{"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/do-vision-and-language-encoders-represent-the","title":"Do Vision and Language Encoders Represent the World Similarly?","arxiv_id":"2401.05224","date":"2024-01-10","proceeding":"CVPR 2024 1","authors":["Mayug Maniparambil","Raiymbek Akshulakov","Yasser Abdelaziz Dahou Djilali","Sanath Narayan","Mohamed El Amine Seddik","Karttikeya Mangalam","Noel E. O'Connor"],"abstract":"Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their respective domains. This raises a central question: does an alignment exist between uni-modal vision and language encoders since they fundamentally represent the same physical world? Analyzing the latent spaces structure of vision and language models on image-caption benchmarks using the Centered Kernel Alignment (CKA), we find that the representation spaces of unaligned and aligned encoders are semantically similar. In the absence of statistical similarity in aligned encoders like CLIP, we show that a possible matching of unaligned encoders exists without any training. We frame this as a seeded graph-matching problem exploiting the semantic similarity between graphs and propose two methods - a Fast Quadratic Assignment Problem optimization, and a novel localized CKA metric-based matching/retrieval. We demonstrate the effectiveness of this on several downstream tasks including cross-lingual, cross-domain caption matching and image classification. Code available at github.com/mayug/0-shot-llm-vision.","url_abs":"https://arxiv.org/abs/2401.05224v2","url_pdf":"https://arxiv.org/pdf/2401.05224v2.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":"do-vision-and-language-encoders-represent-the","repo_url":"https://github.com/mayug/0-shot-llm-vision","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"graph-matching","task_name":"Graph Matching"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.05224","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.05224"}},"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":"deterministic:regex_extraction","url":"https://github.com/mayug/0-shot-llm-vision","reach":{"status":"ok"}}],"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":4,"samples":[{"code_sha256_prefix":"56eb98689a64fa44","entry":"centering","repo":"mayug/0-shot-llm-vision","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/mayug/0-shot-llm-vision/blob/HEAD/src/utils.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":"56eb98689a64fa44"}},{"code_sha256_prefix":"2cdfdbf1a6146db3","entry":"kernel_HSIC","repo":"mayug/0-shot-llm-vision","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/mayug/0-shot-llm-vision/blob/HEAD/src/utils.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":"2cdfdbf1a6146db3"}},{"code_sha256_prefix":"2f7bc86a29367d01","entry":"rbf","repo":"mayug/0-shot-llm-vision","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/mayug/0-shot-llm-vision/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2f7bc86a29367d01"}},{"code_sha256_prefix":"f40c7670988619a9","entry":"get_dataset","repo":"mayug/0-shot-llm-vision","repo_kind":"official","path":"get_embeds.py","file_url":"https://github.com/mayug/0-shot-llm-vision/blob/HEAD/get_embeds.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":"f40c7670988619a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}