{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X345NTZDY6536QVEYZATVJFQFW","short_pith_number":"pith:X345NTZD","schema_version":"1.0","canonical_sha256":"bef9d6cf23c7bbbf42a4c6413aa4b02d87d79d1387f8bb40f4d25f37f32b7c87","source":{"kind":"arxiv","id":"2504.16030","version":1},"attestation_state":"computed","paper":{"title":"LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joya Chen, Mike Zheng Shou, Wei Li, Yiqi Lin, Zejun Ma, Ziyun Zeng","submitted_at":"2025-04-22T16:52:09Z","abstract_excerpt":"Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary model APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) transcripts. Specifically, we propose a novel streaming training approach that densely interleaves the ASR words and video frames according to their timestamps. Compared to previous studies in vision-language representation with ASR, our method naturally fits the streaming characteristics of ASR, t"},"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":"2504.16030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-22T16:52:09Z","cross_cats_sorted":[],"title_canon_sha256":"7bb3edcc95b9cf1c7d2f3fe1b7796445c53f8e67245154ed85e3d75139abced5","abstract_canon_sha256":"e6a712388164a132136e57d8e6b0c3be37fbb7d9341dd9eaf986209d9c453b87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:33.715418Z","signature_b64":"wpRt+yqVF93BTO5Djn6d+4GUB9iEKoFJx+GSF0mEJHCw3B+CLouUvo9b1CqVyMnHqH9gudF8XkWthMqxKziHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bef9d6cf23c7bbbf42a4c6413aa4b02d87d79d1387f8bb40f4d25f37f32b7c87","last_reissued_at":"2026-07-05T10:52:33.714905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:33.714905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Joya Chen, Mike Zheng Shou, Wei Li, Yiqi Lin, Zejun Ma, Ziyun Zeng","submitted_at":"2025-04-22T16:52:09Z","abstract_excerpt":"Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary model APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) transcripts. Specifically, we propose a novel streaming training approach that densely interleaves the ASR words and video frames according to their timestamps. Compared to previous studies in vision-language representation with ASR, our method naturally fits the streaming characteristics of ASR, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16030","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/2504.16030/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":"2504.16030","created_at":"2026-07-05T10:52:33.714968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16030v1","created_at":"2026-07-05T10:52:33.714968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16030","created_at":"2026-07-05T10:52:33.714968+00:00"},{"alias_kind":"pith_short_12","alias_value":"X345NTZDY653","created_at":"2026-07-05T10:52:33.714968+00:00"},{"alias_kind":"pith_short_16","alias_value":"X345NTZDY6536QVE","created_at":"2026-07-05T10:52:33.714968+00:00"},{"alias_kind":"pith_short_8","alias_value":"X345NTZD","created_at":"2026-07-05T10:52:33.714968+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17360","citing_title":"Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17360","citing_title":"Omni-DuplexEval: Evaluating Real-time Duplex Omni-modal Interaction","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17921","citing_title":"An Efficient Streaming Video Understanding Framework with Agentic Control","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2511.21998","citing_title":"Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16893","citing_title":"EasyVideoR1: Easier RL for Video Understanding","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW","json":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW.json","graph_json":"https://pith.science/api/pith-number/X345NTZDY6536QVEYZATVJFQFW/graph.json","events_json":"https://pith.science/api/pith-number/X345NTZDY6536QVEYZATVJFQFW/events.json","paper":"https://pith.science/paper/X345NTZD"},"agent_actions":{"view_html":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW","download_json":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW.json","view_paper":"https://pith.science/paper/X345NTZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16030&json=true","fetch_graph":"https://pith.science/api/pith-number/X345NTZDY6536QVEYZATVJFQFW/graph.json","fetch_events":"https://pith.science/api/pith-number/X345NTZDY6536QVEYZATVJFQFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW/action/storage_attestation","attest_author":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW/action/author_attestation","sign_citation":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW/action/citation_signature","submit_replication":"https://pith.science/pith/X345NTZDY6536QVEYZATVJFQFW/action/replication_record"}},"created_at":"2026-07-05T10:52:33.714968+00:00","updated_at":"2026-07-05T10:52:33.714968+00:00"}