{"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/vl-icl-bench-the-devil-in-the-details-of","title":"VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning","arxiv_id":"2403.13164","date":"2024-03-19","proceeding":null,"authors":["Yongshuo Zong","Ondrej Bohdal","Timothy Hospedales"],"abstract":"Large language models (LLMs) famously exhibit emergent in-context learning (ICL) -- the ability to rapidly adapt to new tasks using few-shot examples provided as a prompt, without updating the model's weights. Built on top of LLMs, vision large language models (VLLMs) have advanced significantly in areas such as recognition, reasoning, and grounding. However, investigations into \\emph{multimodal ICL} have predominantly focused on few-shot visual question answering (VQA), and image captioning, which we will show neither exploit the strengths of ICL, nor test its limitations. The broader capabilities and limitations of multimodal ICL remain under-explored. In this study, we introduce a comprehensive benchmark VL-ICL Bench for multimodal in-context learning, encompassing a broad spectrum of tasks that involve both images and text as inputs and outputs, and different types of challenges, from {perception to reasoning and long context length}. We evaluate the abilities of state-of-the-art VLLMs against this benchmark suite, revealing their diverse strengths and weaknesses, and showing that even the most advanced models, such as GPT-4, find the tasks challenging. By highlighting a range of new ICL tasks, and the associated strengths and limitations of existing models, we hope that our dataset will inspire future work on enhancing the in-context learning capabilities of VLLMs, as well as inspire new applications that leverage VLLM ICL. The code and dataset are available at https://github.com/ys-zong/VL-ICL.","url_abs":"https://arxiv.org/abs/2403.13164v4","url_pdf":"https://arxiv.org/pdf/2403.13164v4.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":"vl-icl-bench-the-devil-in-the-details-of","repo_url":"https://github.com/ys-zong/vl-icl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.13164","atlas_url":"https://app.syntology.ai/?focus=2403.13164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13164"}},"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/ys-zong/vl-icl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":6,"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":"d1db96fcb77d3b5f","entry":"coco_id_to_imgname","repo":"ys-zong/vl-icl","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/ys-zong/vl-icl/blob/HEAD/utils/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d1db96fcb77d3b5f"}},{"code_sha256_prefix":"6908e3a4a22ac1b2","entry":"format_answer","repo":"ys-zong/vl-icl","repo_kind":"official","path":"utils/ICL_utils.py","file_url":"https://github.com/ys-zong/vl-icl/blob/HEAD/utils/ICL_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6908e3a4a22ac1b2"}},{"code_sha256_prefix":"c5402088fb8f3686","entry":"get_task_instruction","repo":"ys-zong/vl-icl","repo_kind":"official","path":"utils/ICL_utils.py","file_url":"https://github.com/ys-zong/vl-icl/blob/HEAD/utils/ICL_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c5402088fb8f3686"}},{"code_sha256_prefix":"2a0bf8b452c624f0","entry":"load_image","repo":"ys-zong/vl-icl","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/ys-zong/vl-icl/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a0bf8b452c624f0"}},{"code_sha256_prefix":"79f8918d0e4fd3f2","entry":"select_demonstration","repo":"ys-zong/vl-icl","repo_kind":"official","path":"utils/ICL_utils.py","file_url":"https://github.com/ys-zong/vl-icl/blob/HEAD/utils/ICL_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"79f8918d0e4fd3f2"}},{"code_sha256_prefix":"d55cfede35824b77","entry":"truncate_prediction","repo":"ys-zong/vl-icl","repo_kind":"official","path":"utils/utils.py","file_url":"https://github.com/ys-zong/vl-icl/blob/HEAD/utils/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d55cfede35824b77"}},{"code_sha256_prefix":"13e940c1b1f7fede","entry":"ICL_I2T_inference","repo":"ys-zong/vl-icl","repo_kind":"official","path":"utils/model_inference.py","file_url":"https://github.com/ys-zong/vl-icl/blob/HEAD/utils/model_inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"13e940c1b1f7fede"}},{"code_sha256_prefix":"feb3b59ad50d25a9","entry":"ICL_T2I_inference","repo":"ys-zong/vl-icl","repo_kind":"official","path":"utils/model_inference.py","file_url":"https://github.com/ys-zong/vl-icl/blob/HEAD/utils/model_inference.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"feb3b59ad50d25a9"}},{"code_sha256_prefix":"f635b601c6d366e4","entry":"load_i2t_model","repo":"ys-zong/vl-icl","repo_kind":"official","path":"utils/load_models.py","file_url":"https://github.com/ys-zong/vl-icl/blob/HEAD/utils/load_models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f635b601c6d366e4"}},{"code_sha256_prefix":"76f7942df9f8c3a3","entry":"load_t2i_model","repo":"ys-zong/vl-icl","repo_kind":"official","path":"utils/load_models.py","file_url":"https://github.com/ys-zong/vl-icl/blob/HEAD/utils/load_models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"76f7942df9f8c3a3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}