{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CFCG6HREL4VKBQSAQEDGDKCA6C","short_pith_number":"pith:CFCG6HRE","schema_version":"1.0","canonical_sha256":"11446f1e245f2aa0c240810661a840f08cb4baf6713c36244947d1c195de3a6b","source":{"kind":"arxiv","id":"2507.18649","version":1},"attestation_state":"computed","paper":{"title":"Livatar-1: Real-Time Talking Heads Generation with Tailored Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiyang Liu, Hongwei Yi, Michael Lingelbach, Wei Li, Xiang Lian, Xiaolin Hong, Xuancheng Yang, Yudi Ruan","submitted_at":"2025-07-22T01:02:29Z","abstract_excerpt":"We present Livatar, a real-time audio-driven talking heads videos generation framework. Existing baselines suffer from limited lip-sync accuracy and long-term pose drift. We address these limitations with a flow matching based framework. Coupled with system optimizations, Livatar achieves competitive lip-sync quality with a 8.50 LipSync Confidence on the HDTF dataset, and reaches a throughput of 141 FPS with an end-to-end latency of 0.17s on a single A10 GPU. This makes high-fidelity avatars accessible to broader applications. Our project is available at https://www.hedra.com/ with with exampl"},"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":"2507.18649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-22T01:02:29Z","cross_cats_sorted":[],"title_canon_sha256":"38dbd8fb1beff6f80b74ba5b334a0aee1b4a00f28191152a1025c61863421851","abstract_canon_sha256":"ec3a758fb05f05c503ea3543d361707461cd15ba42a4304c085fd1ea266e7f13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:55.905011Z","signature_b64":"jdQdwMhwneZdeAW8HQk53p6H6gvftdS5rnPlkjiwOtAyCTJ/c694ZxrSmxhx+jiFU0jwWNRJGrttmtjyA5JQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11446f1e245f2aa0c240810661a840f08cb4baf6713c36244947d1c195de3a6b","last_reissued_at":"2026-07-05T11:42:55.904536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:55.904536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Livatar-1: Real-Time Talking Heads Generation with Tailored Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haiyang Liu, Hongwei Yi, Michael Lingelbach, Wei Li, Xiang Lian, Xiaolin Hong, Xuancheng Yang, Yudi Ruan","submitted_at":"2025-07-22T01:02:29Z","abstract_excerpt":"We present Livatar, a real-time audio-driven talking heads videos generation framework. Existing baselines suffer from limited lip-sync accuracy and long-term pose drift. We address these limitations with a flow matching based framework. Coupled with system optimizations, Livatar achieves competitive lip-sync quality with a 8.50 LipSync Confidence on the HDTF dataset, and reaches a throughput of 141 FPS with an end-to-end latency of 0.17s on a single A10 GPU. This makes high-fidelity avatars accessible to broader applications. Our project is available at https://www.hedra.com/ with with exampl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18649","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/2507.18649/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":"2507.18649","created_at":"2026-07-05T11:42:55.904593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18649v1","created_at":"2026-07-05T11:42:55.904593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18649","created_at":"2026-07-05T11:42:55.904593+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFCG6HREL4VK","created_at":"2026-07-05T11:42:55.904593+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFCG6HREL4VKBQSA","created_at":"2026-07-05T11:42:55.904593+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFCG6HRE","created_at":"2026-07-05T11:42:55.904593+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/CFCG6HREL4VKBQSAQEDGDKCA6C","json":"https://pith.science/pith/CFCG6HREL4VKBQSAQEDGDKCA6C.json","graph_json":"https://pith.science/api/pith-number/CFCG6HREL4VKBQSAQEDGDKCA6C/graph.json","events_json":"https://pith.science/api/pith-number/CFCG6HREL4VKBQSAQEDGDKCA6C/events.json","paper":"https://pith.science/paper/CFCG6HRE"},"agent_actions":{"view_html":"https://pith.science/pith/CFCG6HREL4VKBQSAQEDGDKCA6C","download_json":"https://pith.science/pith/CFCG6HREL4VKBQSAQEDGDKCA6C.json","view_paper":"https://pith.science/paper/CFCG6HRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18649&json=true","fetch_graph":"https://pith.science/api/pith-number/CFCG6HREL4VKBQSAQEDGDKCA6C/graph.json","fetch_events":"https://pith.science/api/pith-number/CFCG6HREL4VKBQSAQEDGDKCA6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFCG6HREL4VKBQSAQEDGDKCA6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFCG6HREL4VKBQSAQEDGDKCA6C/action/storage_attestation","attest_author":"https://pith.science/pith/CFCG6HREL4VKBQSAQEDGDKCA6C/action/author_attestation","sign_citation":"https://pith.science/pith/CFCG6HREL4VKBQSAQEDGDKCA6C/action/citation_signature","submit_replication":"https://pith.science/pith/CFCG6HREL4VKBQSAQEDGDKCA6C/action/replication_record"}},"created_at":"2026-07-05T11:42:55.904593+00:00","updated_at":"2026-07-05T11:42:55.904593+00:00"}