{"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/vision-model-pre-training-on-interleaved","title":"Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning","arxiv_id":"2406.07543","date":"2024-06-11","proceeding":null,"authors":["Chenyu Yang","Xizhou Zhu","Jinguo Zhu","Weijie Su","Junjie Wang","Xuan Dong","Wenhai Wang","Lewei Lu","Bin Li","Jie zhou","Yu Qiao","Jifeng Dai"],"abstract":"Recently, vision model pre-training has evolved from relying on manually annotated datasets to leveraging large-scale, web-crawled image-text data. Despite these advances, there is no pre-training method that effectively exploits the interleaved image-text data, which is very prevalent on the Internet. Inspired by the recent success of compression learning in natural language processing, we propose a novel vision model pre-training method called Latent Compression Learning (LCL) for interleaved image-text data. This method performs latent compression learning by maximizing the mutual information between the inputs and outputs of a causal attention model. The training objective can be decomposed into two basic tasks: 1) contrastive learning between visual representation and preceding context, and 2) generating subsequent text based on visual representation. Our experiments demonstrate that our method not only matches the performance of CLIP on paired pre-training datasets (e.g., LAION), but can also leverage interleaved pre-training data (e.g., MMC4) to learn robust visual representation from scratch, showcasing the potential of vision model pre-training with interleaved image-text data. Code is released at https://github.com/OpenGVLab/LCL.","url_abs":"https://arxiv.org/abs/2406.07543v2","url_pdf":"https://arxiv.org/pdf/2406.07543v2.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":"vision-model-pre-training-on-interleaved","repo_url":"https://github.com/opengvlab/lcl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.07543","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07543"}},"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/opengvlab/lcl","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"ran_draft_wrong":2,"ran":1,"unverified":8},"by_repo_kind":{"official":{"samples":12,"ran":4,"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":0,"samples":[{"code_sha256_prefix":"f19962ebb134b3d7","entry":"convert_to_custom_text_state_dict","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/model.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/model.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f19962ebb134b3d7"}},{"code_sha256_prefix":"dcd422d66b0581d8","entry":"get_cast_dtype","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/model.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dcd422d66b0581d8"}},{"code_sha256_prefix":"b476c8cfbf0f1f47","entry":"get_input_dtype","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/model.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/model.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b476c8cfbf0f1f47"}},{"code_sha256_prefix":"0b94bc3f6eb369a4","entry":"load_state_dict","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/factory.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/factory.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b94bc3f6eb369a4"}},{"code_sha256_prefix":"ddcbd45e940484ee","entry":"gather_features","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/loss.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ddcbd45e940484ee"}},{"code_sha256_prefix":"5c7cf820e99443ff","entry":"get_model_config","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/factory.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/factory.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c7cf820e99443ff"}},{"code_sha256_prefix":"cd2f59a566701fe4","entry":"get_tokenizer","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/factory.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/factory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cd2f59a566701fe4"}},{"code_sha256_prefix":"8811c5d06f3a2eaa","entry":"load_openai_model","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/openai.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/openai.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8811c5d06f3a2eaa"}},{"code_sha256_prefix":"e332856e3c2fc814","entry":"neighbour_exchange","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/loss.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e332856e3c2fc814"}},{"code_sha256_prefix":"5b1fd364afcf3c05","entry":"neighbour_exchange_bidir","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/loss.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/loss.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5b1fd364afcf3c05"}},{"code_sha256_prefix":"fb651d0a97fd4d3f","entry":"prepare_inputs_for_generation","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/coca_model.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/coca_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb651d0a97fd4d3f"}},{"code_sha256_prefix":"2a377da4a76a2d44","entry":"register_pooler","repo":"opengvlab/lcl","repo_kind":"official","path":"src/open_clip/hf_model.py","file_url":"https://github.com/opengvlab/lcl/blob/HEAD/src/open_clip/hf_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a377da4a76a2d44"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}