{"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/all-in-a-single-image-large-multimodal-models","title":"All in an Aggregated Image for In-Image Learning","arxiv_id":"2402.17971","date":"2024-02-28","proceeding":null,"authors":["Lei Wang","Wanyu Xu","Zhiqiang Hu","Yihuai Lan","Shan Dong","Hao Wang","Roy Ka-Wei Lee","Ee-Peng Lim"],"abstract":"This paper introduces a new in-context learning (ICL) mechanism called In-Image Learning (I$^2$L) that combines demonstration examples, visual cues, and chain-of-thought reasoning into an aggregated image to enhance the capabilities of Large Multimodal Models (e.g., GPT-4V) in multimodal reasoning tasks. Unlike previous approaches that rely on converting images to text or incorporating visual input into language models, I$^2$L consolidates all information into an aggregated image and leverages image processing, understanding, and reasoning abilities. This has several advantages: it reduces inaccurate textual descriptions of complex images, provides flexibility in positioning demonstration examples, and avoids multiple input images and lengthy prompts. We also introduce I$^2$L-Hybrid, a method that combines the strengths of I$^2$L with other ICL methods. Specifically, it uses an automatic strategy to select the most suitable method (I$^2$L or another certain ICL method) for a specific task instance. We conduct extensive experiments to assess the effectiveness of I$^2$L and I$^2$L-Hybrid on MathVista, which covers a variety of complex multimodal reasoning tasks. Additionally, we investigate the influence of image resolution, the number of demonstration examples in a single image, and the positions of these demonstrations in the aggregated image on the effectiveness of I$^2$L. Our code is publicly available at https://github.com/AGI-Edgerunners/IIL.","url_abs":"https://arxiv.org/abs/2402.17971v2","url_pdf":"https://arxiv.org/pdf/2402.17971v2.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":"all-in-a-single-image-large-multimodal-models","repo_url":"https://github.com/agi-edgerunners/iil","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"all","task_name":"All"},{"task_slug":"hallucination","task_name":"Hallucination"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.17971","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}