{"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/zoomeye-enhancing-multimodal-llms-with-human","title":"ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration","arxiv_id":"2411.16044","date":"2024-11-25","proceeding":null,"authors":["Haozhan Shen","Kangjia Zhao","Tiancheng Zhao","Ruochen Xu","Zilun Zhang","Mingwei Zhu","Jianwei Yin"],"abstract":"An image, especially with high-resolution, typically consists of numerous visual elements, ranging from dominant large objects to fine-grained detailed objects. When perceiving such images, multimodal large language models~(MLLMs) face limitations due to the restricted input resolution of the pretrained vision encoder and the cluttered, dense context of the image, resulting in a focus on primary objects while easily overlooking detailed ones. In this paper, we propose Zoom Eye, a tree search algorithm designed to navigate the hierarchical and visual nature of images to capture relevant information. Zoom Eye conceptualizes an image as a tree, with each children node representing a zoomed sub-patch of the parent node and the root represents the overall image. Moreover, Zoom Eye is model-agnostic and training-free, so it enables any MLLMs to simulate human zooming actions by searching along the image tree from root to leaf nodes, seeking out pertinent information, and accurately responding to related queries. We experiment on a series of elaborate high-resolution benchmarks and the results demonstrate that Zoom Eye not only consistently improves the performance of a series base MLLMs with large margin~(e.g., LLaVA-v1.5-7B increases by 34.57\\% on $V^*$ Bench and 17.88\\% on HR-Bench), but also enables small 7B MLLMs to outperform strong large models such as GPT-4o. Our code is available at \\href{https://github.com/om-ai-lab/ZoomEye}{https://github.com/om-ai-lab/ZoomEye}.","url_abs":"https://arxiv.org/abs/2411.16044v1","url_pdf":"https://arxiv.org/pdf/2411.16044v1.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":"zoomeye-enhancing-multimodal-llms-with-human","repo_url":"https://github.com/om-ai-lab/ZoomEye","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"ai-agent","task_name":"AI Agent"},{"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":"base","method_name":"BASE"},{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-v-bench","task":"Visual Question Answering","dataset":"V*bench","model":"LLaVA-OneVision7B w. ZoomEye","rank_in_archive_order":2,"of":5,"metrics":{"Accuracy":"90.58"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2411.16044","atlas_url":"https://app.syntology.ai/?focus=2411.16044","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.16044"}},"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/om-ai-lab/ZoomEye","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"92fb7d9bf1f30bda","entry":"get_basename","repo":"om-ai-lab/ZoomEye","repo_kind":"official","path":"ZoomEye/eval/perform_zoom_eye.py","file_url":"https://github.com/om-ai-lab/ZoomEye/blob/HEAD/ZoomEye/eval/perform_zoom_eye.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"92fb7d9bf1f30bda"}},{"code_sha256_prefix":"d61cdd0662f59fed","entry":"get_chunk","repo":"om-ai-lab/ZoomEye","repo_kind":"official","path":"ZoomEye/eval/perform_zoom_eye.py","file_url":"https://github.com/om-ai-lab/ZoomEye/blob/HEAD/ZoomEye/eval/perform_zoom_eye.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d61cdd0662f59fed"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}