{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LFBL7LP6PZXNDQT3VS75XECXOX","short_pith_number":"pith:LFBL7LP6","schema_version":"1.0","canonical_sha256":"5942bfadfe7e6ed1c27bacbfdb905775c69e11196a024cabae39a4cdea6a17d7","source":{"kind":"arxiv","id":"2503.19824","version":1},"attestation_state":"computed","paper":{"title":"AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Borong Liang, Errui Ding, Hang Zhou, Haocheng Feng, Jiazhi Guan, Jingdong Wang, Kaisiyuan Wang, Quanwei Yang, Shengyi He, Yasheng Sun, Yingying Li, Youjian Zhao, Yukang Cao, Zhiliang Xu, Ziwei Liu","submitted_at":"2025-03-25T16:38:23Z","abstract_excerpt":"Despite the recent progress of audio-driven video generation, existing methods mostly focus on driving facial movements, leading to non-coherent head and body dynamics. Moving forward, it is desirable yet challenging to generate holistic human videos with both accurate lip-sync and delicate co-speech gestures w.r.t. given audio. In this work, we propose AudCast, a generalized audio-driven human video generation framework adopting a cascade Diffusion-Transformers (DiTs) paradigm, which synthesizes holistic human videos based on a reference image and a given audio. 1) Firstly, an audio-condition"},"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":"2503.19824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:38:23Z","cross_cats_sorted":["cs.GR","cs.MM"],"title_canon_sha256":"a2235bfd78ac8966ca0366923635b5a9c1e0c3ff70b11207520b9738451da9cc","abstract_canon_sha256":"8ac7676c32cb3ed6a8f8d864b867bf9056d4b9209899b7810b89f51db2690020"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:19.730255Z","signature_b64":"sOBrx+bPusi0ZNKAK1jGLq/6CYXoIWQcmNGJoaFHzl3aA32RK8f21MPldZ1cKYrKgeCAZ0KNfyFoxfHmozK2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5942bfadfe7e6ed1c27bacbfdb905775c69e11196a024cabae39a4cdea6a17d7","last_reissued_at":"2026-07-05T11:18:19.729691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:19.729691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.MM"],"primary_cat":"cs.CV","authors_text":"Borong Liang, Errui Ding, Hang Zhou, Haocheng Feng, Jiazhi Guan, Jingdong Wang, Kaisiyuan Wang, Quanwei Yang, Shengyi He, Yasheng Sun, Yingying Li, Youjian Zhao, Yukang Cao, Zhiliang Xu, Ziwei Liu","submitted_at":"2025-03-25T16:38:23Z","abstract_excerpt":"Despite the recent progress of audio-driven video generation, existing methods mostly focus on driving facial movements, leading to non-coherent head and body dynamics. Moving forward, it is desirable yet challenging to generate holistic human videos with both accurate lip-sync and delicate co-speech gestures w.r.t. given audio. In this work, we propose AudCast, a generalized audio-driven human video generation framework adopting a cascade Diffusion-Transformers (DiTs) paradigm, which synthesizes holistic human videos based on a reference image and a given audio. 1) Firstly, an audio-condition"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19824","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/2503.19824/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":"2503.19824","created_at":"2026-07-05T11:18:19.729770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19824v1","created_at":"2026-07-05T11:18:19.729770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19824","created_at":"2026-07-05T11:18:19.729770+00:00"},{"alias_kind":"pith_short_12","alias_value":"LFBL7LP6PZXN","created_at":"2026-07-05T11:18:19.729770+00:00"},{"alias_kind":"pith_short_16","alias_value":"LFBL7LP6PZXNDQT3","created_at":"2026-07-05T11:18:19.729770+00:00"},{"alias_kind":"pith_short_8","alias_value":"LFBL7LP6","created_at":"2026-07-05T11:18:19.729770+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX","json":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX.json","graph_json":"https://pith.science/api/pith-number/LFBL7LP6PZXNDQT3VS75XECXOX/graph.json","events_json":"https://pith.science/api/pith-number/LFBL7LP6PZXNDQT3VS75XECXOX/events.json","paper":"https://pith.science/paper/LFBL7LP6"},"agent_actions":{"view_html":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX","download_json":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX.json","view_paper":"https://pith.science/paper/LFBL7LP6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19824&json=true","fetch_graph":"https://pith.science/api/pith-number/LFBL7LP6PZXNDQT3VS75XECXOX/graph.json","fetch_events":"https://pith.science/api/pith-number/LFBL7LP6PZXNDQT3VS75XECXOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX/action/storage_attestation","attest_author":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX/action/author_attestation","sign_citation":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX/action/citation_signature","submit_replication":"https://pith.science/pith/LFBL7LP6PZXNDQT3VS75XECXOX/action/replication_record"}},"created_at":"2026-07-05T11:18:19.729770+00:00","updated_at":"2026-07-05T11:18:19.729770+00:00"}