{"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/libra-building-decoupled-vision-system-on","title":"Libra: Building Decoupled Vision System on Large Language Models","arxiv_id":"2405.10140","date":"2024-05-16","proceeding":null,"authors":["Yifan Xu","Xiaoshan Yang","Yaguang Song","Changsheng Xu"],"abstract":"In this work, we introduce Libra, a prototype model with a decoupled vision system on a large language model (LLM). The decoupled vision system decouples inner-modal modeling and cross-modal interaction, yielding unique visual information modeling and effective cross-modal comprehension. Libra is trained through discrete auto-regressive modeling on both vision and language inputs. Specifically, we incorporate a routed visual expert with a cross-modal bridge module into a pretrained LLM to route the vision and language flows during attention computing to enable different attention patterns in inner-modal modeling and cross-modal interaction scenarios. Experimental results demonstrate that the dedicated design of Libra achieves a strong MLLM baseline that rivals existing works in the image-to-text scenario with merely 50 million training data, providing a new perspective for future multimodal foundation models. Code is available at https://github.com/YifanXu74/Libra.","url_abs":"https://arxiv.org/abs/2405.10140v1","url_pdf":"https://arxiv.org/pdf/2405.10140v1.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":"libra-building-decoupled-vision-system-on","repo_url":"https://github.com/yifanxu74/libra","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.10140","atlas_url":"https://app.syntology.ai/?focus=2405.10140","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.10140"}},"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/yifanxu74/libra","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"ran_draft_wrong":4,"ran_violates":1,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":10,"ran":8,"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":"45b8a2c070efc3ed","entry":"apply_rotary_pos_emb","repo":"yifanxu74/libra","repo_kind":"official","path":"libra/models/libra/modeling_libra.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/models/libra/modeling_libra.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"45b8a2c070efc3ed"}},{"code_sha256_prefix":"4675779aec92d6c0","entry":"contrastive_loss","repo":"yifanxu74/libra","repo_kind":"official","path":"libra/models/clip/modeling_clip.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/models/clip/modeling_clip.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4675779aec92d6c0"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"yifanxu74/libra","repo_kind":"official","path":"libra/models/libra/image_tokenizer.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/models/libra/image_tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"7284ea3e763f4e0d","entry":"easy_gather","repo":"yifanxu74/libra","repo_kind":"official","path":"libra/models/libra/modeling_libra.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/models/libra/modeling_libra.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7284ea3e763f4e0d"}},{"code_sha256_prefix":"17279a5f97b07e0d","entry":"get_encoded_image_size","repo":"yifanxu74/libra","repo_kind":"official","path":"libra/models/libra/tokenization_libra.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/models/libra/tokenization_libra.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"17279a5f97b07e0d"}},{"code_sha256_prefix":"98589643273920ba","entry":"main_process","repo":"yifanxu74/libra","repo_kind":"official","path":"libra/common/dist_utils.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/common/dist_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"98589643273920ba"}},{"code_sha256_prefix":"791c72070c0b1cfb","entry":"node_to_dict","repo":"yifanxu74/libra","repo_kind":"official","path":"libra/common/config.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/common/config.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"791c72070c0b1cfb"}},{"code_sha256_prefix":"b99eea6376d1e212","entry":"rotate_half","repo":"yifanxu74/libra","repo_kind":"official","path":"libra/models/libra/modeling_libra.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/models/libra/modeling_libra.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b99eea6376d1e212"}},{"code_sha256_prefix":"f2ca34eca05d40cd","entry":"clip_loss","repo":"yifanxu74/libra","repo_kind":"official","path":"libra/models/clip/modeling_clip.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/models/clip/modeling_clip.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f2ca34eca05d40cd"}},{"code_sha256_prefix":"643539116e049080","entry":"download_cached_file","repo":"yifanxu74/libra","repo_kind":"official","path":"libra/common/dist_utils.py","file_url":"https://github.com/yifanxu74/libra/blob/HEAD/libra/common/dist_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"643539116e049080"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}