{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F4F3B6XSURWOLHT2BCN76XQLDF","short_pith_number":"pith:F4F3B6XS","schema_version":"1.0","canonical_sha256":"2f0bb0faf2a46ce59e7a089bff5e0b196e1893ead60c2a575bebd58f356770c3","source":{"kind":"arxiv","id":"2306.05425","version":1},"attestation_state":"computed","paper":{"title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC"],"primary_cat":"cs.CV","authors_text":"Bo Li, Chunyuan Li, Fanyi Pu, Jinghao Wang, Jingkang Yang, Liangyu Chen, Yuanhan Zhang, Ziwei Liu","submitted_at":"2023-06-08T17:59:56Z","abstract_excerpt":"High-quality instructions and responses are essential for the zero-shot performance of large language models on interactive natural language tasks. For interactive vision-language tasks involving intricate visual scenes, a large quantity of diverse and creative instruction-response pairs should be imperative to tune vision-language models (VLMs). Nevertheless, the current availability of vision-language instruction-response pairs in terms of quantity, diversity, and creativity remains limited, posing challenges to the generalization of interactive VLMs. Here we present MultI-Modal In-Context I"},"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":"2306.05425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-08T17:59:56Z","cross_cats_sorted":["cs.AI","cs.CL","cs.HC"],"title_canon_sha256":"187e285894a4199d28840d0ebb5566a7d28c648887b46f2ec693763c20f54a46","abstract_canon_sha256":"d6604c2f704ba787c9ffea4e9eac9895399e9f267584fd4b8b630e3364ebfd8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:56.921230Z","signature_b64":"QLDVvmW06j8RlAoJwTsmeQR9Uc7TTtRLjjlvUn+CJz5Ir2vYjY+tXYEop6RL3M3+WaHidEoW/BWBZ+h37o1IAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f0bb0faf2a46ce59e7a089bff5e0b196e1893ead60c2a575bebd58f356770c3","last_reissued_at":"2026-07-05T06:18:56.920720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:56.920720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.HC"],"primary_cat":"cs.CV","authors_text":"Bo Li, Chunyuan Li, Fanyi Pu, Jinghao Wang, Jingkang Yang, Liangyu Chen, Yuanhan Zhang, Ziwei Liu","submitted_at":"2023-06-08T17:59:56Z","abstract_excerpt":"High-quality instructions and responses are essential for the zero-shot performance of large language models on interactive natural language tasks. For interactive vision-language tasks involving intricate visual scenes, a large quantity of diverse and creative instruction-response pairs should be imperative to tune vision-language models (VLMs). Nevertheless, the current availability of vision-language instruction-response pairs in terms of quantity, diversity, and creativity remains limited, posing challenges to the generalization of interactive VLMs. Here we present MultI-Modal In-Context I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05425","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/2306.05425/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":"2306.05425","created_at":"2026-07-05T06:18:56.920781+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05425v1","created_at":"2026-07-05T06:18:56.920781+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05425","created_at":"2026-07-05T06:18:56.920781+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4F3B6XSURWO","created_at":"2026-07-05T06:18:56.920781+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4F3B6XSURWOLHT2","created_at":"2026-07-05T06:18:56.920781+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4F3B6XS","created_at":"2026-07-05T06:18:56.920781+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25325","citing_title":"Omni-Perception Policy Optimization for Multimodal Emotion Reasoning","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2406.14194","citing_title":"VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2410.14702","citing_title":"Polymath: A Challenging Multi-modal Mathematical Reasoning Benchmark","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17726","citing_title":"Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15711","citing_title":"EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18962","citing_title":"UniMind: Unleashing the Power of LLMs for Unified Multi-Task Brain Decoding","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2311.07575","citing_title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14624","citing_title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":174,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15947","citing_title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14396","citing_title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06942","citing_title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2409.17146","citing_title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2308.01390","citing_title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2310.03744","citing_title":"Improved Baselines with Visual Instruction Tuning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2407.07895","citing_title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13394","citing_title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13403","citing_title":"Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4F3B6XSURWOLHT2BCN76XQLDF","json":"https://pith.science/pith/F4F3B6XSURWOLHT2BCN76XQLDF.json","graph_json":"https://pith.science/api/pith-number/F4F3B6XSURWOLHT2BCN76XQLDF/graph.json","events_json":"https://pith.science/api/pith-number/F4F3B6XSURWOLHT2BCN76XQLDF/events.json","paper":"https://pith.science/paper/F4F3B6XS"},"agent_actions":{"view_html":"https://pith.science/pith/F4F3B6XSURWOLHT2BCN76XQLDF","download_json":"https://pith.science/pith/F4F3B6XSURWOLHT2BCN76XQLDF.json","view_paper":"https://pith.science/paper/F4F3B6XS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05425&json=true","fetch_graph":"https://pith.science/api/pith-number/F4F3B6XSURWOLHT2BCN76XQLDF/graph.json","fetch_events":"https://pith.science/api/pith-number/F4F3B6XSURWOLHT2BCN76XQLDF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4F3B6XSURWOLHT2BCN76XQLDF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4F3B6XSURWOLHT2BCN76XQLDF/action/storage_attestation","attest_author":"https://pith.science/pith/F4F3B6XSURWOLHT2BCN76XQLDF/action/author_attestation","sign_citation":"https://pith.science/pith/F4F3B6XSURWOLHT2BCN76XQLDF/action/citation_signature","submit_replication":"https://pith.science/pith/F4F3B6XSURWOLHT2BCN76XQLDF/action/replication_record"}},"created_at":"2026-07-05T06:18:56.920781+00:00","updated_at":"2026-07-05T06:18:56.920781+00:00"}