{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/mmicl-empowering-vision-language-model-with","title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","arxiv_id":"2309.07915","date":"2023-09-14","proceeding":null,"authors":["Haozhe Zhao","Zefan Cai","Shuzheng Si","Xiaojian Ma","Kaikai An","Liang Chen","Zixuan Liu","Sheng Wang","Wenjuan Han","Baobao Chang"],"abstract":"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-modal inputs efficiently; 2) proposing a novel context scheme to augment the in-context learning ability of the VLM; 3) constructing the Multi-modal In-Context Learning (MIC) dataset, designed to enhance the VLM's ability to understand complex multi-modal prompts. Our experiments confirm that MMICL achieves new state-of-the-art zero-shot performance on a wide range of general vision-language tasks, especially for complex benchmarks, including MME and MMBench. Our analysis demonstrates that MMICL effectively tackles the challenge of complex multi-modal prompt understanding and emerges the impressive ICL ability. Furthermore, we observe that MMICL successfully alleviates language bias in VLMs, a common issue for VLMs that often leads to hallucination when faced with extensive textual context. Our code, dataset, dataset tool, and model are available at https://github.com/PKUnlp-icler/MIC","url_abs":"https://arxiv.org/abs/2309.07915v3","url_pdf":"https://arxiv.org/pdf/2309.07915v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"mmicl-empowering-vision-language-model-with","repo_url":"https://github.com/haozhezhao/mic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"mmicl-empowering-vision-language-model-with","repo_url":"https://github.com/pkunlp-icler/mic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"mme","task_name":"MME"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-reasoning-on-winoground","task":"Visual Reasoning","dataset":"Winoground","model":"MMICL (FLAN-T5-XXL)","rank_in_archive_order":17,"of":114,"metrics":{"Group Score":"43.00","Image Score":"44.99","Text Score":"45.50"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.07915","atlas_url":"https://app.syntology.ai/?focus=2309.07915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.07915"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/haozhezhao/mic","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pkunlp-icler/mic","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":3,"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"9f3c4268cc75c4b0","entry":"caption_form_fewshot","repo":"haozhezhao/mic","repo_kind":"official","path":"data_preprocess.py","file_url":"https://github.com/haozhezhao/mic/blob/HEAD/data_preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9f3c4268cc75c4b0"}},{"code_sha256_prefix":"ea729b42a37729dd","entry":"create_rename_keys","repo":"pkunlp-icler/mic","repo_kind":"official","path":"model/blip2/convert_blip_2_original_to_pytorch.py","file_url":"https://github.com/pkunlp-icler/mic/blob/HEAD/model/blip2/convert_blip_2_original_to_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea729b42a37729dd"}},{"code_sha256_prefix":"1d25d223bda4a714","entry":"create_rename_keys","repo":"pkunlp-icler/mic","repo_kind":"official","path":"model/instructblip/convert_instructblip_original_to_pytorch.py","file_url":"https://github.com/pkunlp-icler/mic/blob/HEAD/model/instructblip/convert_instructblip_original_to_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d25d223bda4a714"}},{"code_sha256_prefix":"f21e2fafcf17462e","entry":"get_json_file","repo":"haozhezhao/mic","repo_kind":"official","path":"data_preprocess.py","file_url":"https://github.com/haozhezhao/mic/blob/HEAD/data_preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f21e2fafcf17462e"}},{"code_sha256_prefix":"b4e74f94de108a4a","entry":"qa_form_fewshot","repo":"haozhezhao/mic","repo_kind":"official","path":"data_preprocess.py","file_url":"https://github.com/haozhezhao/mic/blob/HEAD/data_preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4e74f94de108a4a"}},{"code_sha256_prefix":"cb9cbe1b70354960","entry":"get_blip2_config","repo":"pkunlp-icler/mic","repo_kind":"official","path":"model/blip2/convert_blip_2_original_to_pytorch.py","file_url":"https://github.com/pkunlp-icler/mic/blob/HEAD/model/blip2/convert_blip_2_original_to_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb9cbe1b70354960"}},{"code_sha256_prefix":"71369565f5232bf2","entry":"get_blip2_config","repo":"pkunlp-icler/mic","repo_kind":"official","path":"model/instructblip/convert_instructblip_original_to_pytorch.py","file_url":"https://github.com/pkunlp-icler/mic/blob/HEAD/model/instructblip/convert_instructblip_original_to_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"71369565f5232bf2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}