{"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/mindgym-enhancing-vision-language-models-via","title":"MindGYM: Enhancing Vision-Language Models via Synthetic Self-Challenging Questions","arxiv_id":"2503.09499","date":"2025-03-12","proceeding":null,"authors":["Zhe Xu","Daoyuan Chen","Zhenqing Ling","Yaliang Li","Ying Shen"],"abstract":"Large vision-language models (VLMs) face challenges in achieving robust, transferable reasoning abilities due to reliance on labor-intensive manual instruction datasets or computationally expensive self-supervised methods. To address these issues, we introduce MindGYM, a framework that enhances VLMs through synthetic self-challenging questions, consisting of three stages: (1) Seed Single-Hop Question Synthesis, generating cognitive questions across textual (e.g., logical deduction) and multimodal contexts (e.g., diagram-based queries) spanning eight semantic areas like ethical analysis; (2) Challenging Multi-Hop Question Synthesis, combining seed questions via diverse principles like bridging, visual-textual alignment, to create multi-step problems demanding deeper reasoning; and (3) Thinking-Induced Curriculum Fine-Tuning, a structured pipeline that progressively trains the model from scaffolded reasoning to standalone inference. By leveraging the model's self-synthesis capability, MindGYM achieves high data efficiency (e.g., +16% gains on MathVision-Mini with only 400 samples), computational efficiency (reducing both training and inference costs), and robust generalization across tasks. Extensive evaluations on seven benchmarks demonstrate superior performance over strong baselines, with notable improvements (+15.77% win rates) in reasoning depth and breadth validated via GPT-based scoring. MindGYM underscores the viability of self-challenging for refining VLM capabilities while minimizing human intervention and resource demands. Code and data are released to advance multimodal reasoning research.","url_abs":"https://arxiv.org/abs/2503.09499v1","url_pdf":"https://arxiv.org/pdf/2503.09499v1.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":"mindgym-enhancing-vision-language-models-via","repo_url":"https://github.com/modelscope/data-juicer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2503.09499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09499"}},"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/modelscope/data-juicer","reach":null}],"summary":{"ran":2,"ran_draft_wrong":2,"ran_fixture":1,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"500c2ea8c5d97fe6","entry":"LLMCallUsage","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/utils/llm_semantic_ops.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/utils/llm_semantic_ops.py","link_basis":"first_harvest_node","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":"500c2ea8c5d97fe6"}},{"code_sha256_prefix":"7c85f594570193fe","entry":"RecordRow","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/utils/llm_semantic_ops.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/utils/llm_semantic_ops.py","link_basis":"first_harvest_node","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":"7c85f594570193fe"}},{"code_sha256_prefix":"202a1d5c77bcba46","entry":"_parse_usage_from_response","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/utils/llm_semantic_ops.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/utils/llm_semantic_ops.py","link_basis":"first_harvest_node","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":"202a1d5c77bcba46"}},{"code_sha256_prefix":"3efc32e5ec4f3db4","entry":"call_llm_sync","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/utils/llm_semantic_ops.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/utils/llm_semantic_ops.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"DEP_MISSING","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3efc32e5ec4f3db4"}},{"code_sha256_prefix":"581178da56072d6f","entry":"get_extract_prompt","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/utils/llm_semantic_ops.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/utils/llm_semantic_ops.py","link_basis":"first_harvest_node","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":"581178da56072d6f"}},{"code_sha256_prefix":"58be2ad46dc599f0","entry":"InferenceStrategy","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/utils/llm_semantic_ops.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/utils/llm_semantic_ops.py","link_basis":"first_harvest_node","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":"58be2ad46dc599f0"}},{"code_sha256_prefix":"21e9afc889c14ac4","entry":"extract_one","repo":"modelscope/data-juicer","repo_kind":"official","path":"data_juicer/utils/llm_semantic_ops.py","file_url":"https://github.com/modelscope/data-juicer/blob/HEAD/data_juicer/utils/llm_semantic_ops.py","link_basis":"first_harvest_node","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":"21e9afc889c14ac4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}