{"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/exploring-perceptual-limitation-of-multimodal","title":"Exploring Perceptual Limitation of Multimodal Large Language Models","arxiv_id":"2402.07384","date":"2024-02-12","proceeding":null,"authors":["Jiarui Zhang","Jinyi Hu","Mahyar Khayatkhoei","Filip Ilievski","Maosong Sun"],"abstract":"Multimodal Large Language Models (MLLMs) have recently shown remarkable perceptual capability in answering visual questions, however, little is known about the limits of their perception. In particular, while prior works have provided anecdotal evidence of MLLMs' sensitivity to object size, this phenomenon and its underlying causes have not been explored comprehensively. In this work, we quantitatively study the perception of small visual objects in several state-of-the-art MLLMs and reveal a pervasive limitation in answering questions about small objects in images. Next, we identify four independent factors that can contribute to this limitation -- object quality, size, distractors, and location -- and conduct controlled intervention studies to measure the effect of each factor on MLLMs' perception. In particular, we find that lower object quality and smaller object size can both independently reduce MLLMs' ability to answer visual questions. More surprisingly, we find that the location of the object in the image and the presence of visual distractors can also significantly reduce MLLMs' question answering accuracy. Our study provides a better understanding of the perceptual limitation of MLLMs and contributes new evaluation protocols for analyzing the perception of future MLLMs. To facilitate further investigations, we release our code and data.","url_abs":"https://arxiv.org/abs/2402.07384v1","url_pdf":"https://arxiv.org/pdf/2402.07384v1.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":"exploring-perceptual-limitation-of-multimodal","repo_url":"https://github.com/saccharomycetes/mllm-perceptual-limitation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.07384","atlas_url":"https://app.syntology.ai/?focus=2402.07384","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.07384"}},"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/saccharomycetes/mllm-perceptual-limitation","reach":{"status":"ok"}}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":3,"samples":[{"code_sha256_prefix":"0958e86d7a9c84fe","entry":"generate_unique_numbers","repo":"saccharomycetes/mllm-perceptual-limitation","repo_kind":"official","path":"creation.py","file_url":"https://github.com/saccharomycetes/mllm-perceptual-limitation/blob/HEAD/creation.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":"0958e86d7a9c84fe"}},{"code_sha256_prefix":"cbdb11e2d93e6708","entry":"draw_text","repo":"saccharomycetes/mllm-perceptual-limitation","repo_kind":"official","path":"creation.py","file_url":"https://github.com/saccharomycetes/mllm-perceptual-limitation/blob/HEAD/creation.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":"cbdb11e2d93e6708"}},{"code_sha256_prefix":"0a6c3693d2d3a8bb","entry":"load_model","repo":"saccharomycetes/mllm-perceptual-limitation","repo_kind":"official","path":"src/models.py","file_url":"https://github.com/saccharomycetes/mllm-perceptual-limitation/blob/HEAD/src/models.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":"0a6c3693d2d3a8bb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}