{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZHEFC2KKLLCJRGFE5VWC6DGJBI","short_pith_number":"pith:ZHEFC2KK","schema_version":"1.0","canonical_sha256":"c9c851694a5ac49898a4ed6c2f0cc90a00c39484acf14c1c2b6336315bebe366","source":{"kind":"arxiv","id":"2309.07915","version":3},"attestation_state":"computed","paper":{"title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Baobao Chang, Haozhe Zhao, Kaikai An, Liang Chen, Sheng Wang, Shuzheng Si, Wenjuan Han, Xiaojian Ma, Zefan Cai, Zixuan Liu","submitted_at":"2023-09-14T17:59:17Z","abstract_excerpt":"Since the resurgence of deep learning, vision-language models (VLMs) enhanced by large language models (LLMs) have grown exponentially in popularity. However, while LLMs can utilize extensive background knowledge and task information with in-context learning, most VLMs still struggle with understanding complex multi-modal prompts with multiple images, making VLMs less effective in downstream vision-language tasks. In this paper, we address the limitation above by 1) introducing vision-language Model with Multi-Modal In-Context Learning(MMICL), a new approach to allow the VLM to deal with multi"},"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":"2309.07915","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T17:59:17Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"0d54a22fc0362d121c62f3855c2b71883a62f96a2f7619dc48203ae8ac1f8621","abstract_canon_sha256":"6a3df6485f745010bd2ee241a1460167bddb9c4eafeccae28c72d31292127d49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:23.136649Z","signature_b64":"j1ls2hYvIjCtYendqhsrZJkLb9mGQ1W2m8uCtW5ghIu+VfVI1hyZ8Or7gOu3OKD5SkjXBKyRHyPbgR0jnm0NDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9c851694a5ac49898a4ed6c2f0cc90a00c39484acf14c1c2b6336315bebe366","last_reissued_at":"2026-07-05T07:58:23.136138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:23.136138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Baobao Chang, Haozhe Zhao, Kaikai An, Liang Chen, Sheng Wang, Shuzheng Si, Wenjuan Han, Xiaojian Ma, Zefan Cai, Zixuan Liu","submitted_at":"2023-09-14T17:59:17Z","abstract_excerpt":"Since the resurgence of deep learning, vision-language models (VLMs) enhanced by large language models (LLMs) have grown exponentially in popularity. However, while LLMs can utilize extensive background knowledge and task information with in-context learning, most VLMs still struggle with understanding complex multi-modal prompts with multiple images, making VLMs less effective in downstream vision-language tasks. In this paper, we address the limitation above by 1) introducing vision-language Model with Multi-Modal In-Context Learning(MMICL), a new approach to allow the VLM to deal with multi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07915","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/2309.07915/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":"2309.07915","created_at":"2026-07-05T07:58:23.136205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.07915v3","created_at":"2026-07-05T07:58:23.136205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07915","created_at":"2026-07-05T07:58:23.136205+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHEFC2KKLLCJ","created_at":"2026-07-05T07:58:23.136205+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHEFC2KKLLCJRGFE","created_at":"2026-07-05T07:58:23.136205+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHEFC2KK","created_at":"2026-07-05T07:58:23.136205+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12744","citing_title":"GRIP: Feedback-Guided Prompt Retrieval for Large Multimodal Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11853","citing_title":"Task-Aware Structured Memory for Dynamic Multi-modal In-Context Learning","ref_index":199,"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":270,"is_internal_anchor":false},{"citing_arxiv_id":"2309.15112","citing_title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2312.13771","citing_title":"AppAgent: Multimodal Agents as Smartphone Users","ref_index":46,"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":42,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23365","citing_title":"SpatialMosaic: A Multiview VLM Dataset for Partial Visibility","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":178,"is_internal_anchor":false},{"citing_arxiv_id":"2311.16502","citing_title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2305.03726","citing_title":"Otter: A Multi-Modal Model with In-Context Instruction Tuning","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02813","citing_title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2404.18930","citing_title":"Hallucination of Multimodal Large Language Models: A Survey","ref_index":215,"is_internal_anchor":false},{"citing_arxiv_id":"2306.13394","citing_title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","ref_index":61,"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":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18562","citing_title":"AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation","ref_index":172,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI","json":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI.json","graph_json":"https://pith.science/api/pith-number/ZHEFC2KKLLCJRGFE5VWC6DGJBI/graph.json","events_json":"https://pith.science/api/pith-number/ZHEFC2KKLLCJRGFE5VWC6DGJBI/events.json","paper":"https://pith.science/paper/ZHEFC2KK"},"agent_actions":{"view_html":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI","download_json":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI.json","view_paper":"https://pith.science/paper/ZHEFC2KK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.07915&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHEFC2KKLLCJRGFE5VWC6DGJBI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHEFC2KKLLCJRGFE5VWC6DGJBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI/action/storage_attestation","attest_author":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI/action/author_attestation","sign_citation":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI/action/citation_signature","submit_replication":"https://pith.science/pith/ZHEFC2KKLLCJRGFE5VWC6DGJBI/action/replication_record"}},"created_at":"2026-07-05T07:58:23.136205+00:00","updated_at":"2026-07-05T07:58:23.136205+00:00"}