{"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/generative-multimodal-models-are-in-context","title":"Generative Multimodal Models are In-Context Learners","arxiv_id":"2312.13286","date":"2023-12-20","proceeding":"CVPR 2024 1","authors":["Quan Sun","Yufeng Cui","Xiaosong Zhang","Fan Zhang","Qiying Yu","Zhengxiong Luo","Yueze Wang","Yongming Rao","Jingjing Liu","Tiejun Huang","Xinlong Wang"],"abstract":"The human ability to easily solve multimodal tasks in context (i.e., with only a few demonstrations or simple instructions), is what current multimodal systems have largely struggled to imitate. In this work, we demonstrate that the task-agnostic in-context learning capabilities of large multimodal models can be significantly enhanced by effective scaling-up. We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences with a unified autoregressive objective. Emu2 exhibits strong multimodal in-context learning abilities, even emerging to solve tasks that require on-the-fly reasoning, such as visual prompting and object-grounded generation. The model sets a new record on multiple multimodal understanding tasks in few-shot settings. When instruction-tuned to follow specific instructions, Emu2 further achieves new state-of-the-art on challenging tasks such as question answering benchmarks for large multimodal models and open-ended subject-driven generation. These achievements demonstrate that Emu2 can serve as a base model and general-purpose interface for a wide range of multimodal tasks. Code and models are publicly available to facilitate future research.","url_abs":"https://arxiv.org/abs/2312.13286v2","url_pdf":"https://arxiv.org/pdf/2312.13286v2.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":"generative-multimodal-models-are-in-context","repo_url":"https://github.com/baaivision/emu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"personalized-image-generation","task_name":"Personalized Image Generation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-prompting","task_name":"Visual Prompting"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/personalized-image-generation-on-dreambench","task":"Personalized Image Generation","dataset":"DreamBooth","model":"Emu2 SDXL v1.0","rank_in_archive_order":3,"of":7,"metrics":{"Concept Preservation (CP)":"0.528","Overall (CP * PF)":"0.364","Prompt Following (PF)":"0.690"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"Emu2-Chat","rank_in_archive_order":75,"of":231,"metrics":{"GPT-4 score":"48.5","Params":"37B"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet-v2","task":"Visual Question Answering","dataset":"MM-Vet v2","model":"Emu2-Chat","rank_in_archive_order":19,"of":24,"metrics":{"GPT-4 score":"38.0±0.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2312.13286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.13286"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/baaivision/emu","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":3,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"2447be83c878aab2","entry":"prepare_generation_data","repo":"baaivision/emu","repo_kind":"official","path":"Emu1/mm_eval/models/emu.py","file_url":"https://github.com/baaivision/emu/blob/HEAD/Emu1/mm_eval/models/emu.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2447be83c878aab2"}},{"code_sha256_prefix":"fafe51cab4281693","entry":"prepare_prediction_data","repo":"baaivision/emu","repo_kind":"official","path":"Emu1/mm_eval/models/emu.py","file_url":"https://github.com/baaivision/emu/blob/HEAD/Emu1/mm_eval/models/emu.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fafe51cab4281693"}},{"code_sha256_prefix":"fe8b1e61f82d575d","entry":"process_img","repo":"baaivision/emu","repo_kind":"official","path":"Emu1/mm_eval/models/emu.py","file_url":"https://github.com/baaivision/emu/blob/HEAD/Emu1/mm_eval/models/emu.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fe8b1e61f82d575d"}},{"code_sha256_prefix":"8daadb5960abfb12","entry":"add_location_symbols","repo":"baaivision/emu","repo_kind":"official","path":"Emu2/emu/lm.py","file_url":"https://github.com/baaivision/emu/blob/HEAD/Emu2/emu/lm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8daadb5960abfb12"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}