{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5WCFTYZZBJ5DROXZNU7TFQJDRL","short_pith_number":"pith:5WCFTYZZ","schema_version":"1.0","canonical_sha256":"ed8459e3390a7a38baf96d3f32c1238ae658217b99f5666e95b8213011a743ac","source":{"kind":"arxiv","id":"2412.09501","version":1},"attestation_state":"computed","paper":{"title":"Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chengyao Wang, Eric Lo, Jiaya Jia, Jingyao Li, Longxiang Tang, Senqiao Yang, Shaozuo Yu, Shu Liu, Sitong Wu, Tianyuan Qu, Yanwei Li, Yuechen Zhang, Yukang Chen, Yuqi Liu, Zhisheng Zhong","submitted_at":"2024-12-12T17:50:39Z","abstract_excerpt":"As Multi-modal Large Language Models (MLLMs) evolve, expanding beyond single-domain capabilities is essential to meet the demands for more versatile and efficient AI. However, previous omni-models have insufficiently explored speech, neglecting its integration with multi-modality. We introduce Lyra, an efficient MLLM that enhances multimodal abilities, including advanced long-speech comprehension, sound understanding, cross-modality efficiency, and seamless speech interaction. To achieve efficiency and speech-centric capabilities, Lyra employs three strategies: (1) leveraging existing open-sou"},"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":"2412.09501","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T17:50:39Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"09cea9b653be7d57e48021dfd033c79adf51a298103cf5cf39cb069e934e1652","abstract_canon_sha256":"4b6feb0631f1c1e94631496b0b1e4af3960bee874d148a10ef1689cfbf40d3c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:25.295218Z","signature_b64":"3p/fVGK2TpgajdtgdfdQC2DEKEzWZfLYt3JEC0c/oWa+rt3f1KOjXRlpwUjKojRvUAKcsjhATwQdKatTE/zOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed8459e3390a7a38baf96d3f32c1238ae658217b99f5666e95b8213011a743ac","last_reissued_at":"2026-07-05T09:48:25.294694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:25.294694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Chengyao Wang, Eric Lo, Jiaya Jia, Jingyao Li, Longxiang Tang, Senqiao Yang, Shaozuo Yu, Shu Liu, Sitong Wu, Tianyuan Qu, Yanwei Li, Yuechen Zhang, Yukang Chen, Yuqi Liu, Zhisheng Zhong","submitted_at":"2024-12-12T17:50:39Z","abstract_excerpt":"As Multi-modal Large Language Models (MLLMs) evolve, expanding beyond single-domain capabilities is essential to meet the demands for more versatile and efficient AI. However, previous omni-models have insufficiently explored speech, neglecting its integration with multi-modality. We introduce Lyra, an efficient MLLM that enhances multimodal abilities, including advanced long-speech comprehension, sound understanding, cross-modality efficiency, and seamless speech interaction. To achieve efficiency and speech-centric capabilities, Lyra employs three strategies: (1) leveraging existing open-sou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09501","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/2412.09501/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":"2412.09501","created_at":"2026-07-05T09:48:25.294757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09501v1","created_at":"2026-07-05T09:48:25.294757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09501","created_at":"2026-07-05T09:48:25.294757+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WCFTYZZBJ5D","created_at":"2026-07-05T09:48:25.294757+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WCFTYZZBJ5DROXZ","created_at":"2026-07-05T09:48:25.294757+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WCFTYZZ","created_at":"2026-07-05T09:48:25.294757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.12455","citing_title":"Mitigating Object Hallucinations via Sentence-Level Early Intervention","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21008","citing_title":"A Survey of Audio Reasoning in Multimodal Foundation Models","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10606","citing_title":"ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2503.06520","citing_title":"Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03677","citing_title":"Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2503.20215","citing_title":"Qwen2.5-Omni Technical Report","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL","json":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL.json","graph_json":"https://pith.science/api/pith-number/5WCFTYZZBJ5DROXZNU7TFQJDRL/graph.json","events_json":"https://pith.science/api/pith-number/5WCFTYZZBJ5DROXZNU7TFQJDRL/events.json","paper":"https://pith.science/paper/5WCFTYZZ"},"agent_actions":{"view_html":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL","download_json":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL.json","view_paper":"https://pith.science/paper/5WCFTYZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09501&json=true","fetch_graph":"https://pith.science/api/pith-number/5WCFTYZZBJ5DROXZNU7TFQJDRL/graph.json","fetch_events":"https://pith.science/api/pith-number/5WCFTYZZBJ5DROXZNU7TFQJDRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL/action/storage_attestation","attest_author":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL/action/author_attestation","sign_citation":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL/action/citation_signature","submit_replication":"https://pith.science/pith/5WCFTYZZBJ5DROXZNU7TFQJDRL/action/replication_record"}},"created_at":"2026-07-05T09:48:25.294757+00:00","updated_at":"2026-07-05T09:48:25.294757+00:00"}