{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3QX34H7OANANN72OQG5LK3J2AC","short_pith_number":"pith:3QX34H7O","schema_version":"1.0","canonical_sha256":"dc2fbe1fee0340d6ff4e81bab56d3a0092c70bc3a1de28dc0547cc76f2571115","source":{"kind":"arxiv","id":"2412.05899","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Video Diffusion Models via Distribution Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanshu Yan, Huan Yang, Junnan Li, Kai Zhang, Yuanzhi Zhu","submitted_at":"2024-12-08T11:36:32Z","abstract_excerpt":"Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often requiring numerous sampling steps that limit their practical application, especially in video generation. This work introduces a novel framework for diffusion distillation and distribution matching that dramatically reduces the number of inference steps while maintaining-and potentially improving-generation quality. Our approach focuses on distilling pre-traine"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.05899","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T11:36:32Z","cross_cats_sorted":[],"title_canon_sha256":"ff0cde8ad5edcb7018b3131935cce59a2ebc7b174737b471b73369965cbeed3c","abstract_canon_sha256":"c386399a9afb4a76f248c85861c6161b095c0aabdfe0dc0244d98937dd2f711d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:11.371355Z","signature_b64":"+FpSFuT18wSQf8KDozsLJV7IkWT1DdX6/63kN8J73rF9ECxIvJQ8/36OeFRzJgDyoSyyAh4IEo8kShsqNWXSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc2fbe1fee0340d6ff4e81bab56d3a0092c70bc3a1de28dc0547cc76f2571115","last_reissued_at":"2026-07-05T09:46:11.370892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:11.370892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Video Diffusion Models via Distribution Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hanshu Yan, Huan Yang, Junnan Li, Kai Zhang, Yuanzhi Zhu","submitted_at":"2024-12-08T11:36:32Z","abstract_excerpt":"Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often requiring numerous sampling steps that limit their practical application, especially in video generation. This work introduces a novel framework for diffusion distillation and distribution matching that dramatically reduces the number of inference steps while maintaining-and potentially improving-generation quality. Our approach focuses on distilling pre-traine"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05899","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.05899/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"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":"2412.05899","created_at":"2026-07-05T09:46:11.370949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05899v1","created_at":"2026-07-05T09:46:11.370949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05899","created_at":"2026-07-05T09:46:11.370949+00:00"},{"alias_kind":"pith_short_12","alias_value":"3QX34H7OANAN","created_at":"2026-07-05T09:46:11.370949+00:00"},{"alias_kind":"pith_short_16","alias_value":"3QX34H7OANANN72O","created_at":"2026-07-05T09:46:11.370949+00:00"},{"alias_kind":"pith_short_8","alias_value":"3QX34H7O","created_at":"2026-07-05T09:46:11.370949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.09981","citing_title":"ReSim: Reliable World Simulation for Autonomous Driving","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15911","citing_title":"Efficient Video Diffusion Models: Advancements and Challenges","ref_index":203,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3QX34H7OANANN72OQG5LK3J2AC","json":"https://pith.science/pith/3QX34H7OANANN72OQG5LK3J2AC.json","graph_json":"https://pith.science/api/pith-number/3QX34H7OANANN72OQG5LK3J2AC/graph.json","events_json":"https://pith.science/api/pith-number/3QX34H7OANANN72OQG5LK3J2AC/events.json","paper":"https://pith.science/paper/3QX34H7O"},"agent_actions":{"view_html":"https://pith.science/pith/3QX34H7OANANN72OQG5LK3J2AC","download_json":"https://pith.science/pith/3QX34H7OANANN72OQG5LK3J2AC.json","view_paper":"https://pith.science/paper/3QX34H7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05899&json=true","fetch_graph":"https://pith.science/api/pith-number/3QX34H7OANANN72OQG5LK3J2AC/graph.json","fetch_events":"https://pith.science/api/pith-number/3QX34H7OANANN72OQG5LK3J2AC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3QX34H7OANANN72OQG5LK3J2AC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3QX34H7OANANN72OQG5LK3J2AC/action/storage_attestation","attest_author":"https://pith.science/pith/3QX34H7OANANN72OQG5LK3J2AC/action/author_attestation","sign_citation":"https://pith.science/pith/3QX34H7OANANN72OQG5LK3J2AC/action/citation_signature","submit_replication":"https://pith.science/pith/3QX34H7OANANN72OQG5LK3J2AC/action/replication_record"}},"created_at":"2026-07-05T09:46:11.370949+00:00","updated_at":"2026-07-05T09:46:11.370949+00:00"}