{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EXLCQCNEKLTKZELHJSQHJDQ5YC","short_pith_number":"pith:EXLCQCNE","schema_version":"1.0","canonical_sha256":"25d62809a452e6ac91674ca0748e1dc094b385ad72923e3828febcfba8cf321f","source":{"kind":"arxiv","id":"2303.04671","version":1},"attestation_state":"computed","paper":{"title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Visual ChatGPT lets users chat with images by linking ChatGPT to visual foundation models through prompts.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenfei Wu, Nan Duan, Shengming Yin, Weizhen Qi, Xiaodong Wang, Zecheng Tang","submitted_at":"2023-03-08T15:50:02Z","abstract_excerpt":"ChatGPT is attracting a cross-field interest as it provides a language interface with remarkable conversational competency and reasoning capabilities across many domains. However, since ChatGPT is trained with languages, it is currently not capable of processing or generating images from the visual world. At the same time, Visual Foundation Models, such as Visual Transformers or Stable Diffusion, although showing great visual understanding and generation capabilities, they are only experts on specific tasks with one-round fixed inputs and outputs. To this end, We build a system called \\textbf{"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2303.04671","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-08T15:50:02Z","cross_cats_sorted":[],"title_canon_sha256":"990bdc7e3e647b036962fbb157f950c841665d609e987e7d95d9fedb63867a44","abstract_canon_sha256":"eee4f9578aa0ad14064cdf31d8f7c34541abf7367a11f22bab2cab92b014d4f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:00:28.485484Z","signature_b64":"NLsWVZ8qZ3+38fOUYZJy6eMynVfirWzPfyRUp+VTGoc5hUor4XSmP8wVJ9e5AaXSre4J3IIkJrg0/IiHBfNfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25d62809a452e6ac91674ca0748e1dc094b385ad72923e3828febcfba8cf321f","last_reissued_at":"2026-05-18T04:00:28.484742Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:00:28.484742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Visual ChatGPT lets users chat with images by linking ChatGPT to visual foundation models through prompts.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenfei Wu, Nan Duan, Shengming Yin, Weizhen Qi, Xiaodong Wang, Zecheng Tang","submitted_at":"2023-03-08T15:50:02Z","abstract_excerpt":"ChatGPT is attracting a cross-field interest as it provides a language interface with remarkable conversational competency and reasoning capabilities across many domains. However, since ChatGPT is trained with languages, it is currently not capable of processing or generating images from the visual world. At the same time, Visual Foundation Models, such as Visual Transformers or Stable Diffusion, although showing great visual understanding and generation capabilities, they are only experts on specific tasks with one-round fixed inputs and outputs. To this end, We build a system called \\textbf{"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We build a system called Visual ChatGPT, incorporating different Visual Foundation Models, to enable the user to interact with ChatGPT by 1) sending and receiving not only languages but also images 2) providing complex visual questions or visual editing instructions that require the collaboration of multiple AI models with multi-steps.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That prompt-based injection of visual model capabilities into ChatGPT enables reliable multi-step collaboration without frequent errors in task decomposition or model selection.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Visual ChatGPT integrates visual foundation models with ChatGPT via prompts to enable multi-step image understanding, generation, and editing in conversational interactions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Visual ChatGPT lets users chat with images by linking ChatGPT to visual foundation models through prompts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5f333e5e5df926a0260980b6126e0f036c3ff09b2748a6e0f927dba23873a111"},"source":{"id":"2303.04671","kind":"arxiv","version":1},"verdict":{"id":"be73130e-f746-4664-9b0e-2a5ad3d993da","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T22:46:45.409554Z","strongest_claim":"We build a system called Visual ChatGPT, incorporating different Visual Foundation Models, to enable the user to interact with ChatGPT by 1) sending and receiving not only languages but also images 2) providing complex visual questions or visual editing instructions that require the collaboration of multiple AI models with multi-steps.","one_line_summary":"Visual ChatGPT integrates visual foundation models with ChatGPT via prompts to enable multi-step image understanding, generation, and editing in conversational interactions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That prompt-based injection of visual model capabilities into ChatGPT enables reliable multi-step collaboration without frequent errors in task decomposition or model selection.","pith_extraction_headline":"Visual ChatGPT lets users chat with images by linking ChatGPT to visual foundation models through prompts."},"references":{"count":58,"sample":[{"doi":"","year":2022,"title":"Flamingo: a visual language model for few-shot learning","work_id":"059e2edb-7251-4c10-907e-c021375c785d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Vqa: Visual question answering","work_id":"cbdd1a33-3045-4f80-9a99-f0866c9fa2ac","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Vlmo: Unified vision-language pre- training with mixture-of-modality-experts","work_id":"bbdebaac-4da3-44ee-92f1-4125efdfe5d8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"In- structpix2pix: Learning to follow image editing instructions","work_id":"de9c4a95-36ff-4e97-a0c0-3cca39f60b1a","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1901,"title":"Lan- guage models are few-shot learners","work_id":"586b225f-281e-4de8-8c7c-dd02e7091ca8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":58,"snapshot_sha256":"0733ffc7970d1b55320fd6d78169072f7d61c0e58b284ff49a25dcd6e4707bcb","internal_anchors":9},"formal_canon":{"evidence_count":2,"snapshot_sha256":"9fb0d4a413c47666296c1d5c3b50d42c6c7f8c57ba9ea500973266d9df332940"},"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":"2303.04671","created_at":"2026-05-18T04:00:28.484866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.04671v1","created_at":"2026-05-18T04:00:28.484866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04671","created_at":"2026-05-18T04:00:28.484866+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXLCQCNEKLTK","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXLCQCNEKLTKZELH","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXLCQCNE","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":45,"internal_anchor_count":45,"sample":[{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":222,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22177","citing_title":"Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2505.23678","citing_title":"Grounded Reinforcement Learning for Visual Reasoning","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2506.05442","citing_title":"Structured Labeling Enables Faster Vision-Language Models for End-to-End Autonomous Driving","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16409","citing_title":"Multilingual OCR-Aware Fine-Tuning and Prompt-Guided Chain-of-Thought Reasoning for Multimodal Large Language Models","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19528","citing_title":"Towards Camera-Robust 3D Localization: Equation-Anchored Tool-Use for MLLMs","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":289,"is_internal_anchor":true},{"citing_arxiv_id":"2506.11989","citing_title":"Thought Graph Traversal for Test-time Scaling in Chest X-ray VLLMs","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2506.20911","citing_title":"FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2409.07825","citing_title":"Deep Multimodal Learning with Missing Modality: A Survey","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2403.18814","citing_title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","ref_index":34,"is_internal_anchor":true},{"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":36,"is_internal_anchor":true},{"citing_arxiv_id":"2403.00476","citing_title":"TempCompass: Do Video LLMs Really Understand Videos?","ref_index":124,"is_internal_anchor":true},{"citing_arxiv_id":"2401.16158","citing_title":"Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":191,"is_internal_anchor":true},{"citing_arxiv_id":"2309.17421","citing_title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","ref_index":137,"is_internal_anchor":true},{"citing_arxiv_id":"2602.22683","citing_title":"SUPERGLASSES: Benchmarking Vision Language Models as Intelligent Agents for AI Smart Glasses","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2603.01400","citing_title":"Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2305.18323","citing_title":"ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Models","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2304.15010","citing_title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2311.10122","citing_title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2303.11381","citing_title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2305.06355","citing_title":"VideoChat: Chat-Centric Video Understanding","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2312.14238","citing_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","ref_index":156,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03156","citing_title":"CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXLCQCNEKLTKZELHJSQHJDQ5YC","json":"https://pith.science/pith/EXLCQCNEKLTKZELHJSQHJDQ5YC.json","graph_json":"https://pith.science/api/pith-number/EXLCQCNEKLTKZELHJSQHJDQ5YC/graph.json","events_json":"https://pith.science/api/pith-number/EXLCQCNEKLTKZELHJSQHJDQ5YC/events.json","paper":"https://pith.science/paper/EXLCQCNE"},"agent_actions":{"view_html":"https://pith.science/pith/EXLCQCNEKLTKZELHJSQHJDQ5YC","download_json":"https://pith.science/pith/EXLCQCNEKLTKZELHJSQHJDQ5YC.json","view_paper":"https://pith.science/paper/EXLCQCNE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.04671&json=true","fetch_graph":"https://pith.science/api/pith-number/EXLCQCNEKLTKZELHJSQHJDQ5YC/graph.json","fetch_events":"https://pith.science/api/pith-number/EXLCQCNEKLTKZELHJSQHJDQ5YC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXLCQCNEKLTKZELHJSQHJDQ5YC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXLCQCNEKLTKZELHJSQHJDQ5YC/action/storage_attestation","attest_author":"https://pith.science/pith/EXLCQCNEKLTKZELHJSQHJDQ5YC/action/author_attestation","sign_citation":"https://pith.science/pith/EXLCQCNEKLTKZELHJSQHJDQ5YC/action/citation_signature","submit_replication":"https://pith.science/pith/EXLCQCNEKLTKZELHJSQHJDQ5YC/action/replication_record"}},"created_at":"2026-05-18T04:00:28.484866+00:00","updated_at":"2026-05-18T04:00:28.484866+00:00"}