{"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/longprolip-a-probabilistic-vision-language","title":"LongProLIP: A Probabilistic Vision-Language Model with Long Context Text","arxiv_id":"2503.08048","date":"2025-03-11","proceeding":null,"authors":["Sanghyuk Chun","Sangdoo Yun"],"abstract":"Recently, Probabilistic Language-Image Pre-Training (ProLIP) has been proposed to tackle the multiplicity issue of vision-language (VL) tasks. Despite their success in probabilistic representation learning at a scale, the ProLIP models cannot handle long context texts longer than 64 context length, which limits their ability to capture rich contextual information from longer text sequences. To address this issue, this paper proposes a fine-tuning strategy for ProLIP to accept longer texts, e.g., 256 text tokens. Experimental results on Urban-1k and the DataComp evaluation suite show that the proposed LongProLIP recipe can improve understanding of long contexts while minimizing the negative effect of fine-tuning.We also observe a trade-off between the long context understanding (measured by Urban-1k) and general zero-shot capability (measured by evaluation datasets by DataComp). Code is available at https://github.com/naver-ai/prolip","url_abs":"https://arxiv.org/abs/2503.08048v2","url_pdf":"https://arxiv.org/pdf/2503.08048v2.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":"longprolip-a-probabilistic-vision-language","repo_url":"https://github.com/naver-ai/prolip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"long-context-understanding","task_name":"Long-Context Understanding"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.08048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.08048"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/naver-ai/prolip","reach":null}],"summary":{"ran":1,"ran_draft_wrong":5,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":11,"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":16,"samples":[{"code_sha256_prefix":"022a5391f0e240ca","entry":"ResidualAttentionBlock","repo":"naver-ai/prolip","repo_kind":"official","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"022a5391f0e240ca"}},{"code_sha256_prefix":"dcd422d66b0581d8","entry":"get_cast_dtype","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"code_sha256_prefix":"4d038cd90610dfa0","entry":"get_input_dtype","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"4d038cd90610dfa0"}},{"code_sha256_prefix":"b476c8cfbf0f1f47","entry":"get_input_dtype","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b476c8cfbf0f1f47"}},{"code_sha256_prefix":"feaac0348de86b5a","entry":"get_model_preprocess_cfg","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"feaac0348de86b5a"}},{"code_sha256_prefix":"4ea5dcdf3bdde1b0","entry":"get_model_preprocess_cfg","repo":"naver-ai/prolip","repo_kind":"official","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4ea5dcdf3bdde1b0"}},{"code_sha256_prefix":"b0071d319dff7f45","entry":"text_global_pool","repo":"naver-ai/prolip","repo_kind":"official","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b0071d319dff7f45"}},{"code_sha256_prefix":"20ab228b3362392c","entry":"ProLIP","repo":"naver-ai/prolip","repo_kind":"official","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"20ab228b3362392c"}},{"code_sha256_prefix":"088887788aa71e94","entry":"ProLIPTextCfg","repo":"naver-ai/prolip","repo_kind":"official","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"088887788aa71e94"}},{"code_sha256_prefix":"56e68dadc6499c62","entry":"ProLIPVisionCfg","repo":"naver-ai/prolip","repo_kind":"official","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"56e68dadc6499c62"}},{"code_sha256_prefix":"bdb64edca7f927cb","entry":"TextTransformer","repo":"naver-ai/prolip","repo_kind":"official","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bdb64edca7f927cb"}},{"code_sha256_prefix":"5918de7404e9237b","entry":"Transformer","repo":"naver-ai/prolip","repo_kind":"official","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5918de7404e9237b"}},{"code_sha256_prefix":"84aa74aff57a00bc","entry":"VisionTransformer","repo":"naver-ai/prolip","repo_kind":"official","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"84aa74aff57a00bc"}},{"code_sha256_prefix":"c6232c0ea06aba61","entry":"_build_text_tower","repo":"naver-ai/prolip","repo_kind":"official","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c6232c0ea06aba61"}},{"code_sha256_prefix":"6631a3008026f80f","entry":"_build_vision_tower","repo":"naver-ai/prolip","repo_kind":"official","path":"src/prolip/model.py","file_url":"https://github.com/naver-ai/prolip/blob/HEAD/src/prolip/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6631a3008026f80f"}},{"code_sha256_prefix":"0529ec3d12d83d1c","entry":"get_cast_dtype","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"0529ec3d12d83d1c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}