{"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/ran/1","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":"ran","order_definition":"only papers where Syntology ran at least one harvested sample; date (newest first), ties by arXiv id","caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","absence":"A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.","page":1,"pages_in_order":3,"rows_per_page":100,"rows":[1,100],"of":257,"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/papers/ran/1","prev":null,"next":"/task/video-generation/papers/ran/2","papers":[{"url":"/paper/scaling-rl-to-long-videos","slug":"scaling-rl-to-long-videos","title":"Scaling RL to Long Videos","date":"2025-07-10","arxiv_id":"2507.07966","repositories_listed":1,"syntology":{"n":24,"n_ran":18,"n_constructed":1,"n_ran_checked":14,"n_instrument":4,"n_unverified":6,"n_honours":0,"n_violates":1,"n_no_contract":13,"n_pointer_only":1,"phrase":"18 ran (of which 1 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 1 violated, 13 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/scaling-rl-to-long-videos#ran","syntology_url":"https://syntology.ai/paper/2507.07966","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.07966"}},"official":{"repos":["hiyouga/easyr1"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":1,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["found_in_text","official"]}}},{"url":"/paper/omni-video-democratizing-unified-video","slug":"omni-video-democratizing-unified-video","title":"Omni-Video: Democratizing Unified Video Understanding and Generation","date":"2025-07-08","arxiv_id":"2507.06119","repositories_listed":1,"syntology":{"n":18,"n_ran":14,"n_constructed":0,"n_ran_checked":11,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":18,"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) · 4 unverified","sample_list":"/paper/omni-video-democratizing-unified-video#ran","syntology_url":"https://syntology.ai/paper/2507.06119","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.06119"}},"official":{"repos":["sais-fuxi/omni-video"],"state":"official (archive's flag): 14 ran","n_ran":14,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/show-o2-improved-native-unified-multimodal","slug":"show-o2-improved-native-unified-multimodal","title":"Show-o2: Improved Native Unified Multimodal Models","date":"2025-06-18","arxiv_id":"2506.15564","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":5,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/show-o2-improved-native-unified-multimodal#ran","syntology_url":"https://syntology.ai/paper/2506.15564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.15564"}},"official":{"repos":["showlab/show-o"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/magcache-fast-video-generation-with-magnitude","slug":"magcache-fast-video-generation-with-magnitude","title":"MagCache: Fast Video Generation with Magnitude-Aware Cache","date":"2025-06-10","arxiv_id":"2506.09045","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/magcache-fast-video-generation-with-magnitude#ran","syntology_url":"https://syntology.ai/paper/2506.09045","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.09045"}},"official":{"repos":["zehong-ma/magcache","Zehong-Ma/ComfyUI-MagCache"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/orv-4d-occupancy-centric-robot-video","slug":"orv-4d-occupancy-centric-robot-video","title":"ORV: 4D Occupancy-centric Robot Video Generation","date":"2025-06-03","arxiv_id":"2506.03079","repositories_listed":1,"syntology":{"n":18,"n_ran":16,"n_constructed":0,"n_ran_checked":14,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":14,"n_pointer_only":0,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/orv-4d-occupancy-centric-robot-video#ran","syntology_url":"https://syntology.ai/paper/2506.03079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.03079"}},"official":{"repos":["orangesodahub/orv"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":14,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/videorepa-learning-physics-for-video","slug":"videorepa-learning-physics-for-video","title":"VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models","date":"2025-05-29","arxiv_id":"2505.23656","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/videorepa-learning-physics-for-video#ran","syntology_url":"https://syntology.ai/paper/2505.23656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23656"}},"official":{"repos":["aHapBean/VideoREPA"],"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/magref-masked-guidance-for-any-reference","slug":"magref-masked-guidance-for-any-reference","title":"MAGREF: Masked Guidance for Any-Reference Video Generation","date":"2025-05-29","arxiv_id":"2505.23742","repositories_listed":1,"syntology":{"n":14,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":4,"n_honours":0,"n_violates":1,"n_no_contract":5,"n_pointer_only":5,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/magref-masked-guidance-for-any-reference#ran","syntology_url":"https://syntology.ai/paper/2505.23742","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23742"}},"official":{"repos":["magref-video/magref"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/let-them-talk-audio-driven-multi-person","slug":"let-them-talk-audio-driven-multi-person","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","date":"2025-05-28","arxiv_id":"2505.22647","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":1,"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: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/let-them-talk-audio-driven-multi-person#ran","syntology_url":"https://syntology.ai/paper/2505.22647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.22647"}},"official":{"repos":["meigen-ai/multitalk"],"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/opens2v-nexus-a-detailed-benchmark-and","slug":"opens2v-nexus-a-detailed-benchmark-and","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","date":"2025-05-26","arxiv_id":"2505.20292","repositories_listed":2,"syntology":{"n":38,"n_ran":35,"n_constructed":0,"n_ran_checked":33,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":33,"n_pointer_only":2,"phrase":"35 ran (of which 0 constructed an object rather than computing a result; 33 with no instrument failure: 0 honoured, 0 violated, 33 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/opens2v-nexus-a-detailed-benchmark-and#ran","syntology_url":"https://syntology.ai/paper/2505.20292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.20292"}},"official":{"repos":["PKU-YuanGroup/ConsisID","PKU-YuanGroup/OpenS2V-Nexus"],"state":"official (archive's flag): 35 ran","n_ran":35,"n_constructed":0,"n_ran_no_instrument_failure":33,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/vorta-efficient-video-diffusion-via-routing","slug":"vorta-efficient-video-diffusion-via-routing","title":"VORTA: Efficient Video Diffusion via Routing Sparse Attention","date":"2025-05-24","arxiv_id":"2505.18809","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/vorta-efficient-video-diffusion-via-routing#ran","syntology_url":"https://syntology.ai/paper/2505.18809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.18809"}},"official":{"repos":["wenhao728/vorta"],"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"]}}},{"url":"/paper/busterx-mllm-powered-ai-generated-video","slug":"busterx-mllm-powered-ai-generated-video","title":"BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation","date":"2025-05-19","arxiv_id":"2505.12620","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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/busterx-mllm-powered-ai-generated-video#ran","syntology_url":"https://syntology.ai/paper/2505.12620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12620"}},"official":{"repos":["l8cv/busterx"],"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/dreamgen-unlocking-generalization-in-robot","slug":"dreamgen-unlocking-generalization-in-robot","title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","date":"2025-05-19","arxiv_id":"2505.12705","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":1,"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/dreamgen-unlocking-generalization-in-robot#ran","syntology_url":"https://syntology.ai/paper/2505.12705","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12705"}},"official":{"repos":["nvidia/gr00t-dreams"],"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/magi-1-autoregressive-video-generation-at","slug":"magi-1-autoregressive-video-generation-at","title":"MAGI-1: Autoregressive Video Generation at Scale","date":"2025-05-19","arxiv_id":"2505.13211","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/magi-1-autoregressive-video-generation-at#ran","syntology_url":"https://syntology.ai/paper/2505.13211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.13211"}},"official":{"repos":["sandai-org/magi-1","sandai-org/magiattention"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/dancegrpo-unleashing-grpo-on-visual","slug":"dancegrpo-unleashing-grpo-on-visual","title":"DanceGRPO: Unleashing GRPO on Visual Generation","date":"2025-05-12","arxiv_id":"2505.07818","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":0,"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, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/dancegrpo-unleashing-grpo-on-visual#ran","syntology_url":"https://syntology.ai/paper/2505.07818","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.07818"}},"official":null}},{"url":"/paper/hunyuancustom-a-multimodal-driven","slug":"hunyuancustom-a-multimodal-driven","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","date":"2025-05-07","arxiv_id":"2505.04512","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/hunyuancustom-a-multimodal-driven#ran","syntology_url":"https://syntology.ai/paper/2505.04512","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.04512"}},"official":null}},{"url":"/paper/holotime-taming-video-diffusion-models-for","slug":"holotime-taming-video-diffusion-models-for","title":"HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation","date":"2025-04-30","arxiv_id":"2504.21650","repositories_listed":1,"syntology":{"n":8,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":1,"n_no_contract":3,"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, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/holotime-taming-video-diffusion-models-for#ran","syntology_url":"https://syntology.ai/paper/2504.21650","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.21650"}},"official":{"repos":["pku-yuangroup/holotime"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/uni3c-unifying-precisely-3d-enhanced-camera","slug":"uni3c-unifying-precisely-3d-enhanced-camera","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation","date":"2025-04-21","arxiv_id":"2504.14899","repositories_listed":1,"syntology":{"n":12,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":1,"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) · 5 unverified","sample_list":"/paper/uni3c-unifying-precisely-3d-enhanced-camera#ran","syntology_url":"https://syntology.ai/paper/2504.14899","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.14899"}},"official":{"repos":["ewrfcas/uni3c"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/diffusion-transformers-for-tabular-data-time","slug":"diffusion-transformers-for-tabular-data-time","title":"Diffusion Transformers for Tabular Data Time Series Generation","date":"2025-04-10","arxiv_id":"2504.07566","repositories_listed":1,"syntology":{"n":5,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":1,"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, 1 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/diffusion-transformers-for-tabular-data-time#ran","syntology_url":"https://syntology.ai/paper/2504.07566","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.07566"}},"official":{"repos":["fabriziogaruti/TabDiT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["community","official"]}}},{"url":"/paper/model-reveals-what-to-cache-profiling-based","slug":"model-reveals-what-to-cache-profiling-based","title":"Model Reveals What to Cache: Profiling-Based Feature Reuse for Video Diffusion Models","date":"2025-04-04","arxiv_id":"2504.03140","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/model-reveals-what-to-cache-profiling-based#ran","syntology_url":"https://syntology.ai/paper/2504.03140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.03140"}},"official":{"repos":["geekguru123/profilingdit"],"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/conmo-controllable-motion-disentanglement-and","slug":"conmo-controllable-motion-disentanglement-and","title":"ConMo: Controllable Motion Disentanglement and Recomposition for Zero-Shot Motion Transfer","date":"2025-04-03","arxiv_id":"2504.02451","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/conmo-controllable-motion-disentanglement-and#ran","syntology_url":"https://syntology.ai/paper/2504.02451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.02451"}},"official":{"repos":["andyplus1/conmo"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hoigen-1m-a-large-scale-dataset-for-human","slug":"hoigen-1m-a-large-scale-dataset-for-human","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","date":"2025-03-31","arxiv_id":"2503.23715","repositories_listed":0,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/hoigen-1m-a-large-scale-dataset-for-human#ran","syntology_url":"https://syntology.ai/paper/2503.23715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.23715"}},"official":null}},{"url":"/paper/efficientmt-efficient-temporal-adaptation-for","slug":"efficientmt-efficient-temporal-adaptation-for","title":"EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion Models","date":"2025-03-25","arxiv_id":"2503.19369","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":4,"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) · 4 unverified","sample_list":"/paper/efficientmt-efficient-temporal-adaptation-for#ran","syntology_url":"https://syntology.ai/paper/2503.19369","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.19369"}},"official":{"repos":["prototypenx/efficientmt"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/leanvae-an-ultra-efficient-reconstruction-vae","slug":"leanvae-an-ultra-efficient-reconstruction-vae","title":"LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models","date":"2025-03-18","arxiv_id":"2503.14325","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/leanvae-an-ultra-efficient-reconstruction-vae#ran","syntology_url":"https://syntology.ai/paper/2503.14325","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.14325"}},"official":{"repos":["westlake-repl/leanvae"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/recammaster-camera-controlled-generative","slug":"recammaster-camera-controlled-generative","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","date":"2025-03-14","arxiv_id":"2503.11647","repositories_listed":0,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/recammaster-camera-controlled-generative#ran","syntology_url":"https://syntology.ai/paper/2503.11647","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.11647"}},"official":null}},{"url":"/paper/vmbench-a-benchmark-for-perception-aligned","slug":"vmbench-a-benchmark-for-perception-aligned","title":"VMBench: A Benchmark for Perception-Aligned Video Motion Generation","date":"2025-03-13","arxiv_id":"2503.10076","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":6,"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, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/vmbench-a-benchmark-for-perception-aligned#ran","syntology_url":"https://syntology.ai/paper/2503.10076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10076"}},"official":{"repos":["gd-aigc/vmbench"],"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/pisa-experiments-exploring-physics-post","slug":"pisa-experiments-exploring-physics-post","title":"PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop","date":"2025-03-12","arxiv_id":"2503.09595","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":0,"n_no_contract":8,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/pisa-experiments-exploring-physics-post#ran","syntology_url":"https://syntology.ai/paper/2503.09595","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09595"}},"official":{"repos":["vision-x-nyu/pisa-experiments"],"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/open-sora-2-0-training-a-commercial-level","slug":"open-sora-2-0-training-a-commercial-level","title":"Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k","date":"2025-03-12","arxiv_id":"2503.09642","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/open-sora-2-0-training-a-commercial-level#ran","syntology_url":"https://syntology.ai/paper/2503.09642","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09642"}},"official":{"repos":["hpcaitech/open-sora"],"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/neighboring-autoregressive-modeling-for","slug":"neighboring-autoregressive-modeling-for","title":"Neighboring Autoregressive Modeling for Efficient Visual Generation","date":"2025-03-12","arxiv_id":"2503.10696","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/neighboring-autoregressive-modeling-for#ran","syntology_url":"https://syntology.ai/paper/2503.10696","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.10696"}},"official":{"repos":["thisisbillhe/nar"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/ar-diffusion-asynchronous-video-generation","slug":"ar-diffusion-asynchronous-video-generation","title":"AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion","date":"2025-03-10","arxiv_id":"2503.07418","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/ar-diffusion-asynchronous-video-generation#ran","syntology_url":"https://syntology.ai/paper/2503.07418","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07418"}},"official":null}},{"url":"/paper/vace-all-in-one-video-creation-and-editing","slug":"vace-all-in-one-video-creation-and-editing","title":"VACE: All-in-One Video Creation and Editing","date":"2025-03-10","arxiv_id":"2503.07598","repositories_listed":2,"syntology":{"n":19,"n_ran":11,"n_constructed":5,"n_ran_checked":9,"n_instrument":2,"n_unverified":8,"n_honours":0,"n_violates":1,"n_no_contract":8,"n_pointer_only":0,"phrase":"11 ran (of which 5 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","sample_list":"/paper/vace-all-in-one-video-creation-and-editing#ran","syntology_url":"https://syntology.ai/paper/2503.07598","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07598"}},"official":null}},{"url":"/paper/videophy-2-a-challenging-action-centric","slug":"videophy-2-a-challenging-action-centric","title":"VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation","date":"2025-03-09","arxiv_id":"2503.06800","repositories_listed":1,"syntology":{"n":17,"n_ran":15,"n_constructed":0,"n_ran_checked":12,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":11,"n_pointer_only":2,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 1 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videophy-2-a-challenging-action-centric#ran","syntology_url":"https://syntology.ai/paper/2503.06800","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.06800"}},"official":null}},{"url":"/paper/gen3c-3d-informed-world-consistent-video","slug":"gen3c-3d-informed-world-consistent-video","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","date":"2025-03-05","arxiv_id":"2503.03751","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":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/gen3c-3d-informed-world-consistent-video#ran","syntology_url":"https://syntology.ai/paper/2503.03751","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.03751"}},"official":{"repos":["nv-tlabs/GEN3C"],"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/extrapolating-and-decoupling-image-to-video","slug":"extrapolating-and-decoupling-image-to-video","title":"Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think","date":"2025-03-02","arxiv_id":"2503.00948","repositories_listed":1,"syntology":{"n":15,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":3,"n_honours":0,"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; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/extrapolating-and-decoupling-image-to-video#ran","syntology_url":"https://syntology.ai/paper/2503.00948","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00948"}},"official":{"repos":["Chuge0335/EDG"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/riflex-a-free-lunch-for-length-extrapolation","slug":"riflex-a-free-lunch-for-length-extrapolation","title":"RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers","date":"2025-02-21","arxiv_id":"2502.15894","repositories_listed":0,"syntology":{"n":7,"n_ran":6,"n_constructed":1,"n_ran_checked":4,"n_instrument":2,"n_unverified":1,"n_honours":2,"n_violates":1,"n_no_contract":1,"n_pointer_only":4,"phrase":"6 ran (of which 1 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/riflex-a-free-lunch-for-length-extrapolation#ran","syntology_url":"https://syntology.ai/paper/2502.15894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15894"}},"official":null}},{"url":"/paper/phantom-subject-consistent-video-generation","slug":"phantom-subject-consistent-video-generation","title":"Phantom: Subject-consistent video generation via cross-modal alignment","date":"2025-02-16","arxiv_id":"2502.11079","repositories_listed":1,"syntology":{"n":12,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":5,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/phantom-subject-consistent-video-generation#ran","syntology_url":"https://syntology.ai/paper/2502.11079","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.11079"}},"official":null}},{"url":"/paper/step-video-t2v-technical-report-the-practice","slug":"step-video-t2v-technical-report-the-practice","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","date":"2025-02-14","arxiv_id":"2502.10248","repositories_listed":3,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":7,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/step-video-t2v-technical-report-the-practice#ran","syntology_url":"https://syntology.ai/paper/2502.10248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.10248"}},"official":{"repos":["stepfun-ai/step-video-t2v"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/triposg-high-fidelity-3d-shape-synthesis","slug":"triposg-high-fidelity-3d-shape-synthesis","title":"TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models","date":"2025-02-10","arxiv_id":"2502.06608","repositories_listed":2,"syntology":{"n":6,"n_ran":6,"n_constructed":0,"n_ran_checked":5,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/triposg-high-fidelity-3d-shape-synthesis#ran","syntology_url":"https://syntology.ai/paper/2502.06608","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.06608"}},"official":{"repos":["VAST-AI-Research/TripoSG"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/flashvideo-flowing-fidelity-to-detail-for","slug":"flashvideo-flowing-fidelity-to-detail-for","title":"FlashVideo:Flowing Fidelity to Detail for Efficient High-Resolution Video Generation","date":"2025-02-07","arxiv_id":"2502.05179","repositories_listed":1,"syntology":{"n":15,"n_ran":13,"n_constructed":0,"n_ran_checked":12,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":3,"n_no_contract":8,"n_pointer_only":2,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 3 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/flashvideo-flowing-fidelity-to-detail-for#ran","syntology_url":"https://syntology.ai/paper/2502.05179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.05179"}},"official":{"repos":["foundationvision/flashvideo"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":12,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/vidsketch-hand-drawn-sketch-driven-video","slug":"vidsketch-hand-drawn-sketch-driven-video","title":"VidSketch: Hand-drawn Sketch-Driven Video Generation with Diffusion Control","date":"2025-02-03","arxiv_id":"2502.01101","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/vidsketch-hand-drawn-sketch-driven-video#ran","syntology_url":"https://syntology.ai/paper/2502.01101","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01101"}},"official":{"repos":["CSfufu/VidSketch"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/improved-training-technique-for-latent","slug":"improved-training-technique-for-latent","title":"Improved Training Technique for Latent Consistency Models","date":"2025-02-03","arxiv_id":"2502.01441","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":1,"n_instrument":6,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":8,"phrase":"7 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; 6 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/improved-training-technique-for-latent#ran","syntology_url":"https://syntology.ai/paper/2502.01441","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.01441"}},"official":{"repos":["quandao10/slct"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/inference-time-text-to-video-alignment-with","slug":"inference-time-text-to-video-alignment-with","title":"Inference-Time Text-to-Video Alignment with Diffusion Latent Beam Search","date":"2025-01-31","arxiv_id":"2501.19252","repositories_listed":1,"syntology":{"n":10,"n_ran":9,"n_constructed":0,"n_ran_checked":5,"n_instrument":4,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/inference-time-text-to-video-alignment-with#ran","syntology_url":"https://syntology.ai/paper/2501.19252","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.19252"}},"official":null}},{"url":"/paper/videoshield-regulating-diffusion-based-video","slug":"videoshield-regulating-diffusion-based-video","title":"VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking","date":"2025-01-24","arxiv_id":"2501.14195","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/videoshield-regulating-diffusion-based-video#ran","syntology_url":"https://syntology.ai/paper/2501.14195","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.14195"}},"official":{"repos":["hurunyi/videoshield"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/video-depth-anything-consistent-depth","slug":"video-depth-anything-consistent-depth","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","date":"2025-01-21","arxiv_id":"2501.12375","repositories_listed":1,"syntology":{"n":10,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":0,"n_honours":1,"n_violates":1,"n_no_contract":4,"n_pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/video-depth-anything-consistent-depth#ran","syntology_url":"https://syntology.ai/paper/2501.12375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.12375"}},"official":null}},{"url":"/paper/diffueraser-a-diffusion-model-for-video","slug":"diffueraser-a-diffusion-model-for-video","title":"DiffuEraser: A Diffusion Model for Video Inpainting","date":"2025-01-17","arxiv_id":"2501.10018","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/diffueraser-a-diffusion-model-for-video#ran","syntology_url":"https://syntology.ai/paper/2501.10018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.10018"}},"official":{"repos":["lixiaowen-xw/diffueraser"],"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/framepainter-endowing-interactive-image","slug":"framepainter-endowing-interactive-image","title":"FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors","date":"2025-01-14","arxiv_id":"2501.08225","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/framepainter-endowing-interactive-image#ran","syntology_url":"https://syntology.ai/paper/2501.08225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08225"}},"official":{"repos":["ybybzhang/framepainter"],"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/vchitect-2-0-parallel-transformer-for-scaling","slug":"vchitect-2-0-parallel-transformer-for-scaling","title":"Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models","date":"2025-01-14","arxiv_id":"2501.08453","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":1,"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) · 3 unverified","sample_list":"/paper/vchitect-2-0-parallel-transformer-for-scaling#ran","syntology_url":"https://syntology.ai/paper/2501.08453","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.08453"}},"official":null}},{"url":"/paper/diffusion-as-shader-3d-aware-video-diffusion","slug":"diffusion-as-shader-3d-aware-video-diffusion","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","date":"2025-01-07","arxiv_id":"2501.03847","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/diffusion-as-shader-3d-aware-video-diffusion#ran","syntology_url":"https://syntology.ai/paper/2501.03847","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.03847"}},"official":{"repos":["igl-hkust/diffusionasshader"],"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/visionreward-fine-grained-multi-dimensional","slug":"visionreward-fine-grained-multi-dimensional","title":"VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation","date":"2024-12-30","arxiv_id":"2412.21059","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":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/visionreward-fine-grained-multi-dimensional#ran","syntology_url":"https://syntology.ai/paper/2412.21059","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.21059"}},"official":{"repos":["thudm/visionreward"],"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/vinci-a-real-time-embodied-smart-assistant","slug":"vinci-a-real-time-embodied-smart-assistant","title":"Vinci: A Real-time Embodied Smart Assistant based on Egocentric Vision-Language Model","date":"2024-12-30","arxiv_id":"2412.21080","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/vinci-a-real-time-embodied-smart-assistant#ran","syntology_url":"https://syntology.ai/paper/2412.21080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.21080"}},"official":{"repos":["opengvlab/vinci"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/ltx-video-realtime-video-latent-diffusion","slug":"ltx-video-realtime-video-latent-diffusion","title":"LTX-Video: Realtime Video Latent Diffusion","date":"2024-12-30","arxiv_id":"2501.00103","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/ltx-video-realtime-video-latent-diffusion#ran","syntology_url":"https://syntology.ai/paper/2501.00103","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.00103"}},"official":{"repos":["Lightricks/LTX-Video"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/open-sora-democratizing-efficient-video","slug":"open-sora-democratizing-efficient-video","title":"Open-Sora: Democratizing Efficient Video Production for All","date":"2024-12-29","arxiv_id":"2412.20404","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/open-sora-democratizing-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2412.20404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.20404"}},"official":{"repos":["hpcaitech/open-sora"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/drivingworld-constructingworld-model-for","slug":"drivingworld-constructingworld-model-for","title":"DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT","date":"2024-12-27","arxiv_id":"2412.19505","repositories_listed":1,"syntology":{"n":9,"n_ran":9,"n_constructed":0,"n_ran_checked":8,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":7,"n_pointer_only":2,"phrase":"9 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/drivingworld-constructingworld-model-for#ran","syntology_url":"https://syntology.ai/paper/2412.19505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.19505"}},"official":{"repos":["yvanyin/drivingworld"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/videomaker-zero-shot-customized-video","slug":"videomaker-zero-shot-customized-video","title":"VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models","date":"2024-12-27","arxiv_id":"2412.19645","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":2,"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/videomaker-zero-shot-customized-video#ran","syntology_url":"https://syntology.ai/paper/2412.19645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.19645"}},"official":null}},{"url":"/paper/accelerating-diffusion-transformers-with-dual","slug":"accelerating-diffusion-transformers-with-dual","title":"Accelerating Diffusion Transformers with Dual Feature Caching","date":"2024-12-25","arxiv_id":"2412.18911","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/accelerating-diffusion-transformers-with-dual#ran","syntology_url":"https://syntology.ai/paper/2412.18911","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18911"}},"official":{"repos":["shenyi-z/duca"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/ditctrl-exploring-attention-control-in-multi","slug":"ditctrl-exploring-attention-control-in-multi","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","date":"2024-12-24","arxiv_id":"2412.18597","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/ditctrl-exploring-attention-control-in-multi#ran","syntology_url":"https://syntology.ai/paper/2412.18597","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.18597"}},"official":{"repos":["tencentarc/ditctrl"],"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/video-prediction-policy-a-generalist-robot","slug":"video-prediction-policy-a-generalist-robot","title":"Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations","date":"2024-12-19","arxiv_id":"2412.14803","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":3,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/video-prediction-policy-a-generalist-robot#ran","syntology_url":"https://syntology.ai/paper/2412.14803","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14803"}},"official":null}},{"url":"/paper/autoregressive-video-generation-without","slug":"autoregressive-video-generation-without","title":"Autoregressive Video Generation without Vector Quantization","date":"2024-12-18","arxiv_id":"2412.14169","repositories_listed":1,"syntology":{"n":26,"n_ran":19,"n_constructed":18,"n_ran_checked":19,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":19,"n_pointer_only":0,"phrase":"19 ran (of which 18 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/autoregressive-video-generation-without#ran","syntology_url":"https://syntology.ai/paper/2412.14169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.14169"}},"official":{"repos":["baaivision/nova"],"state":"official (archive's flag): 19 ran","n_ran":19,"n_constructed":18,"n_ran_no_instrument_failure":19,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/vidtok-a-versatile-and-open-source-video","slug":"vidtok-a-versatile-and-open-source-video","title":"VidTok: A Versatile and Open-Source Video Tokenizer","date":"2024-12-17","arxiv_id":"2412.13061","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/vidtok-a-versatile-and-open-source-video#ran","syntology_url":"https://syntology.ai/paper/2412.13061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.13061"}},"official":{"repos":["microsoft/vidtok"],"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/doe-1-closed-loop-autonomous-driving-with","slug":"doe-1-closed-loop-autonomous-driving-with","title":"Doe-1: Closed-Loop Autonomous Driving with Large World Model","date":"2024-12-12","arxiv_id":"2412.09627","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"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) · 1 unverified","sample_list":"/paper/doe-1-closed-loop-autonomous-driving-with#ran","syntology_url":"https://syntology.ai/paper/2412.09627","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.09627"}},"official":{"repos":["wzzheng/doe"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/acdit-interpolating-autoregressive","slug":"acdit-interpolating-autoregressive","title":"ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer","date":"2024-12-10","arxiv_id":"2412.07720","repositories_listed":1,"syntology":{"n":6,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"5 ran (of which 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) · 1 unverified","sample_list":"/paper/acdit-interpolating-autoregressive#ran","syntology_url":"https://syntology.ai/paper/2412.07720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07720"}},"official":{"repos":["thunlp/acdit"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/syncammaster-synchronizing-multi-camera-video","slug":"syncammaster-synchronizing-multi-camera-video","title":"SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints","date":"2024-12-10","arxiv_id":"2412.07760","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/syncammaster-synchronizing-multi-camera-video#ran","syntology_url":"https://syntology.ai/paper/2412.07760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07760"}},"official":{"repos":["kwaivgi/syncammaster"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/flexdit-dynamic-token-density-control-for","slug":"flexdit-dynamic-token-density-control-for","title":"FlexDiT: Dynamic Token Density Control for Diffusion Transformer","date":"2024-12-08","arxiv_id":"2412.06028","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":6,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/flexdit-dynamic-token-density-control-for#ran","syntology_url":"https://syntology.ai/paper/2412.06028","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.06028"}},"official":{"repos":["changsn/FlexDiT"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":4,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/stag-1-towards-realistic-4d-driving","slug":"stag-1-towards-realistic-4d-driving","title":"Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Model","date":"2024-12-06","arxiv_id":"2412.05280","repositories_listed":1,"syntology":{"n":9,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":9,"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) · 2 unverified","sample_list":"/paper/stag-1-towards-realistic-4d-driving#ran","syntology_url":"https://syntology.ai/paper/2412.05280","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05280"}},"official":{"repos":["wzzheng/stag"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/videogen-of-thought-a-collaborative-framework","slug":"videogen-of-thought-a-collaborative-framework","title":"VideoGen-of-Thought: A Collaborative Framework for Multi-Shot Video Generation","date":"2024-12-03","arxiv_id":"2412.02259","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/videogen-of-thought-a-collaborative-framework#ran","syntology_url":"https://syntology.ai/paper/2412.02259","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.02259"}},"official":{"repos":["DuNGEOnmassster/VideoGen-of-Thought"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/hunyuanvideo-a-systematic-framework-for-large","slug":"hunyuanvideo-a-systematic-framework-for-large","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","date":"2024-12-03","arxiv_id":"2412.03603","repositories_listed":2,"syntology":{"n":27,"n_ran":18,"n_constructed":6,"n_ran_checked":6,"n_instrument":12,"n_unverified":9,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":27,"phrase":"18 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 12 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/hunyuanvideo-a-systematic-framework-for-large#ran","syntology_url":"https://syntology.ai/paper/2412.03603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.03603"}},"official":{"repos":["tencent/hunyuanvideo"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":6,"n_ran_no_instrument_failure":6,"n_unverified":9,"ran_from_kinds":["listed","official","unlocated"]}}},{"url":"/paper/phyt2v-llm-guided-iterative-self-refinement","slug":"phyt2v-llm-guided-iterative-self-refinement","title":"PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation","date":"2024-11-30","arxiv_id":"2412.00596","repositories_listed":1,"syntology":{"n":16,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":16,"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) · 5 unverified","sample_list":"/paper/phyt2v-llm-guided-iterative-self-refinement#ran","syntology_url":"https://syntology.ai/paper/2412.00596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00596"}},"official":{"repos":["pittisl/phyt2v"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/open-sora-plan-open-source-large-video","slug":"open-sora-plan-open-source-large-video","title":"Open-Sora Plan: Open-Source Large Video Generation Model","date":"2024-11-28","arxiv_id":"2412.00131","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/open-sora-plan-open-source-large-video#ran","syntology_url":"https://syntology.ai/paper/2412.00131","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.00131"}},"official":{"repos":["pku-yuangroup/open-sora-plan"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/accelerating-vision-diffusion-transformers","slug":"accelerating-vision-diffusion-transformers","title":"Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints","date":"2024-11-26","arxiv_id":"2411.17616","repositories_listed":1,"syntology":{"n":10,"n_ran":6,"n_constructed":0,"n_ran_checked":3,"n_instrument":3,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"6 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; 3 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/accelerating-vision-diffusion-transformers#ran","syntology_url":"https://syntology.ai/paper/2411.17616","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17616"}},"official":{"repos":["opensparsellms/skip-dit"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/stableanimator-high-quality-identity","slug":"stableanimator-high-quality-identity","title":"StableAnimator: High-Quality Identity-Preserving Human Image Animation","date":"2024-11-26","arxiv_id":"2411.17697","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/stableanimator-high-quality-identity#ran","syntology_url":"https://syntology.ai/paper/2411.17697","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.17697"}},"official":{"repos":["Francis-Rings/StableAnimator"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/ca2-vdm-efficient-autoregressive-video","slug":"ca2-vdm-efficient-autoregressive-video","title":"Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing","date":"2024-11-25","arxiv_id":"2411.16375","repositories_listed":2,"syntology":{"n":21,"n_ran":15,"n_constructed":5,"n_ran_checked":13,"n_instrument":2,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":13,"n_pointer_only":5,"phrase":"15 ran (of which 5 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/ca2-vdm-efficient-autoregressive-video#ran","syntology_url":"https://syntology.ai/paper/2411.16375","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16375"}},"official":{"repos":["dawn-lx/causalcache-vdm"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text","listed"]}}},{"url":"/paper/moviebench-a-hierarchical-movie-level-dataset","slug":"moviebench-a-hierarchical-movie-level-dataset","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","date":"2024-11-22","arxiv_id":"2411.15262","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_constructed":0,"n_ran_checked":11,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":14,"phrase":"13 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; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/moviebench-a-hierarchical-movie-level-dataset#ran","syntology_url":"https://syntology.ai/paper/2411.15262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.15262"}},"official":{"repos":["showlab/moviebecnh"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/taq-dit-time-aware-quantization-for-diffusion","slug":"taq-dit-time-aware-quantization-for-diffusion","title":"TaQ-DiT: Time-aware Quantization for Diffusion Transformers","date":"2024-11-21","arxiv_id":"2411.14172","repositories_listed":0,"syntology":{"n":7,"n_ran":5,"n_constructed":2,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/taq-dit-time-aware-quantization-for-diffusion#ran","syntology_url":"https://syntology.ai/paper/2411.14172","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14172"}},"official":null}},{"url":"/paper/stereocrafter-zero-zero-shot-stereo-video","slug":"stereocrafter-zero-zero-shot-stereo-video","title":"StereoCrafter-Zero: Zero-Shot Stereo Video Generation with Noisy Restart","date":"2024-11-21","arxiv_id":"2411.14295","repositories_listed":1,"syntology":{"n":16,"n_ran":12,"n_constructed":0,"n_ran_checked":8,"n_instrument":4,"n_unverified":4,"n_honours":1,"n_violates":3,"n_no_contract":4,"n_pointer_only":16,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 3 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/stereocrafter-zero-zero-shot-stereo-video#ran","syntology_url":"https://syntology.ai/paper/2411.14295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.14295"}},"official":{"repos":["shijianjian/stereocrafter-zero"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/reducio-generating-1024-times-1024-video","slug":"reducio-generating-1024-times-1024-video","title":"REDUCIO! Generating 1024$\\times$1024 Video within 16 Seconds using Extremely Compressed Motion Latents","date":"2024-11-20","arxiv_id":"2411.13552","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/reducio-generating-1024-times-1024-video#ran","syntology_url":"https://syntology.ai/paper/2411.13552","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.13552"}},"official":{"repos":["microsoft/reducio-vae"],"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/echomimicv2-towards-striking-simplified-and","slug":"echomimicv2-towards-striking-simplified-and","title":"EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation","date":"2024-11-15","arxiv_id":"2411.10061","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"4 ran (of which 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) · 1 unverified","sample_list":"/paper/echomimicv2-towards-striking-simplified-and#ran","syntology_url":"https://syntology.ai/paper/2411.10061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.10061"}},"official":{"repos":["antgroup/echomimic_v2"],"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"]}}},{"url":"/paper/taming-rectified-flow-for-inversion-and","slug":"taming-rectified-flow-for-inversion-and","title":"Taming Rectified Flow for Inversion and Editing","date":"2024-11-07","arxiv_id":"2411.04746","repositories_listed":1,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":10,"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) · 7 unverified","sample_list":"/paper/taming-rectified-flow-for-inversion-and#ran","syntology_url":"https://syntology.ai/paper/2411.04746","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04746"}},"official":{"repos":["wangjiangshan0725/rf-solver-edit"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/mvsplat360-feed-forward-360-scene-synthesis","slug":"mvsplat360-feed-forward-360-scene-synthesis","title":"MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views","date":"2024-11-07","arxiv_id":"2411.04924","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/mvsplat360-feed-forward-360-scene-synthesis#ran","syntology_url":"https://syntology.ai/paper/2411.04924","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.04924"}},"official":{"repos":["donydchen/mvsplat360"],"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/enhancing-motion-in-text-to-video-generation","slug":"enhancing-motion-in-text-to-video-generation","title":"Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning","date":"2024-10-31","arxiv_id":"2410.24219","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":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) · 4 unverified","sample_list":"/paper/enhancing-motion-in-text-to-video-generation#ran","syntology_url":"https://syntology.ai/paper/2410.24219","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.24219"}},"official":{"repos":["pr-ryan/demo"],"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/larp-tokenizing-videos-with-a-learned-1","slug":"larp-tokenizing-videos-with-a-learned-1","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","date":"2024-10-28","arxiv_id":"2410.21264","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":7,"n_pointer_only":2,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/larp-tokenizing-videos-with-a-learned-1#ran","syntology_url":"https://syntology.ai/paper/2410.21264","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.21264"}},"official":null}},{"url":"/paper/robust-watermarking-using-generative-priors","slug":"robust-watermarking-using-generative-priors","title":"Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances","date":"2024-10-24","arxiv_id":"2410.18775","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/robust-watermarking-using-generative-priors#ran","syntology_url":"https://syntology.ai/paper/2410.18775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.18775"}},"official":{"repos":["shilin-lu/vine"],"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/allegro-open-the-black-box-of-commercial","slug":"allegro-open-the-black-box-of-commercial","title":"Allegro: Open the Black Box of Commercial-Level Video Generation Model","date":"2024-10-20","arxiv_id":"2410.15458","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/allegro-open-the-black-box-of-commercial#ran","syntology_url":"https://syntology.ai/paper/2410.15458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.15458"}},"official":{"repos":["rhymes-ai/allegro"],"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/videoagent-self-improving-video-generation","slug":"videoagent-self-improving-video-generation","title":"VideoAgent: Self-Improving Video Generation","date":"2024-10-14","arxiv_id":"2410.10076","repositories_listed":1,"syntology":{"n":14,"n_ran":12,"n_constructed":0,"n_ran_checked":11,"n_instrument":1,"n_unverified":2,"n_honours":1,"n_violates":4,"n_no_contract":6,"n_pointer_only":2,"phrase":"12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 4 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/videoagent-self-improving-video-generation#ran","syntology_url":"https://syntology.ai/paper/2410.10076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10076"}},"official":{"repos":["video-as-agent/videoagent"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/musetalk-real-time-high-quality-lip","slug":"musetalk-real-time-high-quality-lip","title":"MuseTalk: Real-Time High-Fidelity Video Dubbing via Spatio-Temporal Sampling","date":"2024-10-14","arxiv_id":"2410.10122","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":6,"n_pointer_only":8,"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) · 1 unverified","sample_list":"/paper/musetalk-real-time-high-quality-lip#ran","syntology_url":"https://syntology.ai/paper/2410.10122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10122"}},"official":{"repos":["tmelyralab/musetalk"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/lvd-2m-a-long-take-video-dataset-with","slug":"lvd-2m-a-long-take-video-dataset-with","title":"LVD-2M: A Long-take Video Dataset with Temporally Dense Captions","date":"2024-10-14","arxiv_id":"2410.10816","repositories_listed":1,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":6,"n_instrument":1,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lvd-2m-a-long-take-video-dataset-with#ran","syntology_url":"https://syntology.ai/paper/2410.10816","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10816"}},"official":{"repos":["silentview/lvd-2m"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/motionaura-generating-high-quality-and-motion","slug":"motionaura-generating-high-quality-and-motion","title":"MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion","date":"2024-10-10","arxiv_id":"2410.07659","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/motionaura-generating-high-quality-and-motion#ran","syntology_url":"https://syntology.ai/paper/2410.07659","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07659"}},"official":{"repos":["CandleLabAI/MotionAura-ICLR-2025"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/hallo2-long-duration-and-high-resolution","slug":"hallo2-long-duration-and-high-resolution","title":"Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation","date":"2024-10-10","arxiv_id":"2410.07718","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_constructed":0,"n_ran_checked":7,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":1,"phrase":"8 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; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/hallo2-long-duration-and-high-resolution#ran","syntology_url":"https://syntology.ai/paper/2410.07718","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07718"}},"official":{"repos":["fudan-generative-vision/hallo2"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/progressive-autoregressive-video-diffusion","slug":"progressive-autoregressive-video-diffusion","title":"Progressive Autoregressive Video Diffusion Models","date":"2024-10-10","arxiv_id":"2410.08151","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":2,"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/progressive-autoregressive-video-diffusion#ran","syntology_url":"https://syntology.ai/paper/2410.08151","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08151"}},"official":{"repos":["desaixie/pa_vdm"],"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/trans4d-realistic-geometry-aware-transition","slug":"trans4d-realistic-geometry-aware-transition","title":"Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis","date":"2024-10-09","arxiv_id":"2410.07155","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":8,"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) · 1 unverified","sample_list":"/paper/trans4d-realistic-geometry-aware-transition#ran","syntology_url":"https://syntology.ai/paper/2410.07155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07155"}},"official":{"repos":["yangling0818/trans4d"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tweediemix-improving-multi-concept-fusion-for","slug":"tweediemix-improving-multi-concept-fusion-for","title":"TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation","date":"2024-10-08","arxiv_id":"2410.05591","repositories_listed":1,"syntology":{"n":11,"n_ran":5,"n_constructed":0,"n_ran_checked":4,"n_instrument":1,"n_unverified":6,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":11,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/tweediemix-improving-multi-concept-fusion-for#ran","syntology_url":"https://syntology.ai/paper/2410.05591","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05591"}},"official":{"repos":["kwongihyun/tweediemix"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/t2v-turbo-v2-enhancing-video-generation-model","slug":"t2v-turbo-v2-enhancing-video-generation-model","title":"T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design","date":"2024-10-08","arxiv_id":"2410.05677","repositories_listed":1,"syntology":{"n":8,"n_ran":8,"n_constructed":0,"n_ran_checked":6,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":5,"n_pointer_only":8,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/t2v-turbo-v2-enhancing-video-generation-model#ran","syntology_url":"https://syntology.ai/paper/2410.05677","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05677"}},"official":null}},{"url":"/paper/pyramidal-flow-matching-for-efficient-video","slug":"pyramidal-flow-matching-for-efficient-video","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","date":"2024-10-08","arxiv_id":"2410.05954","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":2,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result","sample_list":"/paper/pyramidal-flow-matching-for-efficient-video#ran","syntology_url":"https://syntology.ai/paper/2410.05954","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05954"}},"official":{"repos":["jy0205/Pyramid-Flow"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-world-simulator-crafting-physical","slug":"towards-world-simulator-crafting-physical","title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","date":"2024-10-07","arxiv_id":"2410.05363","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":10,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":1,"n_no_contract":9,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/towards-world-simulator-crafting-physical#ran","syntology_url":"https://syntology.ai/paper/2410.05363","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05363"}},"official":{"repos":["opengvlab/phygenbench"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/accelerating-diffusion-transformers-with","slug":"accelerating-diffusion-transformers-with","title":"Accelerating Diffusion Transformers with Token-wise Feature Caching","date":"2024-10-05","arxiv_id":"2410.05317","repositories_listed":2,"syntology":{"n":13,"n_ran":10,"n_constructed":0,"n_ran_checked":6,"n_instrument":4,"n_unverified":3,"n_honours":5,"n_violates":1,"n_no_contract":0,"n_pointer_only":13,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 5 honoured, 1 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/accelerating-diffusion-transformers-with#ran","syntology_url":"https://syntology.ai/paper/2410.05317","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05317"}},"official":{"repos":["Shenyi-Z/ToCa"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/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/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/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/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/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"]}}}],"record_sha256":"9b5699e46b140ef34e364e765261615f8e1a5a831c344aeed75b39eab80e2de4","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}