{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DANAGOQMYSONYCLBHI5VPKZFV3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0226ae62a6421b6814d91b94483cc947f92cefd1a23c4c3619dbc03f7bc32d4b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T18:59:52Z","title_canon_sha256":"6e3f027dc6145dfab500c2837be05fae09a466ca6207ecf900e63fdf2471478b"},"schema_version":"1.0","source":{"id":"2501.01957","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01957","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01957v4","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01957","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"DANAGOQMYSON","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DANAGOQMYSONYCLB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DANAGOQM","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4aad90a45e99ab6963e9960b3a7c39f2b6f58f2045dbb6e5f2ff857de05c0216","target":"graph","created_at":"2026-05-17T23:38:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A multi-stage training method allows large language models to handle vision and speech together for near real-time interaction."}],"snapshot_sha256":"e8c6731de283f6b18da3eeb7bc841fc5dddec0485d965e8d46b1193eb80b5464"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"56bf5d2546ea0fcddd50ec47bfd0c6b37324b79cc0badd7ccd93ee39d25c0cf4"},"paper":{"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","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","cross_cats":["cs.SD","eess.AS"],"headline":"A multi-stage training method allows large language models to handle vision and speech together for near real-time interaction.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T18:59:52Z","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction"},"references":{"count":77,"internal_anchors":28,"resolved_work":77,"sample":[{"cited_arxiv_id":"2304.08485","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Visual Instruction Tuning","work_id":"68be622d-a6dc-4a13-82de-e3054a3dc509","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","work_id":"647f3087-e96f-4aaa-a599-2dbafb5ac024","year":2024},{"cited_arxiv_id":"2306.02858","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","work_id":"555cf04a-49a7-44b8-9019-a83ce85ace95","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Speechact: Towards generating whole-body motion from speech.IEEE TVCG","work_id":"5c873038-1603-44c8-b3a6-34e24f353959","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"video-salmonn: Speech-enhanced audio-visual large language models","work_id":"14b6b6ca-3c9e-434a-8eb7-ebdcbf08efc6","year":2024}],"snapshot_sha256":"d9c993562d3e8372ceb4bee179753bc295ea9a4e1ab57f406c8829e487e9d3c9"},"source":{"id":"2501.01957","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-17T21:03:49.526514Z","id":"76a7ab1c-81c8-4eb8-9f5c-10000558b2e6","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"A multi-stage training method allows large language models to handle vision and speech together for near real-time interaction.","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.","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."}},"verdict_id":"76a7ab1c-81c8-4eb8-9f5c-10000558b2e6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ea1693aa8a640721e46f7fbae0ddbb2d8af8a14b2778f0d2d82464ea69aee9a6","target":"record","created_at":"2026-05-17T23:38:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0226ae62a6421b6814d91b94483cc947f92cefd1a23c4c3619dbc03f7bc32d4b","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-03T18:59:52Z","title_canon_sha256":"6e3f027dc6145dfab500c2837be05fae09a466ca6207ecf900e63fdf2471478b"},"schema_version":"1.0","source":{"id":"2501.01957","kind":"arxiv","version":4}},"canonical_sha256":"181a033a0cc49cdc09613a3b57ab25aef8b643bb7933a9cc4b8dc3d30518d1bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"181a033a0cc49cdc09613a3b57ab25aef8b643bb7933a9cc4b8dc3d30518d1bd","first_computed_at":"2026-05-17T23:38:13.077493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.077493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2kPLOGvUNM8byHWLQ4xy+O4UPhWdJeByLi0tTERReTzYZBLkjLYV+asf/mJkKLHcnhHbrtCZXCM7AecVBTVhDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.078173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01957","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea1693aa8a640721e46f7fbae0ddbb2d8af8a14b2778f0d2d82464ea69aee9a6","sha256:4aad90a45e99ab6963e9960b3a7c39f2b6f58f2045dbb6e5f2ff857de05c0216"],"state_sha256":"a483deda6b6f92a0476a310b7a0050fac92970fec6d335d668666cfe5fdcacc0"}