{"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/5","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":5,"pages_in_order":15,"rows_per_page":100,"rows":[401,500],"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/4","next":"/task/video-generation/papers/6","papers":[{"url":"/paper/ssm-meets-video-diffusion-models-efficient","slug":"ssm-meets-video-diffusion-models-efficient","title":"SSM Meets Video Diffusion Models: Efficient Long-Term Video Generation with Structured State Spaces","date":"2024-03-12","arxiv_id":"2403.07711","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":4,"n_no_contract":2,"n_pointer_only":2,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 4 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/ssm-meets-video-diffusion-models-efficient#ran","syntology_url":"https://syntology.ai/paper/2403.07711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.07711"}},"official":{"repos":["shim0114/ssm-meets-video-diffusion-models"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/drivedreamer-2-llm-enhanced-world-models-for","slug":"drivedreamer-2-llm-enhanced-world-models-for","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","date":"2024-03-11","arxiv_id":"2403.06845","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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/drivedreamer-2-llm-enhanced-world-models-for#ran","syntology_url":"https://syntology.ai/paper/2403.06845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06845"}},"official":null}},{"url":"/paper/vidprom-a-million-scale-real-prompt-gallery","slug":"vidprom-a-million-scale-real-prompt-gallery","title":"VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models","date":"2024-03-10","arxiv_id":"2403.06098","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":3,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":9,"phrase":"8 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/vidprom-a-million-scale-real-prompt-gallery#ran","syntology_url":"https://syntology.ai/paper/2403.06098","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.06098"}},"official":{"repos":["wangwenhao0716/vidprom"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]}}},{"url":"/paper/videoelevator-elevating-video-generation","slug":"videoelevator-elevating-video-generation","title":"VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models","date":"2024-03-08","arxiv_id":"2403.05438","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/videoelevator-elevating-video-generation#ran","syntology_url":"https://syntology.ai/paper/2403.05438","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05438"}},"official":{"repos":["ybybzhang/videoelevator"],"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/pix2gif-motion-guided-diffusion-for-gif","slug":"pix2gif-motion-guided-diffusion-for-gif","title":"Pix2Gif: Motion-Guided Diffusion for GIF Generation","date":"2024-03-07","arxiv_id":"2403.04634","repositories_listed":1,"syntology":null},{"url":"/paper/unictrl-improving-the-spatiotemporal","slug":"unictrl-improving-the-spatiotemporal","title":"UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control","date":"2024-03-04","arxiv_id":"2403.02332","repositories_listed":1,"syntology":null},{"url":"/paper/panda-70m-captioning-70m-videos-with-multiple","slug":"panda-70m-captioning-70m-videos-with-multiple","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","date":"2024-02-29","arxiv_id":"2402.19479","repositories_listed":1,"syntology":null},{"url":"/paper/sora-a-review-on-background-technology","slug":"sora-a-review-on-background-technology","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","date":"2024-02-27","arxiv_id":"2402.17177","repositories_listed":1,"syntology":null},{"url":"/paper/cross-modal-contextualized-diffusion-models","slug":"cross-modal-contextualized-diffusion-models","title":"Contextualized Diffusion Models for Text-Guided Image and Video Generation","date":"2024-02-26","arxiv_id":"2402.16627","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/cross-modal-contextualized-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2402.16627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.16627"}},"official":{"repos":["yangling0818/contextdiff"],"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/vgmshield-mitigating-misuse-of-video","slug":"vgmshield-mitigating-misuse-of-video","title":"VGMShield: Mitigating Misuse of Video Generative Models","date":"2024-02-20","arxiv_id":"2402.13126","repositories_listed":1,"syntology":null},{"url":"/paper/make-a-cheap-scaling-a-self-cascade-diffusion","slug":"make-a-cheap-scaling-a-self-cascade-diffusion","title":"Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation","date":"2024-02-16","arxiv_id":"2402.10491","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":4,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/make-a-cheap-scaling-a-self-cascade-diffusion#ran","syntology_url":"https://syntology.ai/paper/2402.10491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.10491"}},"official":{"repos":["guolanqing/self-cascade"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/magic-me-identity-specific-video-customized","slug":"magic-me-identity-specific-video-customized","title":"Magic-Me: Identity-Specific Video Customized Diffusion","date":"2024-02-14","arxiv_id":"2402.09368","repositories_listed":1,"syntology":{"n":11,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":2,"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) · 5 unverified","sample_list":"/paper/magic-me-identity-specific-video-customized#ran","syntology_url":"https://syntology.ai/paper/2402.09368","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.09368"}},"official":{"repos":["zhen-dong/magic-me"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/consisti2v-enhancing-visual-consistency-for","slug":"consisti2v-enhancing-visual-consistency-for","title":"ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation","date":"2024-02-06","arxiv_id":"2402.04324","repositories_listed":1,"syntology":{"n":12,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":2,"n_no_contract":5,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 2 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/consisti2v-enhancing-visual-consistency-for#ran","syntology_url":"https://syntology.ai/paper/2402.04324","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.04324"}},"official":{"repos":["TIGER-AI-Lab/ConsistI2V"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/interactivevideo-user-centric-controllable","slug":"interactivevideo-user-centric-controllable","title":"InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions","date":"2024-02-05","arxiv_id":"2402.03040","repositories_listed":1,"syntology":null},{"url":"/paper/projected-generative-diffusion-models-for","slug":"projected-generative-diffusion-models-for","title":"Constrained Synthesis with Projected Diffusion Models","date":"2024-02-05","arxiv_id":"2402.03559","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":1,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 0 unverified; the one sample that ran constructed an object rather than computing a result","sample_list":"/paper/projected-generative-diffusion-models-for#ran","syntology_url":"https://syntology.ai/paper/2402.03559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03559"}},"official":{"repos":["RAISELab-atUVA/Projected-Diffusion"],"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":["official"]}}},{"url":"/paper/video-lavit-unified-video-language-pre","slug":"video-lavit-unified-video-language-pre","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","date":"2024-02-05","arxiv_id":"2402.03161","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/video-lavit-unified-video-language-pre#ran","syntology_url":"https://syntology.ai/paper/2402.03161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.03161"}},"official":null}},{"url":"/paper/decof-generated-video-detection-via-frame","slug":"decof-generated-video-detection-via-frame","title":"Detecting AI-Generated Video via Frame Consistency","date":"2024-02-03","arxiv_id":"2402.02085","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":1,"n_pointer_only":8,"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) · 3 unverified","sample_list":"/paper/decof-generated-video-detection-via-frame#ran","syntology_url":"https://syntology.ai/paper/2402.02085","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.02085"}},"official":{"repos":["wuwuwuyue/decof"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/animatelcm-accelerating-the-animation-of","slug":"animatelcm-accelerating-the-animation-of","title":"AnimateLCM: Computation-Efficient Personalized Style Video Generation without Personalized Video Data","date":"2024-02-01","arxiv_id":"2402.00769","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":3,"phrase":"10 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; 5 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/animatelcm-accelerating-the-animation-of#ran","syntology_url":"https://syntology.ai/paper/2402.00769","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.00769"}},"official":{"repos":["g-u-n/animatelcm"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ddmi-domain-agnostic-latent-diffusion-models","slug":"ddmi-domain-agnostic-latent-diffusion-models","title":"DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations","date":"2024-01-23","arxiv_id":"2401.12517","repositories_listed":1,"syntology":{"n":21,"n_ran":18,"n_constructed":0,"n_ran_checked":12,"n_instrument":6,"n_unverified":3,"n_honours":0,"n_violates":2,"n_no_contract":10,"n_pointer_only":6,"phrase":"18 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 2 violated, 10 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/ddmi-domain-agnostic-latent-diffusion-models#ran","syntology_url":"https://syntology.ai/paper/2401.12517","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12517"}},"official":{"repos":["mlvlab/DDMI"],"state":"official (archive's flag): 18 ran","n_ran":18,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/lumiere-a-space-time-diffusion-model-for","slug":"lumiere-a-space-time-diffusion-model-for","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","date":"2024-01-23","arxiv_id":"2401.12945","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":2,"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: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/lumiere-a-space-time-diffusion-model-for#ran","syntology_url":"https://syntology.ai/paper/2401.12945","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.12945"}},"official":null}},{"url":"/paper/sat2scene-3d-urban-scene-generation-from","slug":"sat2scene-3d-urban-scene-generation-from","title":"Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion","date":"2024-01-19","arxiv_id":"2401.10786","repositories_listed":1,"syntology":null},{"url":"/paper/e2hqv-high-quality-video-generation-from","slug":"e2hqv-high-quality-video-generation-from","title":"E2HQV: High-Quality Video Generation from Event Camera via Theory-Inspired Model-Aided Deep Learning","date":"2024-01-16","arxiv_id":"2401.08117","repositories_listed":1,"syntology":null},{"url":"/paper/videodrafter-content-consistent-multi-scene","slug":"videodrafter-content-consistent-multi-scene","title":"VideoStudio: Generating Consistent-Content and Multi-Scene Videos","date":"2024-01-02","arxiv_id":"2401.01256","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/videodrafter-content-consistent-multi-scene#ran","syntology_url":"https://syntology.ai/paper/2401.01256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.01256"}},"official":{"repos":["fuchenustc/videostudio"],"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/trailblazer-trajectory-control-for-diffusion","slug":"trailblazer-trajectory-control-for-diffusion","title":"TrailBlazer: Trajectory Control for Diffusion-Based Video Generation","date":"2023-12-31","arxiv_id":"2401.00896","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/trailblazer-trajectory-control-for-diffusion#ran","syntology_url":"https://syntology.ai/paper/2401.00896","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00896"}},"official":null}},{"url":"/paper/dreamgaussian4d-generative-4d-gaussian","slug":"dreamgaussian4d-generative-4d-gaussian","title":"DreamGaussian4D: Generative 4D Gaussian Splatting","date":"2023-12-28","arxiv_id":"2312.17142","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dreamgaussian4d-generative-4d-gaussian#ran","syntology_url":"https://syntology.ai/paper/2312.17142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.17142"}},"official":{"repos":["jiawei-ren/dreamgaussian4d"],"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/a-recipe-for-scaling-up-text-to-video","slug":"a-recipe-for-scaling-up-text-to-video","title":"A Recipe for Scaling up Text-to-Video Generation with Text-free Videos","date":"2023-12-25","arxiv_id":"2312.15770","repositories_listed":1,"syntology":null},{"url":"/paper/free-editor-zero-shot-text-driven-3d-scene","slug":"free-editor-zero-shot-text-driven-3d-scene","title":"Free-Editor: Zero-shot Text-driven 3D Scene Editing","date":"2023-12-21","arxiv_id":"2312.13663","repositories_listed":1,"syntology":null},{"url":"/paper/instructvideo-instructing-video-diffusion","slug":"instructvideo-instructing-video-diffusion","title":"InstructVideo: Instructing Video Diffusion Models with Human Feedback","date":"2023-12-19","arxiv_id":"2312.12490","repositories_listed":1,"syntology":null},{"url":"/paper/towards-accurate-guided-diffusion-sampling","slug":"towards-accurate-guided-diffusion-sampling","title":"Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method","date":"2023-12-19","arxiv_id":"2312.12030","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":4,"n_instrument":5,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":12,"phrase":"9 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; 5 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/towards-accurate-guided-diffusion-sampling#ran","syntology_url":"https://syntology.ai/paper/2312.12030","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.12030"}},"official":{"repos":["hanshuyan/adjointdpm"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vidtome-video-token-merging-for-zero-shot","slug":"vidtome-video-token-merging-for-zero-shot","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","date":"2023-12-17","arxiv_id":"2312.10656","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":1,"n_no_contract":9,"n_pointer_only":0,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/vidtome-video-token-merging-for-zero-shot#ran","syntology_url":"https://syntology.ai/paper/2312.10656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.10656"}},"official":{"repos":["lixirui142/VidToMe"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/freeinit-bridging-initialization-gap-in-video","slug":"freeinit-bridging-initialization-gap-in-video","title":"FreeInit: Bridging Initialization Gap in Video Diffusion Models","date":"2023-12-12","arxiv_id":"2312.07537","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":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/freeinit-bridging-initialization-gap-in-video#ran","syntology_url":"https://syntology.ai/paper/2312.07537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07537"}},"official":{"repos":["tianxingwu/freeinit"],"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/peekaboo-interactive-video-generation-via","slug":"peekaboo-interactive-video-generation-via","title":"PEEKABOO: Interactive Video Generation via Masked-Diffusion","date":"2023-12-12","arxiv_id":"2312.07509","repositories_listed":1,"syntology":{"n":12,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"9 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; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/peekaboo-interactive-video-generation-via#ran","syntology_url":"https://syntology.ai/paper/2312.07509","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.07509"}},"official":{"repos":["microsoft/peekaboo"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/motioncrafter-one-shot-motion-customization","slug":"motioncrafter-one-shot-motion-customization","title":"MotionCrafter: One-Shot Motion Customization of Diffusion Models","date":"2023-12-08","arxiv_id":"2312.05288","repositories_listed":1,"syntology":null},{"url":"/paper/dreamvideo-composing-your-dream-videos-with","slug":"dreamvideo-composing-your-dream-videos-with","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","date":"2023-12-07","arxiv_id":"2312.04433","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-spatio-temporal-decoupling-for","slug":"hierarchical-spatio-temporal-decoupling-for","title":"Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation","date":"2023-12-07","arxiv_id":"2312.04483","repositories_listed":1,"syntology":null},{"url":"/paper/animatezero-video-diffusion-models-are-zero","slug":"animatezero-video-diffusion-models-are-zero","title":"AnimateZero: Video Diffusion Models are Zero-Shot Image Animators","date":"2023-12-06","arxiv_id":"2312.03793","repositories_listed":1,"syntology":null},{"url":"/paper/kandinsky-3-0-technical-report","slug":"kandinsky-3-0-technical-report","title":"Kandinsky 3.0 Technical Report","date":"2023-12-06","arxiv_id":"2312.03511","repositories_listed":1,"syntology":{"n":14,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/kandinsky-3-0-technical-report#ran","syntology_url":"https://syntology.ai/paper/2312.03511","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03511"}},"official":{"repos":["ai-forever/kandinsky-3"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/motionctrl-a-unified-and-flexible-motion","slug":"motionctrl-a-unified-and-flexible-motion","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","date":"2023-12-06","arxiv_id":"2312.03641","repositories_listed":1,"syntology":{"n":22,"n_ran":17,"n_constructed":0,"n_ran_checked":15,"n_instrument":2,"n_unverified":5,"n_honours":0,"n_violates":1,"n_no_contract":14,"n_pointer_only":3,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 1 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/motionctrl-a-unified-and-flexible-motion#ran","syntology_url":"https://syntology.ai/paper/2312.03641","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.03641"}},"official":{"repos":["TencentARC/MotionCtrl"],"state":"official (archive's flag): 17 ran","n_ran":17,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/bivdiff-a-training-free-framework-for-general","slug":"bivdiff-a-training-free-framework-for-general","title":"BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models","date":"2023-12-05","arxiv_id":"2312.02813","repositories_listed":1,"syntology":{"n":6,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/bivdiff-a-training-free-framework-for-general#ran","syntology_url":"https://syntology.ai/paper/2312.02813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02813"}},"official":{"repos":["mcg-nju/bivdiff"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/magicstick-controllable-video-editing-via","slug":"magicstick-controllable-video-editing-via","title":"MagicStick: Controllable Video Editing via Control Handle Transformations","date":"2023-12-05","arxiv_id":"2312.03047","repositories_listed":1,"syntology":null},{"url":"/paper/wovogen-world-volume-aware-diffusion-for","slug":"wovogen-world-volume-aware-diffusion-for","title":"WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation","date":"2023-12-05","arxiv_id":"2312.02934","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/wovogen-world-volume-aware-diffusion-for#ran","syntology_url":"https://syntology.ai/paper/2312.02934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02934"}},"official":{"repos":["fudan-zvg/wovogen"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dragvideo-interactive-drag-style-video","slug":"dragvideo-interactive-drag-style-video","title":"DragVideo: Interactive Drag-style Video Editing","date":"2023-12-03","arxiv_id":"2312.02216","repositories_listed":1,"syntology":{"n":14,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":14,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/dragvideo-interactive-drag-style-video#ran","syntology_url":"https://syntology.ai/paper/2312.02216","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.02216"}},"official":{"repos":["rickyskywalker/dragvideo-official"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/trackdiffusion-multi-object-tracking-data","slug":"trackdiffusion-multi-object-tracking-data","title":"TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion Models","date":"2023-12-01","arxiv_id":"2312.00651","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/trackdiffusion-multi-object-tracking-data#ran","syntology_url":"https://syntology.ai/paper/2312.00651","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00651"}},"official":null}},{"url":"/paper/vmc-video-motion-customization-using-temporal","slug":"vmc-video-motion-customization-using-temporal","title":"VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models","date":"2023-12-01","arxiv_id":"2312.00845","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/vmc-video-motion-customization-using-temporal#ran","syntology_url":"https://syntology.ai/paper/2312.00845","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.00845"}},"official":{"repos":["HyeonHo99/Video-Motion-Customization"],"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/vbench-comprehensive-benchmark-suite-for","slug":"vbench-comprehensive-benchmark-suite-for","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","date":"2023-11-29","arxiv_id":"2311.17982","repositories_listed":1,"syntology":null},{"url":"/paper/videoassembler-identity-consistent-video","slug":"videoassembler-identity-consistent-video","title":"MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing","date":"2023-11-29","arxiv_id":"2311.17338","repositories_listed":1,"syntology":{"n":12,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":2,"n_no_contract":7,"n_pointer_only":12,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 2 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videoassembler-identity-consistent-video#ran","syntology_url":"https://syntology.ai/paper/2311.17338","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.17338"}},"official":{"repos":["gulucaptain/videoassembler"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/panacea-panoramic-and-controllable-video","slug":"panacea-panoramic-and-controllable-video","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","date":"2023-11-28","arxiv_id":"2311.16813","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":3,"n_no_contract":4,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 3 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/panacea-panoramic-and-controllable-video#ran","syntology_url":"https://syntology.ai/paper/2311.16813","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16813"}},"official":null}},{"url":"/paper/sparsectrl-adding-sparse-controls-to-text-to","slug":"sparsectrl-adding-sparse-controls-to-text-to","title":"SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models","date":"2023-11-28","arxiv_id":"2311.16933","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":3,"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/sparsectrl-adding-sparse-controls-to-text-to#ran","syntology_url":"https://syntology.ai/paper/2311.16933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.16933"}},"official":null}},{"url":"/paper/fusionframes-efficient-architectural-aspects","slug":"fusionframes-efficient-architectural-aspects","title":"FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline","date":"2023-11-22","arxiv_id":"2311.13073","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-open-domain-image-animation-with","slug":"fine-grained-open-domain-image-animation-with","title":"AnimateAnything: Fine-Grained Open Domain Image Animation with Motion Guidance","date":"2023-11-21","arxiv_id":"2311.12886","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":8,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":1,"phrase":"10 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/fine-grained-open-domain-image-animation-with#ran","syntology_url":"https://syntology.ai/paper/2311.12886","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.12886"}},"official":{"repos":["alibaba/animate-anything"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mevgan-gan-based-plugin-model-for-video","slug":"mevgan-gan-based-plugin-model-for-video","title":"MeVGAN: GAN-based Plugin Model for Video Generation with Applications in Colonoscopy","date":"2023-11-07","arxiv_id":"2311.03884","repositories_listed":1,"syntology":null},{"url":"/paper/fetv-a-benchmark-for-fine-grained-evaluation-1","slug":"fetv-a-benchmark-for-fine-grained-evaluation-1","title":"FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation","date":"2023-11-03","arxiv_id":"2311.01813","repositories_listed":1,"syntology":null},{"url":"/paper/regis-refining-generated-videos-via-iterative","slug":"regis-refining-generated-videos-via-iterative","title":"REGIS: Refining Generated Videos via Iterative Stylistic Redesigning","date":"2023-11-03","arxiv_id":null,"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/cvpr-2023-text-guided-video-editing","slug":"cvpr-2023-text-guided-video-editing","title":"CVPR 2023 Text Guided Video Editing Competition","date":"2023-10-24","arxiv_id":"2310.16003","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/cvpr-2023-text-guided-video-editing#ran","syntology_url":"https://syntology.ai/paper/2310.16003","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16003"}},"official":{"repos":["showlab/loveu-tgve-2023"],"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/evalcrafter-benchmarking-and-evaluating-large","slug":"evalcrafter-benchmarking-and-evaluating-large","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","date":"2023-10-17","arxiv_id":"2310.11440","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":11,"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) · 4 unverified","sample_list":"/paper/evalcrafter-benchmarking-and-evaluating-large#ran","syntology_url":"https://syntology.ai/paper/2310.11440","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.11440"}},"official":{"repos":["EvalCrafter/EvalCrafter"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/a-survey-on-video-diffusion-models","slug":"a-survey-on-video-diffusion-models","title":"A Survey on Video Diffusion Models","date":"2023-10-16","arxiv_id":"2310.10647","repositories_listed":1,"syntology":null},{"url":"/paper/lamp-learn-a-motion-pattern-for-few-shot","slug":"lamp-learn-a-motion-pattern-for-few-shot","title":"LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation","date":"2023-10-16","arxiv_id":"2310.10769","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/lamp-learn-a-motion-pattern-for-few-shot#ran","syntology_url":"https://syntology.ai/paper/2310.10769","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10769"}},"official":{"repos":["RQ-Wu/LAMP"],"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/conditionvideo-training-free-condition-guided","slug":"conditionvideo-training-free-condition-guided","title":"ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation","date":"2023-10-11","arxiv_id":"2310.07697","repositories_listed":1,"syntology":null},{"url":"/paper/drivingdiffusion-layout-guided-multi-view","slug":"drivingdiffusion-layout-guided-multi-view","title":"DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion model","date":"2023-10-11","arxiv_id":"2310.07771","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":1,"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/drivingdiffusion-layout-guided-multi-view#ran","syntology_url":"https://syntology.ai/paper/2310.07771","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.07771"}},"official":{"repos":["shalfun/DrivingDiffusion"],"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/rt-gan-recurrent-temporal-gan-for-adding","slug":"rt-gan-recurrent-temporal-gan-for-adding","title":"RT-GAN: Recurrent Temporal GAN for Adding Lightweight Temporal Consistency to Frame-Based Domain Translation Approaches","date":"2023-10-02","arxiv_id":"2310.00868","repositories_listed":1,"syntology":null},{"url":"/paper/diverse-and-aligned-audio-to-video-generation","slug":"diverse-and-aligned-audio-to-video-generation","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","date":"2023-09-28","arxiv_id":"2309.16429","repositories_listed":1,"syntology":{"n":10,"n_ran":7,"n_constructed":0,"n_ran_checked":3,"n_instrument":4,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":7,"phrase":"7 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; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/diverse-and-aligned-audio-to-video-generation#ran","syntology_url":"https://syntology.ai/paper/2309.16429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.16429"}},"official":{"repos":["guyyariv/TempoTokens"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/show-1-marrying-pixel-and-latent-diffusion","slug":"show-1-marrying-pixel-and-latent-diffusion","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","date":"2023-09-27","arxiv_id":"2309.15818","repositories_listed":1,"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":1,"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/show-1-marrying-pixel-and-latent-diffusion#ran","syntology_url":"https://syntology.ai/paper/2309.15818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.15818"}},"official":{"repos":["showlab/show-1"],"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/glober-coherent-non-autoregressive-video-1","slug":"glober-coherent-non-autoregressive-video-1","title":"GLOBER: Coherent Non-autoregressive Video Generation via GLOBal Guided Video DecodER","date":"2023-09-23","arxiv_id":"2309.13274","repositories_listed":1,"syntology":null},{"url":"/paper/freeu-free-lunch-in-diffusion-u-net","slug":"freeu-free-lunch-in-diffusion-u-net","title":"FreeU: Free Lunch in Diffusion U-Net","date":"2023-09-20","arxiv_id":"2309.11497","repositories_listed":1,"syntology":null},{"url":"/paper/drivedreamer-towards-real-world-driven-world","slug":"drivedreamer-towards-real-world-driven-world","title":"DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving","date":"2023-09-18","arxiv_id":"2309.09777","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/drivedreamer-towards-real-world-driven-world#ran","syntology_url":"https://syntology.ai/paper/2309.09777","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.09777"}},"official":null}},{"url":"/paper/reuse-and-diffuse-iterative-denoising-for","slug":"reuse-and-diffuse-iterative-denoising-for","title":"Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation","date":"2023-09-07","arxiv_id":"2309.03549","repositories_listed":1,"syntology":null},{"url":"/paper/styleinv-a-temporal-style-modulated-inversion","slug":"styleinv-a-temporal-style-modulated-inversion","title":"StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation","date":"2023-08-31","arxiv_id":"2308.16909","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/styleinv-a-temporal-style-modulated-inversion#ran","syntology_url":"https://syntology.ai/paper/2308.16909","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.16909"}},"official":{"repos":["johannwyh/styleinv"],"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/storybench-a-multifaceted-benchmark-for-1","slug":"storybench-a-multifaceted-benchmark-for-1","title":"StoryBench: A Multifaceted Benchmark for Continuous Story Visualization","date":"2023-08-22","arxiv_id":"2308.11606","repositories_listed":1,"syntology":{"n":16,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":2,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/storybench-a-multifaceted-benchmark-for-1#ran","syntology_url":"https://syntology.ai/paper/2308.11606","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11606"}},"official":{"repos":["google/storybench"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/dragnuwa-fine-grained-control-in-video","slug":"dragnuwa-fine-grained-control-in-video","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","date":"2023-08-16","arxiv_id":"2308.08089","repositories_listed":1,"syntology":null},{"url":"/paper/implicit-identity-representation-conditioned","slug":"implicit-identity-representation-conditioned","title":"Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation","date":"2023-07-19","arxiv_id":"2307.09906","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":3,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result","sample_list":"/paper/implicit-identity-representation-conditioned#ran","syntology_url":"https://syntology.ai/paper/2307.09906","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.09906"}},"official":{"repos":["harlanhong/iccv2023-mcnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":3,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/bidirectionally-deformable-motion-modulation","slug":"bidirectionally-deformable-motion-modulation","title":"Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer","date":"2023-07-15","arxiv_id":"2307.07754","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":4,"n_ran_checked":4,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/bidirectionally-deformable-motion-modulation#ran","syntology_url":"https://syntology.ai/paper/2307.07754","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.07754"}},"official":{"repos":["rocketappslab/bdmm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/animate-a-story-storytelling-with-retrieval","slug":"animate-a-story-storytelling-with-retrieval","title":"Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation","date":"2023-07-13","arxiv_id":"2307.06940","repositories_listed":1,"syntology":null},{"url":"/paper/internvid-a-large-scale-video-text-dataset","slug":"internvid-a-large-scale-video-text-dataset","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","date":"2023-07-13","arxiv_id":"2307.06942","repositories_listed":1,"syntology":null},{"url":"/paper/gd-vdm-generated-depth-for-better-diffusion","slug":"gd-vdm-generated-depth-for-better-diffusion","title":"GD-VDM: Generated Depth for better Diffusion-based Video Generation","date":"2023-06-19","arxiv_id":"2306.11173","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/learn-the-force-we-can-multi-object-video","slug":"learn-the-force-we-can-multi-object-video","title":"Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation","date":"2023-06-06","arxiv_id":"2306.03988","repositories_listed":1,"syntology":null},{"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":16,"n_instrument":0,"n_unverified":1,"n_honours":2,"n_violates":3,"n_no_contract":11,"n_pointer_only":3,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 3 violated, 11 with no contract checked; 0 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":16,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/gen-l-video-multi-text-to-long-video","slug":"gen-l-video-multi-text-to-long-video","title":"Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising","date":"2023-05-29","arxiv_id":"2305.18264","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/gen-l-video-multi-text-to-long-video#ran","syntology_url":"https://syntology.ai/paper/2305.18264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.18264"}},"official":{"repos":["g-u-n/gen-l-video"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/control-a-video-controllable-text-to-video","slug":"control-a-video-controllable-text-to-video","title":"Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning","date":"2023-05-23","arxiv_id":"2305.13840","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-are-frame-level","slug":"large-language-models-are-frame-level","title":"DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation","date":"2023-05-23","arxiv_id":"2305.14330","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/large-language-models-are-frame-level#ran","syntology_url":"https://syntology.ai/paper/2305.14330","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14330"}},"official":{"repos":["ku-cvlab/direct2v"],"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/controlvideo-training-free-controllable-text","slug":"controlvideo-training-free-controllable-text","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","date":"2023-05-22","arxiv_id":"2305.13077","repositories_listed":1,"syntology":{"n":9,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":6,"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) · 6 unverified","sample_list":"/paper/controlvideo-training-free-controllable-text#ran","syntology_url":"https://syntology.ai/paper/2305.13077","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.13077"}},"official":{"repos":["ybybzhang/controlvideo"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"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/videofactory-swap-attention-in-spatiotemporal","slug":"videofactory-swap-attention-in-spatiotemporal","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","date":"2023-05-18","arxiv_id":"2305.10874","repositories_listed":1,"syntology":null},{"url":"/paper/dagan-depth-aware-generative-adversarial","slug":"dagan-depth-aware-generative-adversarial","title":"DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation","date":"2023-05-10","arxiv_id":"2305.06225","repositories_listed":1,"syntology":null},{"url":"/paper/sketching-the-future-stf-applying-conditional","slug":"sketching-the-future-stf-applying-conditional","title":"Sketching the Future (STF): Applying Conditional Control Techniques to Text-to-Video Models","date":"2023-05-10","arxiv_id":"2305.05845","repositories_listed":1,"syntology":null},{"url":"/paper/styleavatar-real-time-photo-realistic","slug":"styleavatar-real-time-photo-realistic","title":"StyleAvatar: Real-time Photo-realistic Portrait Avatar from a Single Video","date":"2023-05-01","arxiv_id":"2305.00942","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/styleavatar-real-time-photo-realistic#ran","syntology_url":"https://syntology.ai/paper/2305.00942","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.00942"}},"official":{"repos":["lizhenwangt/styleavatar"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/generative-disco-text-to-video-generation-for","slug":"generative-disco-text-to-video-generation-for","title":"Generative Disco: Text-to-Video Generation for Music Visualization","date":"2023-04-17","arxiv_id":"2304.08551","repositories_listed":1,"syntology":null},{"url":"/paper/text2performer-text-driven-human-video","slug":"text2performer-text-driven-human-video","title":"Text2Performer: Text-Driven Human Video Generation","date":"2023-04-17","arxiv_id":"2304.08483","repositories_listed":1,"syntology":null},{"url":"/paper/mask-conditioned-latent-diffusion-for","slug":"mask-conditioned-latent-diffusion-for","title":"Mask-conditioned latent diffusion for generating gastrointestinal polyp images","date":"2023-04-11","arxiv_id":"2304.05233","repositories_listed":1,"syntology":null},{"url":"/paper/generative-recommendation-towards-next","slug":"generative-recommendation-towards-next","title":"Generative Recommendation: Towards Next-generation Recommender Paradigm","date":"2023-04-07","arxiv_id":"2304.03516","repositories_listed":1,"syntology":null},{"url":"/paper/mostgan-v-video-generation-with-temporal","slug":"mostgan-v-video-generation-with-temporal","title":"MoStGAN-V: Video Generation with Temporal Motion Styles","date":"2023-04-05","arxiv_id":"2304.02777","repositories_listed":1,"syntology":null},{"url":"/paper/sounding-video-generator-a-unified-framework","slug":"sounding-video-generator-a-unified-framework","title":"Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation","date":"2023-03-29","arxiv_id":"2303.16541","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-audible-video-description","slug":"fine-grained-audible-video-description","title":"Fine-grained Audible Video Description","date":"2023-03-27","arxiv_id":"2303.15616","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"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) · 5 unverified","sample_list":"/paper/fine-grained-audible-video-description#ran","syntology_url":"https://syntology.ai/paper/2303.15616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.15616"}},"official":{"repos":["opennlplab/favdbench"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/celebv-text-a-large-scale-facial-text-video","slug":"celebv-text-a-large-scale-facial-text-video","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","date":"2023-03-26","arxiv_id":"2303.14717","repositories_listed":1,"syntology":null},{"url":"/paper/conditional-image-to-video-generation-with","slug":"conditional-image-to-video-generation-with","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","date":"2023-03-24","arxiv_id":"2303.13744","repositories_listed":1,"syntology":{"n":9,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":4,"n_no_contract":1,"n_pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 4 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/conditional-image-to-video-generation-with#ran","syntology_url":"https://syntology.ai/paper/2303.13744","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.13744"}},"official":{"repos":["nihaomiao/cvpr23_lfdm"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/text2video-zero-text-to-image-diffusion","slug":"text2video-zero-text-to-image-diffusion","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","date":"2023-03-23","arxiv_id":"2303.13439","repositories_listed":1,"syntology":null},{"url":"/paper/feature-conditioned-cascaded-video-diffusion","slug":"feature-conditioned-cascaded-video-diffusion","title":"Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis","date":"2023-03-22","arxiv_id":"2303.12644","repositories_listed":1,"syntology":null},{"url":"/paper/towards-end-to-end-generative-modeling-of","slug":"towards-end-to-end-generative-modeling-of","title":"Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers","date":"2023-03-20","arxiv_id":"2303.11251","repositories_listed":1,"syntology":null},{"url":"/paper/blind-video-deflickering-by-neural-filtering","slug":"blind-video-deflickering-by-neural-filtering","title":"Blind Video Deflickering by Neural Filtering with a Flawed Atlas","date":"2023-03-14","arxiv_id":"2303.08120","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":1,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/blind-video-deflickering-by-neural-filtering#ran","syntology_url":"https://syntology.ai/paper/2303.08120","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08120"}},"official":{"repos":["chenyanglei/all-in-one-deflicker"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}}],"record_sha256":"d2afc16848fa65d3d4d0224f9aa6e707f7311d32c34c2238a6ab8f60408586df","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}