2","full_name":"","num_papers_in_archive":290},{"url":"/dataset/kth","name":"KTH","full_name":"KTH Action dataset","num_papers_in_archive":279},{"url":"/dataset/vimeo90k-1","name":"Vimeo90K","full_name":"","num_papers_in_archive":220},{"url":"/dataset/mpi-sintel","name":"MPI Sintel","full_name":"","num_papers_in_archive":198},{"url":"/dataset/moving-mnist","name":"Moving MNIST","full_name":"","num_papers_in_archive":194},{"url":"/dataset/kinetics-600","name":"Kinetics-600","full_name":"","num_papers_in_archive":148},{"url":"/dataset/youtube-8m","name":"YouTube-8M","full_name":"","num_papers_in_archive":147},{"url":"/dataset/sprites","name":"Sprites","full_name":"2D Video Game Character Sprites","num_papers_in_archive":52},{"url":"/dataset/phyre","name":"PHYRE","full_name":"PHYsical REasoning","num_papers_in_archive":35},{"url":"/dataset/bair-robot-pushing","name":"BAIR Robot Pushing","full_name":"","num_papers_in_archive":27},{"url":"/dataset/robotic-pushing","name":"Robotic Pushing","full_name":"","num_papers_in_archive":12},{"url":"/dataset/earthnet2021","name":"EarthNet2021","full_name":"EarthNet2021: Earth Surface Forecasting","num_papers_in_archive":10},{"url":"/dataset/synpick","name":"SynPick","full_name":"","num_papers_in_archive":7},{"url":"/dataset/qst","name":"QST","full_name":"Quick Sky Time","num_papers_in_archive":3},{"url":"/dataset/cloudcast","name":"CloudCast","full_name":"CloudCast: A Satellite-Based Dataset and Baseline for Forecasting Clouds","num_papers_in_archive":1},{"url":"/dataset/iisc-vine","name":"IISc VINE","full_name":"Indian Institute of Science VIdeo Naturalness Evaluation","num_papers_in_archive":1},{"url":"/dataset/moving-symbols","name":"Moving Symbols","full_name":"","num_papers_in_archive":1},{"url":"/dataset/shanghai2020","name":"Shanghai2020","full_name":"Shanghai-2020 Dataset","num_papers_in_archive":0}],"subtasks":[{"url":"/task/earth-surface-forecasting","name":"Earth Surface Forecasting"},{"url":"/task/predict-future-video-frames","name":"Predict Future Video Frames"}],"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":4,"rows_per_page":100,"shown":100,"of":394,"of_with_code":208,"tagged_in_all":394,"counts":{"archive_papers_tagged":394,"with_a_code_link":208,"where_syntology_ran_a_sample":62,"not_listed_spam_title":0,"listed":394,"listed_where_code_ran":62,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":58,"every_run_a_failure_of_syntologys_instrument":4,"listed_with_a_run_with_no_instrument_failure":58,"listed_every_run_a_failure_of_syntologys_instrument":4,"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/convolutional-lstm-network-a-machine-learning","slug":"convolutional-lstm-network-a-machine-learning","title":"Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting","date":"2015-06-13","arxiv_id":"1506.04214","repositories_listed":23,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/convolutional-lstm-network-a-machine-learning#ran","syntology_url":"https://syntology.ai/paper/1506.04214","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.04214"}},"official":null}},{"url":"/paper/deep-predictive-coding-networks-for-video","slug":"deep-predictive-coding-networks-for-video","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","date":"2016-05-25","arxiv_id":"1605.08104","repositories_listed":17,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"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) · 3 unverified","sample_list":"/paper/deep-predictive-coding-networks-for-video#ran","syntology_url":"https://syntology.ai/paper/1605.08104","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1605.08104"}},"official":null}},{"url":"/paper/predrnn-towards-a-resolution-of-the-deep-in","slug":"predrnn-towards-a-resolution-of-the-deep-in","title":"PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning","date":"2018-04-17","arxiv_id":"1804.06300","repositories_listed":11,"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/predrnn-towards-a-resolution-of-the-deep-in#ran","syntology_url":"https://syntology.ai/paper/1804.06300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.06300"}},"official":{"repos":["Yunbo426/predrnn-pp"],"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/video-to-video-synthesis","slug":"video-to-video-synthesis","title":"Video-to-Video Synthesis","date":"2018-08-20","arxiv_id":"1808.06601","repositories_listed":10,"syntology":null},{"url":"/paper/efficient-multi-order-gated-aggregation","slug":"efficient-multi-order-gated-aggregation","title":"MogaNet: Multi-order Gated Aggregation Network","date":"2022-11-07","arxiv_id":"2211.03295","repositories_listed":7,"syntology":{"n":15,"n_ran":12,"n_constructed":7,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"12 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/efficient-multi-order-gated-aggregation#ran","syntology_url":"https://syntology.ai/paper/2211.03295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.03295"}},"official":{"repos":["Westlake-AI/MogaNet","Westlake-AI/openmixup","chengtan9907/OpenSTL"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":7,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["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/the-something-something-video-database-for","slug":"the-something-something-video-database-for","title":"The \"something something\" video database for learning and evaluating visual common sense","date":"2017-06-13","arxiv_id":"1706.04261","repositories_listed":5,"syntology":null},{"url":"/paper/deep-multi-scale-video-prediction-beyond-mean","slug":"deep-multi-scale-video-prediction-beyond-mean","title":"Deep multi-scale video prediction beyond mean square error","date":"2015-11-17","arxiv_id":"1511.05440","repositories_listed":5,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":4,"n_instrument":2,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"6 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; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/deep-multi-scale-video-prediction-beyond-mean#ran","syntology_url":"https://syntology.ai/paper/1511.05440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.05440"}},"official":null}},{"url":"/paper/scalable-gradients-for-stochastic","slug":"scalable-gradients-for-stochastic","title":"Scalable Gradients for Stochastic Differential Equations","date":"2020-01-05","arxiv_id":"2001.01328","repositories_listed":4,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/scalable-gradients-for-stochastic#ran","syntology_url":"https://syntology.ai/paper/2001.01328","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.01328"}},"official":{"repos":["google-research/torchsde"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sme-net-sparse-motion-estimation-for","slug":"sme-net-sparse-motion-estimation-for","title":"SME-Net: Sparse Motion Estimation for Parametric Video Prediction Through Reinforcement Learning","date":"2019-10-01","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/memory-in-memory-a-predictive-neural-network","slug":"memory-in-memory-a-predictive-neural-network","title":"Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics","date":"2018-11-19","arxiv_id":"1811.07490","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/deep-learning-for-precipitation-nowcasting-a","slug":"deep-learning-for-precipitation-nowcasting-a","title":"Deep Learning for Precipitation Nowcasting: A Benchmark and A New Model","date":"2017-06-12","arxiv_id":"1706.03458","repositories_listed":4,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":1,"n_instrument":8,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":5,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deep-learning-for-precipitation-nowcasting-a#ran","syntology_url":"https://syntology.ai/paper/1706.03458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.03458"}},"official":null}},{"url":"/paper/learning-a-driving-simulator","slug":"learning-a-driving-simulator","title":"Learning a Driving Simulator","date":"2016-08-03","arxiv_id":"1608.01230","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"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; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-a-driving-simulator#ran","syntology_url":"https://syntology.ai/paper/1608.01230","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1608.01230"}},"official":null}},{"url":"/paper/generalized-predictive-model-for-autonomous","slug":"generalized-predictive-model-for-autonomous","title":"GenAD: Generalized Predictive Model for Autonomous Driving","date":"2024-03-14","arxiv_id":"2403.09630","repositories_listed":3,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"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, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/generalized-predictive-model-for-autonomous#ran","syntology_url":"https://syntology.ai/paper/2403.09630","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.09630"}},"official":{"repos":["opendrivelab/driveagi"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/switch-ema-a-free-lunch-for-better-flatness","slug":"switch-ema-a-free-lunch-for-better-flatness","title":"Switch EMA: A Free Lunch for Better Flatness and Sharpness","date":"2024-02-14","arxiv_id":"2402.09240","repositories_listed":3,"syntology":null},{"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/video-prediction-models-as-rewards-for","slug":"video-prediction-models-as-rewards-for","title":"Video Prediction Models as Rewards for Reinforcement Learning","date":"2023-05-23","arxiv_id":"2305.14343","repositories_listed":3,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":3,"n_honours":2,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"phrase":"12 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/video-prediction-models-as-rewards-for#ran","syntology_url":"https://syntology.ai/paper/2305.14343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14343"}},"official":null}},{"url":"/paper/simvp-simpler-yet-better-video-prediction-1","slug":"simvp-simpler-yet-better-video-prediction-1","title":"SimVP: Simpler yet Better Video Prediction","date":"2022-06-09","arxiv_id":"2206.05099","repositories_listed":3,"syntology":{"n":9,"n_ran":6,"n_constructed":5,"n_ran_checked":6,"n_instrument":0,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":9,"phrase":"6 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/simvp-simpler-yet-better-video-prediction-1#ran","syntology_url":"https://syntology.ai/paper/2206.05099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.05099"}},"official":{"repos":["gaozhangyang/simvp-simpler-yet-better-video-prediction"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":5,"n_ran_no_instrument_failure":6,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/predrnn-a-recurrent-neural-network-for","slug":"predrnn-a-recurrent-neural-network-for","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","date":"2021-03-17","arxiv_id":"2103.09504","repositories_listed":3,"syntology":null},{"url":"/paper/disentangling-physical-dynamics-from-unknown","slug":"disentangling-physical-dynamics-from-unknown","title":"Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction","date":"2020-03-03","arxiv_id":"2003.01460","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/disentangling-physical-dynamics-from-unknown#ran","syntology_url":"https://syntology.ai/paper/2003.01460","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01460"}},"official":{"repos":["vincent-leguen/PhyDNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/video-action-classification-using-prednet","slug":"video-action-classification-using-prednet","title":"PredNet and Predictive Coding: A Critical Review","date":"2019-06-14","arxiv_id":"1906.11902","repositories_listed":3,"syntology":null},{"url":"/paper/eidetic-3d-lstm-a-model-for-video-prediction","slug":"eidetic-3d-lstm-a-model-for-video-prediction","title":"Eidetic 3D LSTM: A Model for Video Prediction and Beyond","date":"2019-05-01","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/towards-accurate-generative-models-of-video-a","slug":"towards-accurate-generative-models-of-video-a","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","date":"2018-12-03","arxiv_id":"1812.01717","repositories_listed":3,"syntology":null},{"url":"/paper/robustness-via-retrying-closed-loop-robotic","slug":"robustness-via-retrying-closed-loop-robotic","title":"Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning","date":"2018-10-06","arxiv_id":"1810.03043","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/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/self-supervised-visual-planning-with-temporal","slug":"self-supervised-visual-planning-with-temporal","title":"Self-Supervised Visual Planning with Temporal Skip Connections","date":"2017-10-15","arxiv_id":"1710.05268","repositories_listed":3,"syntology":null},{"url":"/paper/video-frame-synthesis-using-deep-voxel-flow","slug":"video-frame-synthesis-using-deep-voxel-flow","title":"Video Frame Synthesis using Deep Voxel Flow","date":"2017-02-08","arxiv_id":"1702.02463","repositories_listed":3,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-frame-synthesis-using-deep-voxel-flow#ran","syntology_url":"https://syntology.ai/paper/1702.02463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.02463"}},"official":null}},{"url":"/paper/rethinking-urban-mobility-prediction-a-super","slug":"rethinking-urban-mobility-prediction-a-super","title":"Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach","date":"2023-12-04","arxiv_id":"2312.01699","repositories_listed":2,"syntology":null},{"url":"/paper/forecasting-localized-weather-impacts-on","slug":"forecasting-localized-weather-impacts-on","title":"Multi-modal learning for geospatial vegetation forecasting","date":"2023-03-28","arxiv_id":"2303.16198","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/forecasting-localized-weather-impacts-on#ran","syntology_url":"https://syntology.ai/paper/2303.16198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.16198"}},"official":{"repos":["vitusbenson/greenearthnet","earthnet2021/earthnet-models-pytorch"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/predictive-experience-replay-for-continual","slug":"predictive-experience-replay-for-continual","title":"Predictive Experience Replay for Continual Visual Control and Forecasting","date":"2023-03-12","arxiv_id":"2303.06572","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/predictive-experience-replay-for-continual#ran","syntology_url":"https://syntology.ai/paper/2303.06572","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.06572"}},"official":{"repos":["wendongzh/continual_visual_control","jc043/cpl"],"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":["unlocated"]}}},{"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/simvp-towards-simple-yet-powerful","slug":"simvp-towards-simple-yet-powerful","title":"SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning","date":"2022-11-22","arxiv_id":"2211.12509","repositories_listed":2,"syntology":null},{"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/temporal-attention-unit-towards-efficient","slug":"temporal-attention-unit-towards-efficient","title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","date":"2022-06-24","arxiv_id":"2206.12126","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/reinforcement-learning-with-action-free-pre","slug":"reinforcement-learning-with-action-free-pre","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","date":"2022-03-25","arxiv_id":"2203.13880","repositories_listed":2,"syntology":null},{"url":"/paper/earthnet2021-a-large-scale-dataset-and","slug":"earthnet2021-a-large-scale-dataset-and","title":"EarthNet2021: A large-scale dataset and challenge for Earth surface forecasting as a guided video prediction task","date":"2021-04-16","arxiv_id":"2104.10066","repositories_listed":2,"syntology":null},{"url":"/paper/clockwork-variational-autoencoders-for-video","slug":"clockwork-variational-autoencoders-for-video","title":"Clockwork Variational Autoencoders","date":"2021-02-18","arxiv_id":"2102.09532","repositories_listed":2,"syntology":null},{"url":"/paper/self-attention-convlstm-for-spatiotemporal","slug":"self-attention-convlstm-for-spatiotemporal","title":"Self-Attention ConvLSTM for Spatiotemporal Prediction","date":"2020-04-03","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/visuospatial-foresight-for-multi-step-multi","slug":"visuospatial-foresight-for-multi-step-multi","title":"VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation","date":"2020-03-19","arxiv_id":"2003.09044","repositories_listed":2,"syntology":null},{"url":"/paper/convolutional-tensor-train-lstm-for-spatio","slug":"convolutional-tensor-train-lstm-for-spatio","title":"Convolutional Tensor-Train LSTM for Spatio-temporal Learning","date":"2020-02-21","arxiv_id":"2002.09131","repositories_listed":2,"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":2,"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/convolutional-tensor-train-lstm-for-spatio#ran","syntology_url":"https://syntology.ai/paper/2002.09131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09131"}},"official":{"repos":["NVlabs/conv-tt-lstm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/inception-inspired-lstm-for-next-frame-video","slug":"inception-inspired-lstm-for-next-frame-video","title":"Inception-inspired LSTM for Next-frame Video Prediction","date":"2019-08-28","arxiv_id":"1909.05622","repositories_listed":2,"syntology":null},{"url":"/paper/compositional-video-prediction","slug":"compositional-video-prediction","title":"Compositional Video Prediction","date":"2019-08-22","arxiv_id":"1908.08522","repositories_listed":2,"syntology":null},{"url":"/paper/model-based-reinforcement-learning-for-atari","slug":"model-based-reinforcement-learning-for-atari","title":"Model-Based Reinforcement Learning for Atari","date":"2019-03-01","arxiv_id":"1903.00374","repositories_listed":2,"syntology":{"n":21,"n_ran":16,"n_constructed":8,"n_ran_checked":10,"n_instrument":6,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":17,"phrase":"16 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/model-based-reinforcement-learning-for-atari#ran","syntology_url":"https://syntology.ai/paper/1903.00374","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.00374"}},"official":{"repos":["tensorflow/tensor2tensor"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/sdcnet-video-prediction-using-spatially","slug":"sdcnet-video-prediction-using-spatially","title":"SDCNet: Video Prediction Using Spatially-Displaced Convolution","date":"2018-11-02","arxiv_id":"1811.00684","repositories_listed":2,"syntology":null},{"url":"/paper/predrnn-recurrent-neural-networks-for-1","slug":"predrnn-recurrent-neural-networks-for-1","title":"PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs","date":"2017-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/learning-to-generate-long-term-future-via","slug":"learning-to-generate-long-term-future-via","title":"Learning to Generate Long-term Future via Hierarchical Prediction","date":"2017-04-19","arxiv_id":"1704.05831","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/learning-to-generate-long-term-future-via#ran","syntology_url":"https://syntology.ai/paper/1704.05831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.05831"}},"official":null}},{"url":"/paper/predicting-deeper-into-the-future-of-semantic","slug":"predicting-deeper-into-the-future-of-semantic","title":"Predicting Deeper into the Future of Semantic Segmentation","date":"2017-03-22","arxiv_id":"1703.07684","repositories_listed":2,"syntology":null},{"url":"/paper/expert-gate-lifelong-learning-with-a-network","slug":"expert-gate-lifelong-learning-with-a-network","title":"Expert Gate: Lifelong Learning with a Network of Experts","date":"2016-11-18","arxiv_id":"1611.06194","repositories_listed":2,"syntology":null},{"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/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/autoregression-free-video-prediction-using","slug":"autoregression-free-video-prediction-using","title":"Autoregression-free video prediction using diffusion model for mitigating error propagation","date":"2025-05-28","arxiv_id":"2505.22111","repositories_listed":1,"syntology":null},{"url":"/paper/programmatic-video-prediction-using-large","slug":"programmatic-video-prediction-using-large","title":"Programmatic Video Prediction Using Large Language Models","date":"2025-05-20","arxiv_id":"2505.14948","repositories_listed":1,"syntology":null},{"url":"/paper/video-gpt-via-next-clip-diffusion","slug":"video-gpt-via-next-clip-diffusion","title":"Video-GPT via Next Clip Diffusion","date":"2025-05-18","arxiv_id":"2505.12489","repositories_listed":1,"syntology":null},{"url":"/paper/srvp-strong-recollection-video-prediction","slug":"srvp-strong-recollection-video-prediction","title":"SRVP: Strong Recollection Video Prediction Model Using Attention-Based Spatiotemporal Correlation Fusion","date":"2025-04-10","arxiv_id":"2504.08012","repositories_listed":1,"syntology":null},{"url":"/paper/syncvp-joint-diffusion-for-synchronous-multi","slug":"syncvp-joint-diffusion-for-synchronous-multi","title":"SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction","date":"2025-03-24","arxiv_id":"2503.18933","repositories_listed":1,"syntology":null},{"url":"/paper/gmg-a-video-prediction-method-based-on-global","slug":"gmg-a-video-prediction-method-based-on-global","title":"GMG: A Video Prediction Method Based on Global Focus and Motion Guided","date":"2025-03-14","arxiv_id":"2503.11297","repositories_listed":1,"syntology":null},{"url":"/paper/dynamical-diffusion-learning-temporal","slug":"dynamical-diffusion-learning-temporal","title":"Dynamical Diffusion: Learning Temporal Dynamics with Diffusion Models","date":"2025-03-02","arxiv_id":"2503.00951","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/dynamical-diffusion-learning-temporal#ran","syntology_url":"https://syntology.ai/paper/2503.00951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00951"}},"official":{"repos":["thuml/dynamical-diffusion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/intuitive-physics-understanding-emerges-from","slug":"intuitive-physics-understanding-emerges-from","title":"Intuitive physics understanding emerges from self-supervised pretraining on natural videos","date":"2025-02-17","arxiv_id":"2502.11831","repositories_listed":1,"syntology":null},{"url":"/paper/maskgwm-a-generalizable-driving-world-model","slug":"maskgwm-a-generalizable-driving-world-model","title":"MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction","date":"2025-02-17","arxiv_id":"2502.11663","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":1,"n_ran_checked":2,"n_instrument":2,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"4 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/maskgwm-a-generalizable-driving-world-model#ran","syntology_url":"https://syntology.ai/paper/2502.11663","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11663"}},"official":{"repos":["sensetime-fvg/opendwm"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/playslot-learning-inverse-latent-dynamics-for","slug":"playslot-learning-inverse-latent-dynamics-for","title":"PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planning","date":"2025-02-11","arxiv_id":"2502.07600","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":7,"phrase":"2 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; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/playslot-learning-inverse-latent-dynamics-for#ran","syntology_url":"https://syntology.ai/paper/2502.07600","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07600"}},"official":null}},{"url":"/paper/video-prediction-policy-a-generalist-robot","slug":"video-prediction-policy-a-generalist-robot","title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","date":"2024-12-19","arxiv_id":"2412.14803","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 3 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) · 1 unverified","sample_list":"/paper/video-prediction-policy-a-generalist-robot#ran","syntology_url":"https://syntology.ai/paper/2412.14803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14803"}},"official":null}},{"url":"/paper/motion-graph-unleashed-a-novel-approach-to","slug":"motion-graph-unleashed-a-novel-approach-to","title":"Motion Graph Unleashed: A Novel Approach to Video Prediction","date":"2024-10-29","arxiv_id":"2410.22288","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":4,"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) · 1 unverified","sample_list":"/paper/motion-graph-unleashed-a-novel-approach-to#ran","syntology_url":"https://syntology.ai/paper/2410.22288","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.22288"}},"official":{"repos":["Kay1794/Motion-Graph-Video-Prediction"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/predformer-transformers-are-effective-spatial","slug":"predformer-transformers-are-effective-spatial","title":"Video Prediction Transformers without Recurrence or Convolution","date":"2024-10-07","arxiv_id":"2410.04733","repositories_listed":1,"syntology":null},{"url":"/paper/advection-augmented-convolutional-neural","slug":"advection-augmented-convolutional-neural","title":"Advection Augmented Convolutional Neural Networks","date":"2024-06-27","arxiv_id":"2406.19253","repositories_listed":1,"syntology":null},{"url":"/paper/video-occupancy-models","slug":"video-occupancy-models","title":"Video Occupancy Models","date":"2024-06-25","arxiv_id":"2407.09533","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":0,"n_honours":3,"n_violates":0,"n_no_contract":0,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-occupancy-models#ran","syntology_url":"https://syntology.ai/paper/2407.09533","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.09533"}},"official":{"repos":["manantomar/video-occupancy-models"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/slot-state-space-models","slug":"slot-state-space-models","title":"Slot State Space Models","date":"2024-06-18","arxiv_id":"2406.12272","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/slot-state-space-models#ran","syntology_url":"https://syntology.ai/paper/2406.12272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.12272"}},"official":{"repos":["jindongjiang/slotssms"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/omnitokenizer-a-joint-image-video-tokenizer","slug":"omnitokenizer-a-joint-image-video-tokenizer","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","date":"2024-06-13","arxiv_id":"2406.09399","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/omnitokenizer-a-joint-image-video-tokenizer#ran","syntology_url":"https://syntology.ai/paper/2406.09399","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09399"}},"official":{"repos":["foundationvision/omnitokenizer"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/ctrl-v-higher-fidelity-video-generation-with","slug":"ctrl-v-higher-fidelity-video-generation-with","title":"Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object Motion","date":"2024-06-09","arxiv_id":"2406.05630","repositories_listed":1,"syntology":null},{"url":"/paper/ivideogpt-interactive-videogpts-are-scalable","slug":"ivideogpt-interactive-videogpts-are-scalable","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","date":"2024-05-24","arxiv_id":"2405.15223","repositories_listed":1,"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":1,"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/ivideogpt-interactive-videogpts-are-scalable#ran","syntology_url":"https://syntology.ai/paper/2405.15223","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15223"}},"official":{"repos":["thuml/iVideoGPT"],"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/general-surgery-vision-transformer-a-video","slug":"general-surgery-vision-transformer-a-video","title":"General surgery vision transformer: A video pre-trained foundation model for general surgery","date":"2024-03-09","arxiv_id":"2403.05949","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-augmentation-training-makes","slug":"adversarial-augmentation-training-makes","title":"Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts","date":"2024-01-21","arxiv_id":"2401.11406","repositories_listed":1,"syntology":null},{"url":"/paper/stdiff-spatio-temporal-diffusion-for","slug":"stdiff-spatio-temporal-diffusion-for","title":"STDiff: Spatio-temporal Diffusion for Continuous Stochastic Video Prediction","date":"2023-12-11","arxiv_id":"2312.06486","repositories_listed":1,"syntology":null},{"url":"/paper/svq-sparse-vector-quantization-for","slug":"svq-sparse-vector-quantization-for","title":"Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach","date":"2023-12-06","arxiv_id":"2312.03406","repositories_listed":1,"syntology":null},{"url":"/paper/pair-wise-layer-attention-with-spatial","slug":"pair-wise-layer-attention-with-spatial","title":"Pair-wise Layer Attention with Spatial Masking for Video Prediction","date":"2023-11-19","arxiv_id":"2311.11289","repositories_listed":1,"syntology":null},{"url":"/paper/seine-short-to-long-video-diffusion-model-for","slug":"seine-short-to-long-video-diffusion-model-for","title":"SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction","date":"2023-10-31","arxiv_id":"2310.20700","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/seine-short-to-long-video-diffusion-model-for#ran","syntology_url":"https://syntology.ai/paper/2310.20700","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20700"}},"official":null}},{"url":"/paper/mmvp-motion-matrix-based-video-prediction","slug":"mmvp-motion-matrix-based-video-prediction","title":"MMVP: Motion-Matrix-based Video Prediction","date":"2023-08-30","arxiv_id":"2308.16154","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/mmvp-motion-matrix-based-video-prediction#ran","syntology_url":"https://syntology.ai/paper/2308.16154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16154"}},"official":{"repos":["kay1794/mmvp-motion-matrix-based-video-prediction"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/swinlstm-improving-spatiotemporal-prediction","slug":"swinlstm-improving-spatiotemporal-prediction","title":"SwinLSTM:Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","date":"2023-08-19","arxiv_id":"2308.09891","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/swinlstm-improving-spatiotemporal-prediction#ran","syntology_url":"https://syntology.ai/paper/2308.09891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.09891"}},"official":{"repos":["SongTang-x/SwinLSTM"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-multigrid-memory-for-computational","slug":"neural-multigrid-memory-for-computational","title":"Neural Multigrid Memory For Computational Fluid Dynamics","date":"2023-06-21","arxiv_id":"2306.12545","repositories_listed":1,"syntology":null},{"url":"/paper/skygpt-probabilistic-short-term-solar","slug":"skygpt-probabilistic-short-term-solar","title":"SkyGPT: Probabilistic Short-term Solar Forecasting Using Synthetic Sky Videos from Physics-constrained VideoGPT","date":"2023-06-20","arxiv_id":"2306.11682","repositories_listed":1,"syntology":null},{"url":"/paper/fast-fourier-inception-networks-for-occluded","slug":"fast-fourier-inception-networks-for-occluded","title":"Fast Fourier Inception Networks for Occluded Video Prediction","date":"2023-06-17","arxiv_id":"2306.10346","repositories_listed":1,"syntology":null},{"url":"/paper/ddlp-unsupervised-object-centric-video","slug":"ddlp-unsupervised-object-centric-video","title":"DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles","date":"2023-06-09","arxiv_id":"2306.05957","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ddlp-unsupervised-object-centric-video#ran","syntology_url":"https://syntology.ai/paper/2306.05957","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05957"}},"official":{"repos":["taldatech/ddlp"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/video-diffusion-models-with-local-global","slug":"video-diffusion-models-with-local-global","title":"Video Diffusion Models with Local-Global Context Guidance","date":"2023-06-05","arxiv_id":"2306.02562","repositories_listed":1,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":1,"n_honours":3,"n_violates":3,"n_no_contract":8,"n_pointer_only":3,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 3 honoured, 3 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/video-diffusion-models-with-local-global#ran","syntology_url":"https://syntology.ai/paper/2306.02562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.02562"}},"official":{"repos":["exisas/lgc-vd"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/let-s-think-frame-by-frame-evaluating-video","slug":"let-s-think-frame-by-frame-evaluating-video","title":"Let's Think Frame by Frame with VIP: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought","date":"2023-05-23","arxiv_id":"2305.13903","repositories_listed":1,"syntology":null},{"url":"/paper/vdt-an-empirical-study-on-video-diffusion","slug":"vdt-an-empirical-study-on-video-diffusion","title":"VDT: General-purpose Video Diffusion Transformers via Mask Modeling","date":"2023-05-22","arxiv_id":"2305.13311","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vdt-an-empirical-study-on-video-diffusion#ran","syntology_url":"https://syntology.ai/paper/2305.13311","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13311"}},"official":{"repos":["rerv/vdt"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/pastnet-introducing-physical-inductive-biases","slug":"pastnet-introducing-physical-inductive-biases","title":"PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction","date":"2023-05-19","arxiv_id":"2305.11421","repositories_listed":1,"syntology":null},{"url":"/paper/a-control-centric-benchmark-for-video","slug":"a-control-centric-benchmark-for-video","title":"A Control-Centric Benchmark for Video Prediction","date":"2023-04-26","arxiv_id":"2304.13723","repositories_listed":1,"syntology":null},{"url":"/paper/seer-language-instructed-video-prediction","slug":"seer-language-instructed-video-prediction","title":"Seer: Language Instructed Video Prediction with Latent Diffusion Models","date":"2023-03-27","arxiv_id":"2303.14897","repositories_listed":1,"syntology":null},{"url":"/paper/a-dynamic-multi-scale-voxel-flow-network-for","slug":"a-dynamic-multi-scale-voxel-flow-network-for","title":"A Dynamic Multi-Scale Voxel Flow Network for Video Prediction","date":"2023-03-17","arxiv_id":"2303.09875","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":2,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"3 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; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-dynamic-multi-scale-voxel-flow-network-for#ran","syntology_url":"https://syntology.ai/paper/2303.09875","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.09875"}},"official":{"repos":["megvii-research/CVPR2023-DMVFN"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/implicit-stacked-autoregressive-model-for-1","slug":"implicit-stacked-autoregressive-model-for-1","title":"Implicit Stacked Autoregressive Model for Video Prediction","date":"2023-03-14","arxiv_id":"2303.07849","repositories_listed":1,"syntology":null},{"url":"/paper/object-centric-video-prediction-via","slug":"object-centric-video-prediction-via","title":"Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions","date":"2023-02-23","arxiv_id":"2302.11850","repositories_listed":1,"syntology":null},{"url":"/paper/swinlstm-improving-spatiotemporal-prediction-1","slug":"swinlstm-improving-spatiotemporal-prediction-1","title":"SwinLSTM: Improving Spatiotemporal Prediction Accuracy using Swin Transformer and LSTM","date":"2023-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/predictive-coding-based-multiscale-network","slug":"predictive-coding-based-multiscale-network","title":"Predictive Coding Based Multiscale Network with Encoder-Decoder LSTM for Video Prediction","date":"2022-12-22","arxiv_id":"2212.11642","repositories_listed":1,"syntology":null},{"url":"/paper/video-prediction-by-efficient-transformers","slug":"video-prediction-by-efficient-transformers","title":"Video Prediction by Efficient Transformers","date":"2022-12-12","arxiv_id":"2212.06026","repositories_listed":1,"syntology":{"n":7,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 7 unverified","sample_list":"/paper/video-prediction-by-efficient-transformers#ran","syntology_url":"https://syntology.ai/paper/2212.06026","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.06026"}},"official":{"repos":["xiye20/vptr"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":7,"ran_from_kinds":[]}}},{"url":"/paper/magvit-masked-generative-video-transformer","slug":"magvit-masked-generative-video-transformer","title":"MAGVIT: Masked Generative Video Transformer","date":"2022-12-10","arxiv_id":"2212.05199","repositories_listed":1,"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"]}}},{"url":"/paper/mimo-is-all-you-need-a-strong-multi-in-multi","slug":"mimo-is-all-you-need-a-strong-multi-in-multi","title":"MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Prediction","date":"2022-12-09","arxiv_id":"2212.04655","repositories_listed":1,"syntology":null}],"syntology_records":44,"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":62,"papers_where_code_ran_first_page":"/task/video-prediction/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":4,"url":"/task/video-prediction/papers/2","json":"/task/video-prediction/papers/2.json","rows":100},{"order":"archive","page":3,"of":4,"url":"/task/video-prediction/papers/3","json":"/task/video-prediction/papers/3.json","rows":100},{"order":"archive","page":4,"of":4,"url":"/task/video-prediction/papers/4","json":"/task/video-prediction/papers/4.json","rows":94},{"order":"ran","page":1,"of":1,"url":"/task/video-prediction/papers/ran/1","json":"/task/video-prediction/papers/ran/1.json","rows":62}],"description_links":{"kept":0,"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":"aa89b11ac6bf8661a561c3d4ef7a1dbf6c17254c9a83578115a9e7a9a834e205","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}