{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:24VY7DOQJES6X7AR3HDF5HR6U2","short_pith_number":"pith:24VY7DOQ","schema_version":"1.0","canonical_sha256":"d72b8f8dd04925ebfc11d9c65e9e3ea6a3f3fbcc8eb4ef942ce9276d6fea79c6","source":{"kind":"arxiv","id":"2410.11190","version":3},"attestation_state":"computed","paper":{"title":"Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Changqiao Wu, Zhifei Xie","submitted_at":"2024-10-15T02:10:45Z","abstract_excerpt":"GPT-4o, an all-encompassing model, represents a milestone in the development of large multi-modal language models. It can understand visual, auditory, and textual modalities, directly output audio, and support flexible duplex interaction. Models from the open-source community often achieve some functionalities of GPT-4o, such as visual understanding and voice chat. Nevertheless, training a unified model that incorporates all modalities is challenging due to the complexities of multi-modal data, intricate model architectures, and training processes. In this paper, we introduce Mini-Omni2, a vis"},"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":"2410.11190","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-10-15T02:10:45Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SD"],"title_canon_sha256":"a259a681ff0801580297ac53eef6deb18a2889d73caa043ad9c4653e8f24c7a5","abstract_canon_sha256":"97db3f566d788fbfbcfad572c7953728d9c8fc9764fadc42cc643ab1752f53ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:09.310049Z","signature_b64":"7O1KfiLhtJmMz1fEVbRpjHQS8hRsxovdQsKSiiuSrRHgaebkTxNa9t8TEvIeHG47W5Zs130YzwJUrD8LK5jUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d72b8f8dd04925ebfc11d9c65e9e3ea6a3f3fbcc8eb4ef942ce9276d6fea79c6","last_reissued_at":"2026-07-05T09:31:09.309579Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:09.309579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Changqiao Wu, Zhifei Xie","submitted_at":"2024-10-15T02:10:45Z","abstract_excerpt":"GPT-4o, an all-encompassing model, represents a milestone in the development of large multi-modal language models. It can understand visual, auditory, and textual modalities, directly output audio, and support flexible duplex interaction. Models from the open-source community often achieve some functionalities of GPT-4o, such as visual understanding and voice chat. Nevertheless, training a unified model that incorporates all modalities is challenging due to the complexities of multi-modal data, intricate model architectures, and training processes. In this paper, we introduce Mini-Omni2, a vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11190","kind":"arxiv","version":3},"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/2410.11190/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":"2410.11190","created_at":"2026-07-05T09:31:09.309635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11190v3","created_at":"2026-07-05T09:31:09.309635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11190","created_at":"2026-07-05T09:31:09.309635+00:00"},{"alias_kind":"pith_short_12","alias_value":"24VY7DOQJES6","created_at":"2026-07-05T09:31:09.309635+00:00"},{"alias_kind":"pith_short_16","alias_value":"24VY7DOQJES6X7AR","created_at":"2026-07-05T09:31:09.309635+00:00"},{"alias_kind":"pith_short_8","alias_value":"24VY7DOQ","created_at":"2026-07-05T09:31:09.309635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06540","citing_title":"Hierarchical Acoustic-Semantic Modeling: Modality Separation and Semantic Coherence for Full-Duplex SLMs","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2606.20970","citing_title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19453","citing_title":"A Survey of Full-Duplex Spoken Dialogue Systems: Architectural Hierarchy, Interaction Ontology, and Decision State Machine","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06559","citing_title":"IRAF: Interference-Resilient Adaptive Fusion for Noise-Robust End-to-End Full-Duplex Spoken Dialogue Systems","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05121","citing_title":"Audio Interaction Model","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":258,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20755","citing_title":"DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30256","citing_title":"VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agents","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20755","citing_title":"DuplexSLA: A Full-Duplex Spoken Language Model with Synchronized Speech, Language, and Action","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21008","citing_title":"A Survey of Audio Reasoning in Multimodal Foundation Models","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20035","citing_title":"Stage-adaptive Token Selection for Efficient Omni-modal LLMs","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2508.10016","citing_title":"Training-Free Multimodal Large Language Model Orchestration","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2501.01957","citing_title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14582","citing_title":"OmniZip: Audio-Guided Dynamic Token Compression for Fast Omnimodal Large Language Models","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2410.17196","citing_title":"VoiceBench: Benchmarking LLM-Based Voice Assistants","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":215,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22267","citing_title":"TiCo: Time-Controllable Spoken Dialogue Model","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12056","citing_title":"OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models","ref_index":50,"is_internal_anchor":false},{"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":51,"is_internal_anchor":false},{"citing_arxiv_id":"2503.01743","citing_title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06765","citing_title":"VITA-QinYu: Expressive Spoken Language Model for Role-Playing and Singing","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2","json":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2.json","graph_json":"https://pith.science/api/pith-number/24VY7DOQJES6X7AR3HDF5HR6U2/graph.json","events_json":"https://pith.science/api/pith-number/24VY7DOQJES6X7AR3HDF5HR6U2/events.json","paper":"https://pith.science/paper/24VY7DOQ"},"agent_actions":{"view_html":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2","download_json":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2.json","view_paper":"https://pith.science/paper/24VY7DOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11190&json=true","fetch_graph":"https://pith.science/api/pith-number/24VY7DOQJES6X7AR3HDF5HR6U2/graph.json","fetch_events":"https://pith.science/api/pith-number/24VY7DOQJES6X7AR3HDF5HR6U2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2/action/storage_attestation","attest_author":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2/action/author_attestation","sign_citation":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2/action/citation_signature","submit_replication":"https://pith.science/pith/24VY7DOQJES6X7AR3HDF5HR6U2/action/replication_record"}},"created_at":"2026-07-05T09:31:09.309635+00:00","updated_at":"2026-07-05T09:31:09.309635+00:00"}