{"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/decoupled-visual-interpretation-and","title":"Decoupled Visual Interpretation and Linguistic Reasoning for Math Problem Solving","arxiv_id":"2505.17609","date":"2025-05-23","proceeding":null,"authors":["Zixian Guo","Ming Liu","Zhilong Ji","Jinfeng Bai","Lei Zhang","WangMeng Zuo"],"abstract":"Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified process. Well alignment needs high-quality pre-training data and a carefully designed training process. Current LVLMs face challenges when addressing complex vision-language reasoning tasks, with their reasoning capabilities notably lagging behind those of LLMs. This paper proposes a paradigm shift: instead of training end-to-end vision-language reasoning models, we advocate for developing a decoupled reasoning framework based on existing visual interpretation specialists and text-based reasoning LLMs. Our approach leverages (1) a dedicated vision-language model to transform the visual content of images into textual descriptions and (2) an LLM to perform reasoning according to the visual-derived text and the original question. This method presents a cost-efficient solution for multi-modal model development by optimizing existing models to work collaboratively, avoiding end-to-end development of vision-language models from scratch. By transforming images into language model-compatible text representations, it facilitates future low-cost and flexible upgrades to upcoming powerful LLMs. We introduce an outcome-rewarded joint-tuning strategy to optimize the cooperation between the visual interpretation and linguistic reasoning model. Evaluation results on vision-language benchmarks demonstrate that the decoupled reasoning framework outperforms recent LVLMs. Our approach yields particularly significant performance gains on visually intensive geometric mathematics problems. The code is available: https://github.com/guozix/DVLR.","url_abs":"https://arxiv.org/abs/2505.17609v1","url_pdf":"https://arxiv.org/pdf/2505.17609v1.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":"decoupled-visual-interpretation-and","repo_url":"https://github.com/guozix/dvlr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"math","task_name":"Math"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.17609","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17609"}},"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/guozix/dvlr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":4,"ran_fixture":1},"by_repo_kind":{"official":{"samples":4,"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":1,"samples":[{"code_sha256_prefix":"9c139a95c7324740","entry":"create_one_query","repo":"guozix/dvlr","repo_kind":"official","path":"eval/MathVerse/evaluation/build_query.py","file_url":"https://github.com/guozix/dvlr/blob/HEAD/eval/MathVerse/evaluation/build_query.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9c139a95c7324740"}},{"code_sha256_prefix":"93f012e28ba3ca67","entry":"dynamic_preprocess","repo":"guozix/dvlr","repo_kind":"official","path":"eval/MathVerse/evaluation/generate_response_geo_text_qwen_2.py","file_url":"https://github.com/guozix/dvlr/blob/HEAD/eval/MathVerse/evaluation/generate_response_geo_text_qwen_2.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93f012e28ba3ca67"}},{"code_sha256_prefix":"bd77f5f8067f18e9","entry":"find_closest_aspect_ratio","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"bd77f5f8067f18e9"}},{"code_sha256_prefix":"d027e6e473c9fcd4","entry":"refine_caption","repo":"guozix/dvlr","repo_kind":"official","path":"eval/MathVerse/evaluation/build_query.py","file_url":"https://github.com/guozix/dvlr/blob/HEAD/eval/MathVerse/evaluation/build_query.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d027e6e473c9fcd4"}},{"code_sha256_prefix":"bfd184123c9012c3","entry":"refine_ocr","repo":"guozix/dvlr","repo_kind":"official","path":"eval/MathVerse/evaluation/build_query.py","file_url":"https://github.com/guozix/dvlr/blob/HEAD/eval/MathVerse/evaluation/build_query.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bfd184123c9012c3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}