{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6YZWALWPGYNSW6YY67ZGFN7RCP","short_pith_number":"pith:6YZWALWP","schema_version":"1.0","canonical_sha256":"f633602ecf361b2b7b18f7f262b7f113cfd82092afd3931f8fbfe8792ab348cf","source":{"kind":"arxiv","id":"2304.08345","version":2},"attestation_state":"computed","paper":{"title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.LG","authors_text":"Jing Liu, Jinhui Tang, Longteng Guo, Sihan Chen, Weining Wang, Xingjian He, Xinxin Zhu","submitted_at":"2023-04-17T15:08:15Z","abstract_excerpt":"In this paper, we propose a Vision-Audio-Language Omni-peRception pretraining model (VALOR) for multi-modal understanding and generation. Different from widely-studied vision-language pretraining models, VALOR jointly models relationships of vision, audio and language in an end-to-end manner. It contains three separate encoders for single modality representations, and a decoder for multimodal conditional text generation. We design two pretext tasks to pretrain VALOR model, including Multimodal Grouping Alignment (MGA) and Multimodal Grouping Captioning (MGC). MGA projects vision, language and "},"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":"2304.08345","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-17T15:08:15Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"e6c8ba09b0b5a7ff81eab039d628140f3149a1cd339fcbc7f6412051bfbbe2f6","abstract_canon_sha256":"329cd2cee8cb5794503beed804fcd3d8e508189f5257d9cc6f4a0f9fd477cb2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:18.074222Z","signature_b64":"UeqSCpiy6AbiQX8hD5F/ERBoNThSJtRmHB02SsrNT+Q3N0l+1Nt/+m9BBICDtvaL6ZXIDXllXnMJrSnpd/jCBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f633602ecf361b2b7b18f7f262b7f113cfd82092afd3931f8fbfe8792ab348cf","last_reissued_at":"2026-07-05T09:57:18.073736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:18.073736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.LG","authors_text":"Jing Liu, Jinhui Tang, Longteng Guo, Sihan Chen, Weining Wang, Xingjian He, Xinxin Zhu","submitted_at":"2023-04-17T15:08:15Z","abstract_excerpt":"In this paper, we propose a Vision-Audio-Language Omni-peRception pretraining model (VALOR) for multi-modal understanding and generation. Different from widely-studied vision-language pretraining models, VALOR jointly models relationships of vision, audio and language in an end-to-end manner. It contains three separate encoders for single modality representations, and a decoder for multimodal conditional text generation. We design two pretext tasks to pretrain VALOR model, including Multimodal Grouping Alignment (MGA) and Multimodal Grouping Captioning (MGC). MGA projects vision, language and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08345","kind":"arxiv","version":2},"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/2304.08345/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":"2304.08345","created_at":"2026-07-05T09:57:18.073803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08345v2","created_at":"2026-07-05T09:57:18.073803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08345","created_at":"2026-07-05T09:57:18.073803+00:00"},{"alias_kind":"pith_short_12","alias_value":"6YZWALWPGYNS","created_at":"2026-07-05T09:57:18.073803+00:00"},{"alias_kind":"pith_short_16","alias_value":"6YZWALWPGYNSW6YY","created_at":"2026-07-05T09:57:18.073803+00:00"},{"alias_kind":"pith_short_8","alias_value":"6YZWALWP","created_at":"2026-07-05T09:57:18.073803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21734","citing_title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","ref_index":299,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":216,"is_internal_anchor":false},{"citing_arxiv_id":"2510.18346","citing_title":"AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2511.12034","citing_title":"Calibrated Multimodal Representation Learning with Missing Modalities","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2511.21331","citing_title":"The More, the Merrier: Contrastive Fusion for Higher-Order Multimodal Alignment","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2310.01852","citing_title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","ref_index":200,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06942","citing_title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14129","citing_title":"Don't Let the Video Speak: Audio-Contrastive Preference Optimization for Audio-Visual Language Models","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP","json":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP.json","graph_json":"https://pith.science/api/pith-number/6YZWALWPGYNSW6YY67ZGFN7RCP/graph.json","events_json":"https://pith.science/api/pith-number/6YZWALWPGYNSW6YY67ZGFN7RCP/events.json","paper":"https://pith.science/paper/6YZWALWP"},"agent_actions":{"view_html":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP","download_json":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP.json","view_paper":"https://pith.science/paper/6YZWALWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08345&json=true","fetch_graph":"https://pith.science/api/pith-number/6YZWALWPGYNSW6YY67ZGFN7RCP/graph.json","fetch_events":"https://pith.science/api/pith-number/6YZWALWPGYNSW6YY67ZGFN7RCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP/action/storage_attestation","attest_author":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP/action/author_attestation","sign_citation":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP/action/citation_signature","submit_replication":"https://pith.science/pith/6YZWALWPGYNSW6YY67ZGFN7RCP/action/replication_record"}},"created_at":"2026-07-05T09:57:18.073803+00:00","updated_at":"2026-07-05T09:57:18.073803+00:00"}