{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KEQRYRVALBT3KP4JDPYH2TSVDD","short_pith_number":"pith:KEQRYRVA","schema_version":"1.0","canonical_sha256":"51211c46a05867b53f891bf07d4e5518da41b382fb8fbfbac0e1b10ce75a2070","source":{"kind":"arxiv","id":"2305.04790","version":3},"attestation_state":"computed","paper":{"title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chengqi Lyu, Kai Chen, Kuikun Liu, Miao Zheng, Ping Luo, Qian Zhao, Shilong Zhang, Tao Gong, Wenwei Zhang, Yudong Wang","submitted_at":"2023-05-08T15:45:42Z","abstract_excerpt":"We present a vision and language model named MultiModal-GPT to conduct multi-round dialogue with humans. MultiModal-GPT can follow various instructions from humans, such as generating a detailed caption, counting the number of interested objects, and answering general questions from users. MultiModal-GPT is parameter-efficiently fine-tuned from OpenFlamingo, with Low-rank Adapter (LoRA) added both in the cross-attention part and the self-attention part of the language model. We first construct instruction templates with vision and language data for multi-modality instruction tuning to make the"},"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":"2305.04790","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-08T15:45:42Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a8e9682d20196a48185931455ead6cf07fbcfdb3fe3dff0ba0865d3d50001a07","abstract_canon_sha256":"b29dbc7acc78ab2aa73fc9cd1b8b68dd8c50e926a88124473a2842423d19fadd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:58.754807Z","signature_b64":"HyNP9XfiFPqToCQ1H4lK4lB2bI54vWxQz5emc9tATsHhRMu5/hoxs3NDyT8LCMOhjMUXeHIQsgkcXTPDDqiaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51211c46a05867b53f891bf07d4e5518da41b382fb8fbfbac0e1b10ce75a2070","last_reissued_at":"2026-07-05T06:19:58.754373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:58.754373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiModal-GPT: A Vision and Language Model for Dialogue with Humans","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chengqi Lyu, Kai Chen, Kuikun Liu, Miao Zheng, Ping Luo, Qian Zhao, Shilong Zhang, Tao Gong, Wenwei Zhang, Yudong Wang","submitted_at":"2023-05-08T15:45:42Z","abstract_excerpt":"We present a vision and language model named MultiModal-GPT to conduct multi-round dialogue with humans. MultiModal-GPT can follow various instructions from humans, such as generating a detailed caption, counting the number of interested objects, and answering general questions from users. MultiModal-GPT is parameter-efficiently fine-tuned from OpenFlamingo, with Low-rank Adapter (LoRA) added both in the cross-attention part and the self-attention part of the language model. We first construct instruction templates with vision and language data for multi-modality instruction tuning to make the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.04790","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/2305.04790/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":"2305.04790","created_at":"2026-07-05T06:19:58.754431+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.04790v3","created_at":"2026-07-05T06:19:58.754431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.04790","created_at":"2026-07-05T06:19:58.754431+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEQRYRVALBT3","created_at":"2026-07-05T06:19:58.754431+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEQRYRVALBT3KP4J","created_at":"2026-07-05T06:19:58.754431+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEQRYRVA","created_at":"2026-07-05T06:19:58.754431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21734","citing_title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","ref_index":292,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17015","citing_title":"Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2408.12935","citing_title":"AI Safety Landscape for Large Language Models: Taxonomy, State-of-the-art, and Future Directions","ref_index":255,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18275","citing_title":"Visual Adversarial Attack on Vision-Language Models for Autonomous Driving","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13130","citing_title":"ZINA: Multimodal Fine-grained Hallucination Detection and Editing","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2311.04257","citing_title":"mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2311.17005","citing_title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2310.09478","citing_title":"MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2403.09611","citing_title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2401.15947","citing_title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2311.10122","citing_title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2306.14565","citing_title":"Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning","ref_index":8,"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":10,"is_internal_anchor":false},{"citing_arxiv_id":"2310.03744","citing_title":"Improved Baselines with Visual Instruction Tuning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2305.10355","citing_title":"Evaluating Object Hallucination in Large Vision-Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":290,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13394","citing_title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KEQRYRVALBT3KP4JDPYH2TSVDD","json":"https://pith.science/pith/KEQRYRVALBT3KP4JDPYH2TSVDD.json","graph_json":"https://pith.science/api/pith-number/KEQRYRVALBT3KP4JDPYH2TSVDD/graph.json","events_json":"https://pith.science/api/pith-number/KEQRYRVALBT3KP4JDPYH2TSVDD/events.json","paper":"https://pith.science/paper/KEQRYRVA"},"agent_actions":{"view_html":"https://pith.science/pith/KEQRYRVALBT3KP4JDPYH2TSVDD","download_json":"https://pith.science/pith/KEQRYRVALBT3KP4JDPYH2TSVDD.json","view_paper":"https://pith.science/paper/KEQRYRVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.04790&json=true","fetch_graph":"https://pith.science/api/pith-number/KEQRYRVALBT3KP4JDPYH2TSVDD/graph.json","fetch_events":"https://pith.science/api/pith-number/KEQRYRVALBT3KP4JDPYH2TSVDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEQRYRVALBT3KP4JDPYH2TSVDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEQRYRVALBT3KP4JDPYH2TSVDD/action/storage_attestation","attest_author":"https://pith.science/pith/KEQRYRVALBT3KP4JDPYH2TSVDD/action/author_attestation","sign_citation":"https://pith.science/pith/KEQRYRVALBT3KP4JDPYH2TSVDD/action/citation_signature","submit_replication":"https://pith.science/pith/KEQRYRVALBT3KP4JDPYH2TSVDD/action/replication_record"}},"created_at":"2026-07-05T06:19:58.754431+00:00","updated_at":"2026-07-05T06:19:58.754431+00:00"}