{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UCFL54T5TYCJIGF4EG4OUKZIID","short_pith_number":"pith:UCFL54T5","schema_version":"1.0","canonical_sha256":"a08abef27d9e049418bc21b8ea2b2840fd028bb99319803a1c9b926dadbd5add","source":{"kind":"arxiv","id":"2507.12898","version":4},"attestation_state":"computed","paper":{"title":"Vidar: Embodied Video Diffusion Model for Generalist Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A video diffusion model pre-trained on internet-scale data and 750K robot trajectories adapts to new robot embodiments with only 20 minutes of demonstrations.","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chendong Xiang, Guodong Liu, Hang Su, Hengkai Tan, Jun Zhu, Shuhe Huang, Xinyi Mao, Yao Feng","submitted_at":"2025-07-17T08:31:55Z","abstract_excerpt":"Scaling general-purpose manipulation to new robot embodiments remains challenging: each platform typically needs large, homogeneous demonstrations, and end-to-end pixel-to-action pipelines may degenerate under background and viewpoint shifts. Based on previous advances in video-based robot control, we present Vidar, consisting of an embodied video diffusion model as the generalizable prior and a masked inverse dynamics model (MIDM) as the adapter. We leverage a video diffusion model pre-trained at Internet scale, and further continuously pre-train it for the embodied domain using 750K multi-vi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2507.12898","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T08:31:55Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO"],"title_canon_sha256":"fa3c128f8b8583963347041a1d34688c91ca0ea5ec73addaaa8e286d2aaa09b0","abstract_canon_sha256":"b93945cdd00928251a5e5d498e11d02981f54dfc1915fba1b499718dfc9f733a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:48.276091Z","signature_b64":"F3/z76/qDuG/SfZcfBA5bw0VZyNt8m+LtcCH4IRt7VQkXXXR5L+vhBUSP9NCMyn3ACDAJ9y55Lxs0umT88bFBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a08abef27d9e049418bc21b8ea2b2840fd028bb99319803a1c9b926dadbd5add","last_reissued_at":"2026-05-17T23:38:48.275613Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:48.275613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vidar: Embodied Video Diffusion Model for Generalist Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A video diffusion model pre-trained on internet-scale data and 750K robot trajectories adapts to new robot embodiments with only 20 minutes of demonstrations.","cross_cats":["cs.AI","cs.CV","cs.RO"],"primary_cat":"cs.LG","authors_text":"Chendong Xiang, Guodong Liu, Hang Su, Hengkai Tan, Jun Zhu, Shuhe Huang, Xinyi Mao, Yao Feng","submitted_at":"2025-07-17T08:31:55Z","abstract_excerpt":"Scaling general-purpose manipulation to new robot embodiments remains challenging: each platform typically needs large, homogeneous demonstrations, and end-to-end pixel-to-action pipelines may degenerate under background and viewpoint shifts. Based on previous advances in video-based robot control, we present Vidar, consisting of an embodied video diffusion model as the generalizable prior and a masked inverse dynamics model (MIDM) as the adapter. We leverage a video diffusion model pre-trained at Internet scale, and further continuously pre-train it for the embodied domain using 750K multi-vi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"With only 20 minutes of human demonstrations on an unseen robot (1% of typical data), Vidar outperforms state-of-the-art baselines and generalizes to unseen tasks, backgrounds, and camera layouts.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That continuous pre-training of an internet-scale video diffusion model on 750K trajectories from only three robot platforms produces a sufficiently general visual-dynamics prior that can be grounded to arbitrary new embodiments via a lightweight masked inverse dynamics adapter.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Vidar shows that a video diffusion prior continuously pre-trained on 750K multi-view robot trajectories plus a label-free masked inverse dynamics adapter can generalize manipulation to new robot embodiments with 1% of typical demonstration data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A video diffusion model pre-trained on internet-scale data and 750K robot trajectories adapts to new robot embodiments with only 20 minutes of demonstrations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c0533665f2f93f4230fdbfa435f80abef7506b75c76ee93708999befbbe66809"},"source":{"id":"2507.12898","kind":"arxiv","version":4},"verdict":{"id":"47d47346-9e8c-4074-9134-099faeccb479","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T09:50:48.324061Z","strongest_claim":"With only 20 minutes of human demonstrations on an unseen robot (1% of typical data), Vidar outperforms state-of-the-art baselines and generalizes to unseen tasks, backgrounds, and camera layouts.","one_line_summary":"Vidar shows that a video diffusion prior continuously pre-trained on 750K multi-view robot trajectories plus a label-free masked inverse dynamics adapter can generalize manipulation to new robot embodiments with 1% of typical demonstration data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That continuous pre-training of an internet-scale video diffusion model on 750K trajectories from only three robot platforms produces a sufficiently general visual-dynamics prior that can be grounded to arbitrary new embodiments via a lightweight masked inverse dynamics adapter.","pith_extraction_headline":"A video diffusion model pre-trained on internet-scale data and 750K robot trajectories adapts to new robot embodiments with only 20 minutes of demonstrations."},"references":{"count":46,"sample":[{"doi":"","year":2024,"title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration","work_id":"5e1215f6-254f-4463-b555-ef06efc0e71d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"OpenVLA: An Open-Source Vision-Language-Action Model","work_id":"c58a80f3-556e-4070-8e8e-8969c4f0a263","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","work_id":"12319725-bc7d-4c32-a229-ad270a7460bc","ref_index":3,"cited_arxiv_id":"2410.07864","is_internal_anchor":true},{"doi":"","year":2023,"title":"Crossformer: Transformer Utilizing Cross-Dimension Depen- dency for Multivariate Time Series Forecasting","work_id":"fbe803e5-9aa0-4f94-8c82-4c3eab7b9890","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","work_id":"d1ad7304-d09a-49bc-809e-846439f6aff9","ref_index":5,"cited_arxiv_id":"2504.16054","is_internal_anchor":true}],"resolved_work":46,"snapshot_sha256":"45cd919227676cd242ef839aeb74f4319d3c288045301f80474c8cf998cff2fc","internal_anchors":20},"formal_canon":{"evidence_count":1,"snapshot_sha256":"836e78ec6461bff8a138f46abccd699d4b599eb8df19712fe6821ad38c1f73dc"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.12898","created_at":"2026-05-17T23:38:48.275692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12898v4","created_at":"2026-05-17T23:38:48.275692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12898","created_at":"2026-05-17T23:38:48.275692+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCFL54T5TYCJ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCFL54T5TYCJIGF4","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCFL54T5","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":19,"sample":[{"citing_arxiv_id":"2605.17912","citing_title":"WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2601.23286","citing_title":"VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2510.10125","citing_title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2603.09030","citing_title":"PlayWorld: Learning Robot World Models from Autonomous Play","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14274","citing_title":"CreFlow: Corrective Reflow for Sparse-Reward Embodied Video Diffusion RL","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2603.16666","citing_title":"Fast-WAM: Do World Action Models Need Test-time Future Imagination?","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":197,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"2512.13030","citing_title":"Motus: A Unified Latent Action World Model","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2601.16163","citing_title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21998","citing_title":"Causal World Modeling for Robot Control","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27792","citing_title":"MotuBrain: An Advanced World Action Model for Robot Control","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10942","citing_title":"HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06247","citing_title":"CKT-WAM: Parameter-Efficient Context Knowledge Transfer Between World Action Models","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00080","citing_title":"World Model for Robot Learning: A Comprehensive Survey","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00078","citing_title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04502","citing_title":"Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17887","citing_title":"StableIDM: Stabilizing Inverse Dynamics Model against Manipulator Truncation via Spatio-Temporal Refinement","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20841","citing_title":"DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UCFL54T5TYCJIGF4EG4OUKZIID","json":"https://pith.science/pith/UCFL54T5TYCJIGF4EG4OUKZIID.json","graph_json":"https://pith.science/api/pith-number/UCFL54T5TYCJIGF4EG4OUKZIID/graph.json","events_json":"https://pith.science/api/pith-number/UCFL54T5TYCJIGF4EG4OUKZIID/events.json","paper":"https://pith.science/paper/UCFL54T5"},"agent_actions":{"view_html":"https://pith.science/pith/UCFL54T5TYCJIGF4EG4OUKZIID","download_json":"https://pith.science/pith/UCFL54T5TYCJIGF4EG4OUKZIID.json","view_paper":"https://pith.science/paper/UCFL54T5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12898&json=true","fetch_graph":"https://pith.science/api/pith-number/UCFL54T5TYCJIGF4EG4OUKZIID/graph.json","fetch_events":"https://pith.science/api/pith-number/UCFL54T5TYCJIGF4EG4OUKZIID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCFL54T5TYCJIGF4EG4OUKZIID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCFL54T5TYCJIGF4EG4OUKZIID/action/storage_attestation","attest_author":"https://pith.science/pith/UCFL54T5TYCJIGF4EG4OUKZIID/action/author_attestation","sign_citation":"https://pith.science/pith/UCFL54T5TYCJIGF4EG4OUKZIID/action/citation_signature","submit_replication":"https://pith.science/pith/UCFL54T5TYCJIGF4EG4OUKZIID/action/replication_record"}},"created_at":"2026-05-17T23:38:48.275692+00:00","updated_at":"2026-05-17T23:38:48.275692+00:00"}