{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JIAFUH4ZBLLR6EM64ZIC4KMAU5","short_pith_number":"pith:JIAFUH4Z","schema_version":"1.0","canonical_sha256":"4a005a1f990ad71f119ee6502e2980a75e2624693ce8def7ad10fd9c0ae7e880","source":{"kind":"arxiv","id":"2506.05806","version":1},"attestation_state":"computed","paper":{"title":"LLIA -- Enabling Low-Latency Interactive Avatars: Real-Time Audio-Driven Portrait Video Generation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Wang, Haojie Yu, Hao Yang, Meng Cheng, Tao Xie, Xiaoming Wei, Xiaoming Xu, Xunliang Cai, Yihan Pan, Zhaonian Wang","submitted_at":"2025-06-06T07:09:07Z","abstract_excerpt":"Diffusion-based models have gained wide adoption in the virtual human generation due to their outstanding expressiveness. However, their substantial computational requirements have constrained their deployment in real-time interactive avatar applications, where stringent speed, latency, and duration requirements are paramount. We present a novel audio-driven portrait video generation framework based on the diffusion model to address these challenges. Firstly, we propose robust variable-length video generation to reduce the minimum time required to generate the initial video clip or state trans"},"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":"2506.05806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T07:09:07Z","cross_cats_sorted":[],"title_canon_sha256":"ccbe11a8c7d01f80ca140710955fe87c1a50613236d7949569d1fe6e7bebd7ff","abstract_canon_sha256":"86b0e494ac5ef12cea6f1d72a05a6728c6bc166425255112259ef230b2d2b8a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:10.286887Z","signature_b64":"LVGP9Bizk/UdR/zJ7ocBIQBAQtVvmXgIVi6pyawwDbr3GU+jbc3gND8SRE7pEOR2U98UMwxjjWu36LmZ24f8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a005a1f990ad71f119ee6502e2980a75e2624693ce8def7ad10fd9c0ae7e880","last_reissued_at":"2026-07-05T11:17:10.286224Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:10.286224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLIA -- Enabling Low-Latency Interactive Avatars: Real-Time Audio-Driven Portrait Video Generation with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Wang, Haojie Yu, Hao Yang, Meng Cheng, Tao Xie, Xiaoming Wei, Xiaoming Xu, Xunliang Cai, Yihan Pan, Zhaonian Wang","submitted_at":"2025-06-06T07:09:07Z","abstract_excerpt":"Diffusion-based models have gained wide adoption in the virtual human generation due to their outstanding expressiveness. However, their substantial computational requirements have constrained their deployment in real-time interactive avatar applications, where stringent speed, latency, and duration requirements are paramount. We present a novel audio-driven portrait video generation framework based on the diffusion model to address these challenges. Firstly, we propose robust variable-length video generation to reduce the minimum time required to generate the initial video clip or state trans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05806","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/2506.05806/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":"2506.05806","created_at":"2026-07-05T11:17:10.286296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05806v1","created_at":"2026-07-05T11:17:10.286296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05806","created_at":"2026-07-05T11:17:10.286296+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIAFUH4ZBLLR","created_at":"2026-07-05T11:17:10.286296+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIAFUH4ZBLLR6EM6","created_at":"2026-07-05T11:17:10.286296+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIAFUH4Z","created_at":"2026-07-05T11:17:10.286296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.04677","citing_title":"Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JIAFUH4ZBLLR6EM64ZIC4KMAU5","json":"https://pith.science/pith/JIAFUH4ZBLLR6EM64ZIC4KMAU5.json","graph_json":"https://pith.science/api/pith-number/JIAFUH4ZBLLR6EM64ZIC4KMAU5/graph.json","events_json":"https://pith.science/api/pith-number/JIAFUH4ZBLLR6EM64ZIC4KMAU5/events.json","paper":"https://pith.science/paper/JIAFUH4Z"},"agent_actions":{"view_html":"https://pith.science/pith/JIAFUH4ZBLLR6EM64ZIC4KMAU5","download_json":"https://pith.science/pith/JIAFUH4ZBLLR6EM64ZIC4KMAU5.json","view_paper":"https://pith.science/paper/JIAFUH4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05806&json=true","fetch_graph":"https://pith.science/api/pith-number/JIAFUH4ZBLLR6EM64ZIC4KMAU5/graph.json","fetch_events":"https://pith.science/api/pith-number/JIAFUH4ZBLLR6EM64ZIC4KMAU5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIAFUH4ZBLLR6EM64ZIC4KMAU5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIAFUH4ZBLLR6EM64ZIC4KMAU5/action/storage_attestation","attest_author":"https://pith.science/pith/JIAFUH4ZBLLR6EM64ZIC4KMAU5/action/author_attestation","sign_citation":"https://pith.science/pith/JIAFUH4ZBLLR6EM64ZIC4KMAU5/action/citation_signature","submit_replication":"https://pith.science/pith/JIAFUH4ZBLLR6EM64ZIC4KMAU5/action/replication_record"}},"created_at":"2026-07-05T11:17:10.286296+00:00","updated_at":"2026-07-05T11:17:10.286296+00:00"}