{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q3FUYAY4I5ZQQVF7XB4DYH355J","short_pith_number":"pith:Q3FUYAY4","schema_version":"1.0","canonical_sha256":"86cb4c031c47730854bfb8783c1f7dea47e31f1250d02c3c3dcf2777c54f1ca7","source":{"kind":"arxiv","id":"2311.04257","version":2},"attestation_state":"computed","paper":{"title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Anwen Hu, Fei Huang, Haiyang Xu, Haowei Liu, Jiabo Ye, Jingren Zhou, Ji Zhang, Ming Yan, Qinghao Ye, Qi Qian","submitted_at":"2023-11-07T14:21:29Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have demonstrated impressive instruction abilities across various open-ended tasks. However, previous methods primarily focus on enhancing multi-modal capabilities. In this work, we introduce a versatile multi-modal large language model, mPLUG-Owl2, which effectively leverages modality collaboration to improve performance in both text and multi-modal tasks. mPLUG-Owl2 utilizes a modularized network design, with the language decoder acting as a universal interface for managing different modalities. Specifically, mPLUG-Owl2 incorporates shared functional"},"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":"2311.04257","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-07T14:21:29Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"438038f1b7e49f9e4b1caa99cf89eb59a90458ff74f88168e3afc438f756a50a","abstract_canon_sha256":"4d5e26ecf6ecb9e908558c6abf9882bc231e9606f92e632ec0e82d6ad6986ae2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:14:37.403725Z","signature_b64":"LXNqk2n3abMPnfwJAqRNYgcTZ0SbNe2Iz4ucbI30ifcC3s651qpkADM7qIuDFWqXLaP2tU3fe15fiPnaLEB2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86cb4c031c47730854bfb8783c1f7dea47e31f1250d02c3c3dcf2777c54f1ca7","last_reissued_at":"2026-05-18T03:14:37.403116Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:14:37.403116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Anwen Hu, Fei Huang, Haiyang Xu, Haowei Liu, Jiabo Ye, Jingren Zhou, Ji Zhang, Ming Yan, Qinghao Ye, Qi Qian","submitted_at":"2023-11-07T14:21:29Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) have demonstrated impressive instruction abilities across various open-ended tasks. However, previous methods primarily focus on enhancing multi-modal capabilities. In this work, we introduce a versatile multi-modal large language model, mPLUG-Owl2, which effectively leverages modality collaboration to improve performance in both text and multi-modal tasks. mPLUG-Owl2 utilizes a modularized network design, with the language decoder acting as a universal interface for managing different modalities. Specifically, mPLUG-Owl2 incorporates shared functional"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04257","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":""},"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":"2311.04257","created_at":"2026-05-18T03:14:37.403198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04257v2","created_at":"2026-05-18T03:14:37.403198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04257","created_at":"2026-05-18T03:14:37.403198+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3FUYAY4I5ZQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3FUYAY4I5ZQQVF7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3FUYAY4","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":19,"sample":[{"citing_arxiv_id":"2406.10185","citing_title":"Detecting and Evaluating Medical Hallucinations in Large Vision Language Models","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2411.16771","citing_title":"VidHal: Benchmarking Temporal Hallucinations in Vision LLMs","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2502.13923","citing_title":"Qwen2.5-VL Technical Report","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2401.16158","citing_title":"Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":125,"is_internal_anchor":true},{"citing_arxiv_id":"2311.03079","citing_title":"CogVLM: Visual Expert for Pretrained Language Models","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2311.16502","citing_title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"2409.02813","citing_title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":128,"is_internal_anchor":true},{"citing_arxiv_id":"2307.06281","citing_title":"MMBench: Is Your Multi-modal Model an All-around Player?","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10582","citing_title":"Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":189,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12508","citing_title":"From Attenuation to Attention: Variational Information Flow Manipulation for Fine-Grained Visual Perception","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10971","citing_title":"MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language Models","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2306.13394","citing_title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":137,"is_internal_anchor":true},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":276,"is_internal_anchor":true},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":166,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20366","citing_title":"Mitigating Hallucinations in Large Vision-Language Models without Performance Degradation","ref_index":136,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3FUYAY4I5ZQQVF7XB4DYH355J","json":"https://pith.science/pith/Q3FUYAY4I5ZQQVF7XB4DYH355J.json","graph_json":"https://pith.science/api/pith-number/Q3FUYAY4I5ZQQVF7XB4DYH355J/graph.json","events_json":"https://pith.science/api/pith-number/Q3FUYAY4I5ZQQVF7XB4DYH355J/events.json","paper":"https://pith.science/paper/Q3FUYAY4"},"agent_actions":{"view_html":"https://pith.science/pith/Q3FUYAY4I5ZQQVF7XB4DYH355J","download_json":"https://pith.science/pith/Q3FUYAY4I5ZQQVF7XB4DYH355J.json","view_paper":"https://pith.science/paper/Q3FUYAY4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04257&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3FUYAY4I5ZQQVF7XB4DYH355J/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3FUYAY4I5ZQQVF7XB4DYH355J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3FUYAY4I5ZQQVF7XB4DYH355J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3FUYAY4I5ZQQVF7XB4DYH355J/action/storage_attestation","attest_author":"https://pith.science/pith/Q3FUYAY4I5ZQQVF7XB4DYH355J/action/author_attestation","sign_citation":"https://pith.science/pith/Q3FUYAY4I5ZQQVF7XB4DYH355J/action/citation_signature","submit_replication":"https://pith.science/pith/Q3FUYAY4I5ZQQVF7XB4DYH355J/action/replication_record"}},"created_at":"2026-05-18T03:14:37.403198+00:00","updated_at":"2026-05-18T03:14:37.403198+00:00"}