{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DANAGOQMYSONYCLBHI5VPKZFV3","short_pith_number":"pith:DANAGOQM","schema_version":"1.0","canonical_sha256":"181a033a0cc49cdc09613a3b57ab25aef8b643bb7933a9cc4b8dc3d30518d1bd","source":{"kind":"arxiv","id":"2501.01957","version":4},"attestation_state":"computed","paper":{"title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A multi-stage training method allows large language models to handle vision and speech together for near real-time interaction.","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Caifeng Shan, Chaoyou Fu, Haojia Lin, Haoyu Cao, Heting Gao, Ke Li, Long Ma, Ran He, Rongrong Ji, Xiaoyu Liu, Xiawu Zheng, Xing Sun, Xiong Wang, Yi-Fan Zhang, Yunhang Shen, Zuwei Long","submitted_at":"2025-01-03T18:59:52Z","abstract_excerpt":"Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction. However, speech plays a crucial role in multimodal dialogue systems, and implementing high-performance in both vision and speech tasks remains a significant challenge due to the fundamental modality differences. In this paper, we propose a carefully designed multi-stage training methodology that progressively trains LLM to understand both visual and speech information, ultimately enabling fluent vision 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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2501.01957","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T18:59:52Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"6e3f027dc6145dfab500c2837be05fae09a466ca6207ecf900e63fdf2471478b","abstract_canon_sha256":"0226ae62a6421b6814d91b94483cc947f92cefd1a23c4c3619dbc03f7bc32d4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.078173Z","signature_b64":"2kPLOGvUNM8byHWLQ4xy+O4UPhWdJeByLi0tTERReTzYZBLkjLYV+asf/mJkKLHcnhHbrtCZXCM7AecVBTVhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"181a033a0cc49cdc09613a3b57ab25aef8b643bb7933a9cc4b8dc3d30518d1bd","last_reissued_at":"2026-05-17T23:38:13.077493Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.077493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A multi-stage training method allows large language models to handle vision and speech together for near real-time interaction.","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Caifeng Shan, Chaoyou Fu, Haojia Lin, Haoyu Cao, Heting Gao, Ke Li, Long Ma, Ran He, Rongrong Ji, Xiaoyu Liu, Xiawu Zheng, Xing Sun, Xiong Wang, Yi-Fan Zhang, Yunhang Shen, Zuwei Long","submitted_at":"2025-01-03T18:59:52Z","abstract_excerpt":"Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction. However, speech plays a crucial role in multimodal dialogue systems, and implementing high-performance in both vision and speech tasks remains a significant challenge due to the fundamental modality differences. In this paper, we propose a carefully designed multi-stage training methodology that progressively trains LLM to understand both visual and speech information, ultimately enabling fluent vision and"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By comparing our method against state-of-the-art counterparts across benchmarks for image, video, and speech tasks, we demonstrate that our model is equipped with both strong visual and speech capabilities, making near real-time vision and speech interaction.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The multi-stage training can be balanced so that speech capabilities are added without degrading the pre-existing vision-language capacity, an assumption stated in the description of the progressive training methodology.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VITA-1.5 integrates vision and speech into a single LLM through multi-stage training, delivering competitive benchmark results on image, video, and speech tasks with near real-time response speed.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A multi-stage training method allows large language models to handle vision and speech together for near real-time interaction.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e8c6731de283f6b18da3eeb7bc841fc5dddec0485d965e8d46b1193eb80b5464"},"source":{"id":"2501.01957","kind":"arxiv","version":4},"verdict":{"id":"76a7ab1c-81c8-4eb8-9f5c-10000558b2e6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T21:03:49.526514Z","strongest_claim":"By comparing our method against state-of-the-art counterparts across benchmarks for image, video, and speech tasks, we demonstrate that our model is equipped with both strong visual and speech capabilities, making near real-time vision and speech interaction.","one_line_summary":"VITA-1.5 integrates vision and speech into a single LLM through multi-stage training, delivering competitive benchmark results on image, video, and speech tasks with near real-time response speed.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The multi-stage training can be balanced so that speech capabilities are added without degrading the pre-existing vision-language capacity, an assumption stated in the description of the progressive training methodology.","pith_extraction_headline":"A multi-stage training method allows large language models to handle vision and speech together for near real-time interaction."},"references":{"count":77,"sample":[{"doi":"","year":2023,"title":"Visual Instruction Tuning","work_id":"68be622d-a6dc-4a13-82de-e3054a3dc509","ref_index":1,"cited_arxiv_id":"2304.08485","is_internal_anchor":true},{"doi":"","year":2024,"title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","work_id":"647f3087-e96f-4aaa-a599-2dbafb5ac024","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","work_id":"555cf04a-49a7-44b8-9019-a83ce85ace95","ref_index":3,"cited_arxiv_id":"2306.02858","is_internal_anchor":true},{"doi":"","year":2025,"title":"Speechact: Towards generating whole-body motion from speech.IEEE TVCG","work_id":"5c873038-1603-44c8-b3a6-34e24f353959","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"video-salmonn: Speech-enhanced audio-visual large language models","work_id":"14b6b6ca-3c9e-434a-8eb7-ebdcbf08efc6","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":77,"snapshot_sha256":"d9c993562d3e8372ceb4bee179753bc295ea9a4e1ab57f406c8829e487e9d3c9","internal_anchors":28},"formal_canon":{"evidence_count":2,"snapshot_sha256":"56bf5d2546ea0fcddd50ec47bfd0c6b37324b79cc0badd7ccd93ee39d25c0cf4"},"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":"2501.01957","created_at":"2026-05-17T23:38:13.077593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01957v4","created_at":"2026-05-17T23:38:13.077593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01957","created_at":"2026-05-17T23:38:13.077593+00:00"},{"alias_kind":"pith_short_12","alias_value":"DANAGOQMYSON","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"DANAGOQMYSONYCLB","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"DANAGOQM","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":24,"internal_anchor_count":24,"sample":[{"citing_arxiv_id":"2505.14654","citing_title":"Beyond Words: Multimodal LLM Knows When to Speak","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22012","citing_title":"LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18758","citing_title":"OmniGUI: Benchmarking GUI Agents in Omni-Modal Smartphone Environments","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20755","citing_title":"DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2509.26388","citing_title":"Game-Time: Evaluating Temporal Dynamics in Spoken Language Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2501.00574","citing_title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2511.14582","citing_title":"OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2502.04326","citing_title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2512.01707","citing_title":"StreamGaze: Gaze-Guided Temporal Reasoning and Proactive Understanding in Streaming Videos","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2512.02231","citing_title":"See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2603.01455","citing_title":"From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2603.22267","citing_title":"TiCo: Time-Controllable Spoken Dialogue Model","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01897","citing_title":"FastTurn: Unifying Acoustic and Streaming Semantic Cues for Low-Latency and Robust Turn Detection","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09982","citing_title":"ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token Pruning","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09269","citing_title":"DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10199","citing_title":"How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03276","citing_title":"VEBench:Benchmarking Large Multimodal Models for Real-World Video Editing","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03276","citing_title":"VEBench:Benchmarking Large Multimodal Models for Real-World Video Editing","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21406","citing_title":"Full-Duplex Interaction in Spoken Dialogue Systems: A Comprehensive Study from the ICASSP 2026 HumDial Challenge","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01278","citing_title":"Valley3: Scaling Omni Foundation Models for E-commerce","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01024","citing_title":"EmoMM: Benchmarking and Steering MLLM for Multimodal Emotion Recognition under Conflict and Missingness","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08120","citing_title":"Small Vision-Language Models are Smart Compressors for Long Video Understanding","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05015","citing_title":"Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09222","citing_title":"GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DANAGOQMYSONYCLBHI5VPKZFV3","json":"https://pith.science/pith/DANAGOQMYSONYCLBHI5VPKZFV3.json","graph_json":"https://pith.science/api/pith-number/DANAGOQMYSONYCLBHI5VPKZFV3/graph.json","events_json":"https://pith.science/api/pith-number/DANAGOQMYSONYCLBHI5VPKZFV3/events.json","paper":"https://pith.science/paper/DANAGOQM"},"agent_actions":{"view_html":"https://pith.science/pith/DANAGOQMYSONYCLBHI5VPKZFV3","download_json":"https://pith.science/pith/DANAGOQMYSONYCLBHI5VPKZFV3.json","view_paper":"https://pith.science/paper/DANAGOQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01957&json=true","fetch_graph":"https://pith.science/api/pith-number/DANAGOQMYSONYCLBHI5VPKZFV3/graph.json","fetch_events":"https://pith.science/api/pith-number/DANAGOQMYSONYCLBHI5VPKZFV3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DANAGOQMYSONYCLBHI5VPKZFV3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DANAGOQMYSONYCLBHI5VPKZFV3/action/storage_attestation","attest_author":"https://pith.science/pith/DANAGOQMYSONYCLBHI5VPKZFV3/action/author_attestation","sign_citation":"https://pith.science/pith/DANAGOQMYSONYCLBHI5VPKZFV3/action/citation_signature","submit_replication":"https://pith.science/pith/DANAGOQMYSONYCLBHI5VPKZFV3/action/replication_record"}},"created_at":"2026-05-17T23:38:13.077593+00:00","updated_at":"2026-05-17T23:38:13.077593+00:00"}