{"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/papers/4","list_of":"/task/video-generation","task":"Video Generation","archive":{"snapshot":"2025-07-28"},"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)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":4,"pages_in_order":15,"rows_per_page":100,"rows":[301,400],"of":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":221,"every_run_a_failure_of_syntologys_instrument":36,"listed_with_a_run_with_no_instrument_failure":221,"listed_every_run_a_failure_of_syntologys_instrument":36,"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"},"first_page":"/task/video-generation","prev":"/task/video-generation/papers/3","next":"/task/video-generation/papers/5","papers":[{"url":"/paper/echopulse-ecg-controlled-echocardio-grams","slug":"echopulse-ecg-controlled-echocardio-grams","title":"ECHOPulse: ECG controlled echocardio-grams video generation","date":"2024-10-04","arxiv_id":"2410.03143","repositories_listed":1,"syntology":{"n":14,"n_ran":14,"n_constructed":0,"n_ran_checked":13,"n_instrument":1,"n_unverified":0,"n_honours":3,"n_violates":6,"n_no_contract":4,"n_pointer_only":14,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 6 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/echopulse-ecg-controlled-echocardio-grams#ran","syntology_url":"https://syntology.ai/paper/2410.03143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03143"}},"official":{"repos":["levyisthebest/echopulse_prelease"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/redefining-temporal-modeling-in-video","slug":"redefining-temporal-modeling-in-video","title":"Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach","date":"2024-10-04","arxiv_id":"2410.03160","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/redefining-temporal-modeling-in-video#ran","syntology_url":"https://syntology.ai/paper/2410.03160","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03160"}},"official":{"repos":["yaofang-liu/fvdm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/sageattention-accurate-8-bit-attention-for","slug":"sageattention-accurate-8-bit-attention-for","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","date":"2024-10-03","arxiv_id":"2410.02367","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/sageattention-accurate-8-bit-attention-for#ran","syntology_url":"https://syntology.ai/paper/2410.02367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02367"}},"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/mm-ldm-multi-modal-latent-diffusion-model-for","slug":"mm-ldm-multi-modal-latent-diffusion-model-for","title":"MM-LDM: Multi-Modal Latent Diffusion Model for Sounding Video Generation","date":"2024-10-02","arxiv_id":"2410.01594","repositories_listed":1,"syntology":null},{"url":"/paper/scaling-offline-model-based-rl-via-jointly","slug":"scaling-offline-model-based-rl-via-jointly","title":"Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining","date":"2024-10-01","arxiv_id":"2410.00564","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/scaling-offline-model-based-rl-via-jointly#ran","syntology_url":"https://syntology.ai/paper/2410.00564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.00564"}},"official":{"repos":["cjreinforce/jowa"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/immersepro-end-to-end-stereo-video-synthesis","slug":"immersepro-end-to-end-stereo-video-synthesis","title":"ImmersePro: End-to-End Stereo Video Synthesis Via Implicit Disparity Learning","date":"2024-09-30","arxiv_id":"2410.00262","repositories_listed":1,"syntology":null},{"url":"/paper/replace-anyone-in-videos","slug":"replace-anyone-in-videos","title":"Replace Anyone in Videos","date":"2024-09-30","arxiv_id":"2409.19911","repositories_listed":1,"syntology":null},{"url":"/paper/physgen-rigid-body-physics-grounded-image-to","slug":"physgen-rigid-body-physics-grounded-image-to","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","date":"2024-09-27","arxiv_id":"2409.18964","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/physgen-rigid-body-physics-grounded-image-to#ran","syntology_url":"https://syntology.ai/paper/2409.18964","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.18964"}},"official":{"repos":["stevenlsw/physgen"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-simple-but-strong-baseline-for-sounding","slug":"a-simple-but-strong-baseline-for-sounding","title":"A Simple but Strong Baseline for Sounding Video Generation: Effective Adaptation of Audio and Video Diffusion Models for Joint Generation","date":"2024-09-26","arxiv_id":"2409.17550","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":4,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":3,"n_no_contract":1,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 3 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-simple-but-strong-baseline-for-sounding#ran","syntology_url":"https://syntology.ai/paper/2409.17550","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17550"}},"official":{"repos":["sonyresearch/svg_baseline"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/dormant-defending-against-pose-driven-human","slug":"dormant-defending-against-pose-driven-human","title":"Dormant: Defending against Pose-driven Human Image Animation","date":"2024-09-22","arxiv_id":"2409.14424","repositories_listed":1,"syntology":null},{"url":"/paper/infrared-small-target-detection-in-satellite","slug":"infrared-small-target-detection-in-satellite","title":"Infrared Small Target Detection in Satellite Videos: A New Dataset and A Novel Recurrent Feature Refinement Framework","date":"2024-09-19","arxiv_id":"2409.12448","repositories_listed":1,"syntology":{"n":8,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"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) · 2 unverified","sample_list":"/paper/infrared-small-target-detection-in-satellite#ran","syntology_url":"https://syntology.ai/paper/2409.12448","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.12448"}},"official":{"repos":["xinyiying/rfr"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/emodiffhead-continuously-emotional-control-in","slug":"emodiffhead-continuously-emotional-control-in","title":"EMOdiffhead: Continuously Emotional Control in Talking Head Generation via Diffusion","date":"2024-09-11","arxiv_id":"2409.07255","repositories_listed":1,"syntology":null},{"url":"/paper/hi3d-pursuing-high-resolution-image-to-3d","slug":"hi3d-pursuing-high-resolution-image-to-3d","title":"Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models","date":"2024-09-11","arxiv_id":"2409.07452","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hi3d-pursuing-high-resolution-image-to-3d#ran","syntology_url":"https://syntology.ai/paper/2409.07452","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.07452"}},"official":{"repos":["yanghb22-fdu/hi3d-official"],"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/sara-high-efficient-diffusion-model-fine","slug":"sara-high-efficient-diffusion-model-fine","title":"SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation","date":"2024-09-10","arxiv_id":"2409.06633","repositories_listed":1,"syntology":null},{"url":"/paper/dreamforge-motion-aware-autoregressive-video","slug":"dreamforge-motion-aware-autoregressive-video","title":"DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes","date":"2024-09-06","arxiv_id":"2409.04003","repositories_listed":1,"syntology":null},{"url":"/paper/qihoo-t2x-an-efficiency-focused-diffusion","slug":"qihoo-t2x-an-efficiency-focused-diffusion","title":"Qihoo-T2X: An Efficient Proxy-Tokenized Diffusion Transformer for Text-to-Any-Task","date":"2024-09-06","arxiv_id":"2409.04005","repositories_listed":1,"syntology":null},{"url":"/paper/depthcrafter-generating-consistent-long-depth","slug":"depthcrafter-generating-consistent-long-depth","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","date":"2024-09-03","arxiv_id":"2409.02095","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/depthcrafter-generating-consistent-long-depth#ran","syntology_url":"https://syntology.ai/paper/2409.02095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.02095"}},"official":{"repos":["Tencent/DepthCrafter"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/amg-avatar-motion-guided-video-generation","slug":"amg-avatar-motion-guided-video-generation","title":"AMG: Avatar Motion Guided Video Generation","date":"2024-09-02","arxiv_id":"2409.01502","repositories_listed":1,"syntology":null},{"url":"/paper/od-vae-an-omni-dimensional-video-compressor","slug":"od-vae-an-omni-dimensional-video-compressor","title":"OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model","date":"2024-09-02","arxiv_id":"2409.01199","repositories_listed":1,"syntology":null},{"url":"/paper/fundus2video-cross-modal-angiography-video","slug":"fundus2video-cross-modal-angiography-video","title":"Fundus2Video: Cross-Modal Angiography Video Generation from Static Fundus Photography with Clinical Knowledge Guidance","date":"2024-08-27","arxiv_id":"2408.15217","repositories_listed":1,"syntology":null},{"url":"/paper/genrec-unifying-video-generation-and","slug":"genrec-unifying-video-generation-and","title":"GenRec: Unifying Video Generation and Recognition with Diffusion Models","date":"2024-08-27","arxiv_id":"2408.15241","repositories_listed":1,"syntology":null},{"url":"/paper/customcrafter-customized-video-generation","slug":"customcrafter-customized-video-generation","title":"CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities","date":"2024-08-23","arxiv_id":"2408.13239","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":10,"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) · 3 unverified","sample_list":"/paper/customcrafter-customized-video-generation#ran","syntology_url":"https://syntology.ai/paper/2408.13239","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.13239"}},"official":{"repos":["wutao-cs/customcrafter"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/real-time-video-generation-with-pyramid","slug":"real-time-video-generation-with-pyramid","title":"Real-Time Video Generation with Pyramid Attention Broadcast","date":"2024-08-22","arxiv_id":"2408.12588","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/real-time-video-generation-with-pyramid#ran","syntology_url":"https://syntology.ai/paper/2408.12588","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.12588"}},"official":{"repos":["NUS-HPC-AI-Lab/VideoSys"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/anim-director-a-large-multimodal-model","slug":"anim-director-a-large-multimodal-model","title":"Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation","date":"2024-08-19","arxiv_id":"2408.09787","repositories_listed":1,"syntology":null},{"url":"/paper/fancyvideo-towards-dynamic-and-consistent","slug":"fancyvideo-towards-dynamic-and-consistent","title":"FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance","date":"2024-08-15","arxiv_id":"2408.08189","repositories_listed":1,"syntology":null},{"url":"/paper/panacea-panoramic-and-controllable-video-1","slug":"panacea-panoramic-and-controllable-video-1","title":"Panacea+: Panoramic and Controllable Video Generation for Autonomous Driving","date":"2024-08-14","arxiv_id":"2408.07605","repositories_listed":1,"syntology":null},{"url":"/paper/controlnext-powerful-and-efficient-control","slug":"controlnext-powerful-and-efficient-control","title":"ControlNeXt: Powerful and Efficient Control for Image and Video Generation","date":"2024-08-12","arxiv_id":"2408.06070","repositories_listed":1,"syntology":{"n":9,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":2,"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) · 5 unverified","sample_list":"/paper/controlnext-powerful-and-efficient-control#ran","syntology_url":"https://syntology.ai/paper/2408.06070","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06070"}},"official":{"repos":["dvlab-research/controlnext"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/tora-trajectory-oriented-diffusion","slug":"tora-trajectory-oriented-diffusion","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","date":"2024-07-31","arxiv_id":"2407.21705","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":4,"n_ran_checked":7,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":6,"n_pointer_only":0,"phrase":"9 ran (of which 4 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/tora-trajectory-oriented-diffusion#ran","syntology_url":"https://syntology.ai/paper/2407.21705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.21705"}},"official":{"repos":["alibaba/Tora"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":4,"n_ran_no_instrument_failure":7,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/find-fine-tuning-initial-noise-distribution","slug":"find-fine-tuning-initial-noise-distribution","title":"FIND: Fine-tuning Initial Noise Distribution with Policy Optimization for Diffusion Models","date":"2024-07-28","arxiv_id":"2407.19453","repositories_listed":1,"syntology":null},{"url":"/paper/humanvid-demystifying-training-data-for","slug":"humanvid-demystifying-training-data-for","title":"HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation","date":"2024-07-24","arxiv_id":"2407.17438","repositories_listed":1,"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/humanvid-demystifying-training-data-for#ran","syntology_url":"https://syntology.ai/paper/2407.17438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.17438"}},"official":{"repos":["zhenzhiwang/humanvid"],"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/t2v-compbench-a-comprehensive-benchmark-for","slug":"t2v-compbench-a-comprehensive-benchmark-for","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","date":"2024-07-19","arxiv_id":"2407.14505","repositories_listed":1,"syntology":{"n":11,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":2,"n_honours":2,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/t2v-compbench-a-comprehensive-benchmark-for#ran","syntology_url":"https://syntology.ai/paper/2407.14505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14505"}},"official":{"repos":["KaiyueSun98/T2V-CompBench"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-understanding-unsafe-video-generation","slug":"towards-understanding-unsafe-video-generation","title":"Towards Understanding Unsafe Video Generation","date":"2024-07-17","arxiv_id":"2407.12581","repositories_listed":1,"syntology":null},{"url":"/paper/idol-unified-dual-modal-latent-diffusion-for","slug":"idol-unified-dual-modal-latent-diffusion-for","title":"IDOL: Unified Dual-Modal Latent Diffusion for Human-Centric Joint Video-Depth Generation","date":"2024-07-15","arxiv_id":"2407.10937","repositories_listed":1,"syntology":null},{"url":"/paper/a-comprehensive-survey-on-human-video","slug":"a-comprehensive-survey-on-human-video","title":"A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights","date":"2024-07-11","arxiv_id":"2407.08428","repositories_listed":1,"syntology":null},{"url":"/paper/mobius-an-high-efficient-spatial-temporal","slug":"mobius-an-high-efficient-spatial-temporal","title":"Mobius: A High Efficient Spatial-Temporal Parallel Training Paradigm for Text-to-Video Generation Task","date":"2024-07-09","arxiv_id":"2407.06617","repositories_listed":1,"syntology":null},{"url":"/paper/liveportrait-efficient-portrait-animation","slug":"liveportrait-efficient-portrait-animation","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","date":"2024-07-03","arxiv_id":"2407.03168","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/liveportrait-efficient-portrait-animation#ran","syntology_url":"https://syntology.ai/paper/2407.03168","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.03168"}},"official":{"repos":["KwaiVGI/LivePortrait"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/evaluation-of-text-to-video-generation-models","slug":"evaluation-of-text-to-video-generation-models","title":"Evaluation of Text-to-Video Generation Models: A Dynamics Perspective","date":"2024-07-01","arxiv_id":"2407.01094","repositories_listed":1,"syntology":{"n":21,"n_ran":13,"n_constructed":0,"n_ran_checked":13,"n_instrument":0,"n_unverified":8,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":21,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/evaluation-of-text-to-video-generation-models#ran","syntology_url":"https://syntology.ai/paper/2407.01094","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01094"}},"official":{"repos":["mingxiangl/devil"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":13,"n_unverified":8,"ran_from_kinds":["official"]}}},{"url":"/paper/mimicmotion-high-quality-human-motion-video","slug":"mimicmotion-high-quality-human-motion-video","title":"MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","date":"2024-06-28","arxiv_id":"2406.19680","repositories_listed":1,"syntology":null},{"url":"/paper/q-dit-accurate-post-training-quantization-for","slug":"q-dit-accurate-post-training-quantization-for","title":"Q-DiT: Accurate Post-Training Quantization for Diffusion Transformers","date":"2024-06-25","arxiv_id":"2406.17343","repositories_listed":1,"syntology":{"n":19,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":2,"n_honours":4,"n_violates":0,"n_no_contract":7,"n_pointer_only":19,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 4 honoured, 0 violated, 7 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/q-dit-accurate-post-training-quantization-for#ran","syntology_url":"https://syntology.ai/paper/2406.17343","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.17343"}},"official":{"repos":["juanerx/q-dit"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/freetraj-tuning-free-trajectory-control-in","slug":"freetraj-tuning-free-trajectory-control-in","title":"FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models","date":"2024-06-24","arxiv_id":"2406.16863","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":10,"n_instrument":2,"n_unverified":3,"n_honours":2,"n_violates":1,"n_no_contract":7,"n_pointer_only":4,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/freetraj-tuning-free-trajectory-control-in#ran","syntology_url":"https://syntology.ai/paper/2406.16863","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.16863"}},"official":{"repos":["arthur-qiu/freetraj"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/mvoc-a-training-free-multiple-video-object","slug":"mvoc-a-training-free-multiple-video-object","title":"MVOC: a training-free multiple video object composition method with diffusion models","date":"2024-06-22","arxiv_id":"2406.15829","repositories_listed":1,"syntology":null},{"url":"/paper/exvideo-extending-video-diffusion-models-via","slug":"exvideo-extending-video-diffusion-models-via","title":"ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning","date":"2024-06-20","arxiv_id":"2406.14130","repositories_listed":1,"syntology":null},{"url":"/paper/fantastic-copyrighted-beasts-and-how-not-to","slug":"fantastic-copyrighted-beasts-and-how-not-to","title":"Fantastic Copyrighted Beasts and How (Not) to Generate Them","date":"2024-06-20","arxiv_id":"2406.14526","repositories_listed":1,"syntology":null},{"url":"/paper/safesora-towards-safety-alignment-of","slug":"safesora-towards-safety-alignment-of","title":"SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset","date":"2024-06-20","arxiv_id":"2406.14477","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"0 ran · 2 unverified","sample_list":"/paper/safesora-towards-safety-alignment-of#ran","syntology_url":"https://syntology.ai/paper/2406.14477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14477"}},"official":{"repos":["pku-alignment/safe-sora"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/vid3d-synthesis-of-dynamic-3d-scenes-using-2d","slug":"vid3d-synthesis-of-dynamic-3d-scenes-using-2d","title":"Vid3D: Synthesis of Dynamic 3D Scenes using 2D Video Diffusion","date":"2024-06-17","arxiv_id":"2406.11196","repositories_listed":1,"syntology":null},{"url":"/paper/vid-gpt-introducing-gpt-style-autoregressive","slug":"vid-gpt-introducing-gpt-style-autoregressive","title":"ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Models","date":"2024-06-16","arxiv_id":"2406.10981","repositories_listed":1,"syntology":null},{"url":"/paper/needle-in-a-video-haystack-a-scalable","slug":"needle-in-a-video-haystack-a-scalable","title":"Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs","date":"2024-06-13","arxiv_id":"2406.09367","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/needle-in-a-video-haystack-a-scalable#ran","syntology_url":"https://syntology.ai/paper/2406.09367","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09367"}},"official":{"repos":["joez17/videoniah"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["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/tc-bench-benchmarking-temporal","slug":"tc-bench-benchmarking-temporal","title":"TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation","date":"2024-06-12","arxiv_id":"2406.08656","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/tc-bench-benchmarking-temporal#ran","syntology_url":"https://syntology.ai/paper/2406.08656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.08656"}},"official":{"repos":["weixi-feng/tc-bench"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/compositional-video-generation-as-flow","slug":"compositional-video-generation-as-flow","title":"Compositional Video Generation as Flow Equalization","date":"2024-06-10","arxiv_id":"2407.06182","repositories_listed":1,"syntology":null},{"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/genai-arena-an-open-evaluation-platform-for","slug":"genai-arena-an-open-evaluation-platform-for","title":"GenAI Arena: An Open Evaluation Platform for Generative Models","date":"2024-06-06","arxiv_id":"2406.04485","repositories_listed":1,"syntology":null},{"url":"/paper/sf-v-single-forward-video-generation-model","slug":"sf-v-single-forward-video-generation-model","title":"SF-V: Single Forward Video Generation Model","date":"2024-06-06","arxiv_id":"2406.04324","repositories_listed":1,"syntology":null},{"url":"/paper/sharegpt4video-improving-video-understanding","slug":"sharegpt4video-improving-video-understanding","title":"ShareGPT4Video: Improving Video Understanding and Generation with Better Captions","date":"2024-06-06","arxiv_id":"2406.04325","repositories_listed":1,"syntology":null},{"url":"/paper/videotetris-towards-compositional-text-to","slug":"videotetris-towards-compositional-text-to","title":"VideoTetris: Towards Compositional Text-to-Video Generation","date":"2024-06-06","arxiv_id":"2406.04277","repositories_listed":1,"syntology":{"n":9,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/videotetris-towards-compositional-text-to#ran","syntology_url":"https://syntology.ai/paper/2406.04277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.04277"}},"official":{"repos":["yangling0818/videotetris"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vidit-q-efficient-and-accurate-quantization","slug":"vidit-q-efficient-and-accurate-quantization","title":"ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation","date":"2024-06-04","arxiv_id":"2406.02540","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":10,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/vidit-q-efficient-and-accurate-quantization#ran","syntology_url":"https://syntology.ai/paper/2406.02540","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02540"}},"official":{"repos":["a-suozhang/vidit-q"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/zerosmooth-training-free-diffuser-adaptation","slug":"zerosmooth-training-free-diffuser-adaptation","title":"ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation","date":"2024-06-03","arxiv_id":"2406.00908","repositories_listed":1,"syntology":null},{"url":"/paper/demamba-ai-generated-video-detection-on","slug":"demamba-ai-generated-video-detection-on","title":"DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark","date":"2024-05-30","arxiv_id":"2405.19707","repositories_listed":1,"syntology":{"n":19,"n_ran":13,"n_constructed":0,"n_ran_checked":9,"n_instrument":4,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":8,"n_pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/demamba-ai-generated-video-detection-on#ran","syntology_url":"https://syntology.ai/paper/2405.19707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.19707"}},"official":{"repos":["chenhaoxing/DeMamba"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/improving-the-training-of-rectified-flows","slug":"improving-the-training-of-rectified-flows","title":"Improving the Training of Rectified Flows","date":"2024-05-30","arxiv_id":"2405.20320","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/improving-the-training-of-rectified-flows#ran","syntology_url":"https://syntology.ai/paper/2405.20320","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20320"}},"official":{"repos":["sangyun884/rfpp"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mofa-video-controllable-image-animation-via","slug":"mofa-video-controllable-image-animation-via","title":"MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model","date":"2024-05-30","arxiv_id":"2405.20222","repositories_listed":1,"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":6,"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/mofa-video-controllable-image-animation-via#ran","syntology_url":"https://syntology.ai/paper/2405.20222","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.20222"}},"official":{"repos":["myniuuu/mofa-video"],"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/motionfollower-editing-video-motion-via","slug":"motionfollower-editing-video-motion-via","title":"MotionFollower: Editing Video Motion via Lightweight Score-Guided Diffusion","date":"2024-05-30","arxiv_id":"2405.20325","repositories_listed":1,"syntology":null},{"url":"/paper/promptus-can-prompts-streaming-replace-video","slug":"promptus-can-prompts-streaming-replace-video","title":"Promptus: Can Prompts Streaming Replace Video Streaming with Stable Diffusion","date":"2024-05-30","arxiv_id":"2405.20032","repositories_listed":1,"syntology":null},{"url":"/paper/easyanimate-a-high-performance-long-video","slug":"easyanimate-a-high-performance-long-video","title":"EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture","date":"2024-05-29","arxiv_id":"2405.18991","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":2,"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/easyanimate-a-high-performance-long-video#ran","syntology_url":"https://syntology.ai/paper/2405.18991","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18991"}},"official":{"repos":["aigc-apps/easyanimate"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/t2v-turbo-breaking-the-quality-bottleneck-of","slug":"t2v-turbo-breaking-the-quality-bottleneck-of","title":"T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback","date":"2024-05-29","arxiv_id":"2405.18750","repositories_listed":1,"syntology":null},{"url":"/paper/discriminator-guided-cooperative-diffusion","slug":"discriminator-guided-cooperative-diffusion","title":"MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation","date":"2024-05-28","arxiv_id":"2405.17842","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/discriminator-guided-cooperative-diffusion#ran","syntology_url":"https://syntology.ai/paper/2405.17842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17842"}},"official":{"repos":["sonyresearch/mmdisco"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/eg4d-explicit-generation-of-4d-object-without","slug":"eg4d-explicit-generation-of-4d-object-without","title":"EG4D: Explicit Generation of 4D Object without Score Distillation","date":"2024-05-28","arxiv_id":"2405.18132","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/eg4d-explicit-generation-of-4d-object-without#ran","syntology_url":"https://syntology.ai/paper/2405.18132","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18132"}},"official":{"repos":["jasongzy/eg4d"],"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/mavin-multi-action-video-generation-with","slug":"mavin-multi-action-video-generation-with","title":"MAVIN: Multi-Action Video Generation with Diffusion Models via Transition Video Infilling","date":"2024-05-28","arxiv_id":"2405.18003","repositories_listed":1,"syntology":null},{"url":"/paper/phased-consistency-model","slug":"phased-consistency-model","title":"Phased Consistency Models","date":"2024-05-28","arxiv_id":"2405.18407","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/phased-consistency-model#ran","syntology_url":"https://syntology.ai/paper/2405.18407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.18407"}},"official":{"repos":["G-U-N/Phased-Consistency-Model"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/classdiffusion-more-aligned-personalization","slug":"classdiffusion-more-aligned-personalization","title":"ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance","date":"2024-05-27","arxiv_id":"2405.17532","repositories_listed":1,"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/classdiffusion-more-aligned-personalization#ran","syntology_url":"https://syntology.ai/paper/2405.17532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17532"}},"official":{"repos":["Rbrq03/ClassDiffusion"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/a-misleading-gallery-of-fluid-motion-by","slug":"a-misleading-gallery-of-fluid-motion-by","title":"A Misleading Gallery of Fluid Motion by Generative Artificial Intelligence","date":"2024-05-24","arxiv_id":"2405.15406","repositories_listed":1,"syntology":null},{"url":"/paper/video-diffusion-models-are-training-free","slug":"video-diffusion-models-are-training-free","title":"Video Diffusion Models are Training-free Motion Interpreter and Controller","date":"2024-05-23","arxiv_id":"2405.14864","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":1,"phrase":"0 ran · 1 unverified","sample_list":"/paper/video-diffusion-models-are-training-free#ran","syntology_url":"https://syntology.ai/paper/2405.14864","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.14864"}},"official":null}},{"url":"/paper/motioncraft-physics-based-zero-shot-video","slug":"motioncraft-physics-based-zero-shot-video","title":"MotionCraft: Physics-based Zero-Shot Video Generation","date":"2024-05-22","arxiv_id":"2405.13557","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 3 unverified","sample_list":"/paper/motioncraft-physics-based-zero-shot-video#ran","syntology_url":"https://syntology.ai/paper/2405.13557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13557"}},"official":{"repos":["mezzelfo/MotionCraft"],"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/opencarboneval-a-unified-carbon-emission","slug":"opencarboneval-a-unified-carbon-emission","title":"OpenCarbonEval: A Unified Carbon Emission Estimation Framework in Large-Scale AI Models","date":"2024-05-21","arxiv_id":"2405.12843","repositories_listed":1,"syntology":null},{"url":"/paper/fifo-diffusion-generating-infinite-videos","slug":"fifo-diffusion-generating-infinite-videos","title":"FIFO-Diffusion: Generating Infinite Videos from Text without Training","date":"2024-05-19","arxiv_id":"2405.11473","repositories_listed":1,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":3,"n_honours":1,"n_violates":1,"n_no_contract":6,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/fifo-diffusion-generating-infinite-videos#ran","syntology_url":"https://syntology.ai/paper/2405.11473","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.11473"}},"official":{"repos":["jjihwan/FIFO-Diffusion_public"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/from-sora-what-we-can-see-a-survey-of-text-to","slug":"from-sora-what-we-can-see-a-survey-of-text-to","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","date":"2024-05-17","arxiv_id":"2405.10674","repositories_listed":1,"syntology":null},{"url":"/paper/oneto3d-one-image-to-re-editable-dynamic-3d","slug":"oneto3d-one-image-to-re-editable-dynamic-3d","title":"OneTo3D: One Image to Re-editable Dynamic 3D Model and Video Generation","date":"2024-05-10","arxiv_id":"2405.06547","repositories_listed":1,"syntology":null},{"url":"/paper/talc-time-aligned-captions-for-multi-scene","slug":"talc-time-aligned-captions-for-multi-scene","title":"TALC: Time-Aligned Captions for Multi-Scene Text-to-Video Generation","date":"2024-05-07","arxiv_id":"2405.04682","repositories_listed":1,"syntology":null},{"url":"/paper/is-sora-a-world-simulator-a-comprehensive","slug":"is-sora-a-world-simulator-a-comprehensive","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","date":"2024-05-06","arxiv_id":"2405.03520","repositories_listed":1,"syntology":null},{"url":"/paper/video-diffusion-models-a-survey","slug":"video-diffusion-models-a-survey","title":"Video Diffusion Models: A Survey","date":"2024-05-06","arxiv_id":"2405.03150","repositories_listed":1,"syntology":null},{"url":"/paper/storydiffusion-consistent-self-attention-for","slug":"storydiffusion-consistent-self-attention-for","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","date":"2024-05-02","arxiv_id":"2405.01434","repositories_listed":1,"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/storydiffusion-consistent-self-attention-for#ran","syntology_url":"https://syntology.ai/paper/2405.01434","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.01434"}},"official":{"repos":["hvision-nku/storydiffusion"],"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/flexifilm-long-video-generation-with-flexible","slug":"flexifilm-long-video-generation-with-flexible","title":"FlexiFilm: Long Video Generation with Flexible Conditions","date":"2024-04-29","arxiv_id":"2404.18620","repositories_listed":1,"syntology":null},{"url":"/paper/synthesizing-audio-from-silent-video-using","slug":"synthesizing-audio-from-silent-video-using","title":"Synthesizing Audio from Silent Video using Sequence to Sequence Modeling","date":"2024-04-25","arxiv_id":"2404.17608","repositories_listed":1,"syntology":null},{"url":"/paper/ti2v-zero-zero-shot-image-conditioning-for","slug":"ti2v-zero-zero-shot-image-conditioning-for","title":"TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models","date":"2024-04-25","arxiv_id":"2404.16306","repositories_listed":1,"syntology":null},{"url":"/paper/id-animator-zero-shot-identity-preserving","slug":"id-animator-zero-shot-identity-preserving","title":"ID-Animator: Zero-Shot Identity-Preserving Human Video Generation","date":"2024-04-23","arxiv_id":"2404.15275","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/id-animator-zero-shot-identity-preserving#ran","syntology_url":"https://syntology.ai/paper/2404.15275","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.15275"}},"official":{"repos":["id-animator/id-animator"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/tavgbench-benchmarking-text-to-audible-video","slug":"tavgbench-benchmarking-text-to-audible-video","title":"TAVGBench: Benchmarking Text to Audible-Video Generation","date":"2024-04-22","arxiv_id":"2404.14381","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":0,"n_honours":1,"n_violates":2,"n_no_contract":5,"n_pointer_only":11,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 2 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/tavgbench-benchmarking-text-to-audible-video#ran","syntology_url":"https://syntology.ai/paper/2404.14381","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.14381"}},"official":{"repos":["opennlplab/tavgbench"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-content-bias-in-frechet-video-distance","slug":"on-the-content-bias-in-frechet-video-distance","title":"On the Content Bias in Fréchet Video Distance","date":"2024-04-18","arxiv_id":"2404.12391","repositories_listed":1,"syntology":{"n":21,"n_ran":16,"n_constructed":0,"n_ran_checked":9,"n_instrument":7,"n_unverified":5,"n_honours":0,"n_violates":2,"n_no_contract":7,"n_pointer_only":7,"phrase":"16 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; 7 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/on-the-content-bias-in-frechet-video-distance#ran","syntology_url":"https://syntology.ai/paper/2404.12391","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12391"}},"official":null}},{"url":"/paper/cameractrl-enabling-camera-control-for-text","slug":"cameractrl-enabling-camera-control-for-text","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","date":"2024-04-02","arxiv_id":"2404.02101","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cameractrl-enabling-camera-control-for-text#ran","syntology_url":"https://syntology.ai/paper/2404.02101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.02101"}},"official":{"repos":["hehao13/cameractrl"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/co-speech-gesture-video-generation-via-motion","slug":"co-speech-gesture-video-generation-via-motion","title":"Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model","date":"2024-04-02","arxiv_id":"2404.01862","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":2,"n_ran_checked":4,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/co-speech-gesture-video-generation-via-motion#ran","syntology_url":"https://syntology.ai/paper/2404.01862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.01862"}},"official":{"repos":["thuhcsi/s2g-mddiffusion"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":2,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/motion-inversion-for-video-customization","slug":"motion-inversion-for-video-customization","title":"Motion Inversion for Video Customization","date":"2024-03-29","arxiv_id":"2403.20193","repositories_listed":1,"syntology":null},{"url":"/paper/annotated-biomedical-video-generation-using","slug":"annotated-biomedical-video-generation-using","title":"Annotated Biomedical Video Generation using Denoising Diffusion Probabilistic Models and Flow Fields","date":"2024-03-26","arxiv_id":"2403.17808","repositories_listed":1,"syntology":null},{"url":"/paper/adaptive-super-resolution-for-one-shot","slug":"adaptive-super-resolution-for-one-shot","title":"Adaptive Super Resolution For One-Shot Talking-Head Generation","date":"2024-03-23","arxiv_id":"2403.15944","repositories_listed":1,"syntology":null},{"url":"/paper/anyv2v-a-plug-and-play-framework-for-any","slug":"anyv2v-a-plug-and-play-framework-for-any","title":"AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks","date":"2024-03-21","arxiv_id":"2403.14468","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"n_honours":1,"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; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/anyv2v-a-plug-and-play-framework-for-any#ran","syntology_url":"https://syntology.ai/paper/2403.14468","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14468"}},"official":{"repos":["tiger-ai-lab/anyv2v"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/champ-controllable-and-consistent-human-image","slug":"champ-controllable-and-consistent-human-image","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","date":"2024-03-21","arxiv_id":"2403.14781","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":3,"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) · 3 unverified","sample_list":"/paper/champ-controllable-and-consistent-human-image#ran","syntology_url":"https://syntology.ai/paper/2403.14781","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14781"}},"official":{"repos":["fudan-generative-vision/champ"],"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":["official"]}}},{"url":"/paper/streamingt2v-consistent-dynamic-and","slug":"streamingt2v-consistent-dynamic-and","title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","date":"2024-03-21","arxiv_id":"2403.14773","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/streamingt2v-consistent-dynamic-and#ran","syntology_url":"https://syntology.ai/paper/2403.14773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14773"}},"official":{"repos":["picsart-ai-research/streamingt2v"],"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/stylecinegan-landscape-cinemagraph-generation","slug":"stylecinegan-landscape-cinemagraph-generation","title":"StyleCineGAN: Landscape Cinemagraph Generation using a Pre-trained StyleGAN","date":"2024-03-21","arxiv_id":"2403.14186","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 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; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/stylecinegan-landscape-cinemagraph-generation#ran","syntology_url":"https://syntology.ai/paper/2403.14186","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14186"}},"official":{"repos":["jeolpyeoni/StyleCineGAN"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/mora-enabling-generalist-video-generation-via","slug":"mora-enabling-generalist-video-generation-via","title":"Mora: Enabling Generalist Video Generation via A Multi-Agent Framework","date":"2024-03-20","arxiv_id":"2403.13248","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 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; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/mora-enabling-generalist-video-generation-via#ran","syntology_url":"https://syntology.ai/paper/2403.13248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13248"}},"official":{"repos":["lichao-sun/mora"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/vstar-generative-temporal-nursing-for-longer","slug":"vstar-generative-temporal-nursing-for-longer","title":"VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis","date":"2024-03-20","arxiv_id":"2403.13501","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":9,"n_instrument":3,"n_unverified":2,"n_honours":2,"n_violates":3,"n_no_contract":4,"n_pointer_only":14,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 3 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/vstar-generative-temporal-nursing-for-longer#ran","syntology_url":"https://syntology.ai/paper/2403.13501","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13501"}},"official":{"repos":["boschresearch/VSTAR"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/cococo-improving-text-guided-video-inpainting","slug":"cococo-improving-text-guided-video-inpainting","title":"CoCoCo: Improving Text-Guided Video Inpainting for Better Consistency, Controllability and Compatibility","date":"2024-03-18","arxiv_id":"2403.12035","repositories_listed":1,"syntology":null},{"url":"/paper/echoreel-enhancing-action-generation-of","slug":"echoreel-enhancing-action-generation-of","title":"AICL: Action In-Context Learning for Video Diffusion Model","date":"2024-03-18","arxiv_id":"2403.11535","repositories_listed":1,"syntology":null},{"url":"/paper/follow-your-click-open-domain-regional-image","slug":"follow-your-click-open-domain-regional-image","title":"Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts","date":"2024-03-13","arxiv_id":"2403.08268","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":9,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/follow-your-click-open-domain-regional-image#ran","syntology_url":"https://syntology.ai/paper/2403.08268","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.08268"}},"official":{"repos":["mayuelala/followyourclick"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}}],"record_sha256":"c2ae6ff3b5d19f0d529842c846bfb940dfbffd6a355e5c1b377ff195e643d7f8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}