{"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/lmm-r1-empowering-3b-lmms-with-strong","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","arxiv_id":"2503.07536","date":"2025-03-10","proceeding":null,"authors":["Yingzhe Peng","Gongrui Zhang","Miaosen Zhang","Zhiyuan You","Jie Liu","Qipeng Zhu","Kai Yang","Xingzhong Xu","Xin Geng","Xu Yang"],"abstract":"Enhancing reasoning in Large Multimodal Models (LMMs) faces unique challenges from the complex interplay between visual perception and logical reasoning, particularly in compact 3B-parameter architectures where architectural constraints limit reasoning capacity and modality alignment. While rule-based reinforcement learning (RL) excels in text-only domains, its multimodal extension confronts two critical barriers: (1) data limitations due to ambiguous answers and scarce complex reasoning examples, and (2) degraded foundational reasoning induced by multimodal pretraining. To address these challenges, we propose \\textbf{\\method}, a two-stage framework adapting rule-based RL for multimodal reasoning through \\textbf{Foundational Reasoning Enhancement (FRE)} followed by \\textbf{Multimodal Generalization Training (MGT)}. The FRE stage first strengthens reasoning abilities using text-only data with rule-based RL, then the MGT stage generalizes these reasoning capabilities to multimodal domains. Experiments on Qwen2.5-VL-Instruct-3B demonstrate that \\method achieves 4.83\\% and 4.5\\% average improvements over baselines in multimodal and text-only benchmarks, respectively, with a 3.63\\% gain in complex Football Game tasks. These results validate that text-based reasoning enhancement enables effective multimodal generalization, offering a data-efficient paradigm that bypasses costly high-quality multimodal training data.","url_abs":"https://arxiv.org/abs/2503.07536v1","url_pdf":"https://arxiv.org/pdf/2503.07536v1.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":"lmm-r1-empowering-3b-lmms-with-strong","repo_url":"https://github.com/tidedra/lmm-r1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"multimodal-reasoning","task_name":"Multimodal Reasoning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.07536","atlas_url":"https://app.syntology.ai/?focus=2503.07536","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.07536"}},"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/tidedra/lmm-r1","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"listed":{"samples":3,"ran":1,"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":"d2ebfe8d0a5ecf10","entry":"hack_peft_model","repo":"tidedra/lmm-r1","repo_kind":"listed","path":"openrlhf/models/lmm_kits/utils.py","file_url":"https://github.com/tidedra/lmm-r1/blob/HEAD/openrlhf/models/lmm_kits/utils.py","link_basis":"harvester_set","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":"d2ebfe8d0a5ecf10"}},{"code_sha256_prefix":"f743dbb9eddd7027","entry":"get_data_processor","repo":"tidedra/lmm-r1","repo_kind":"listed","path":"openrlhf/models/lmm_kits/utils.py","file_url":"https://github.com/tidedra/lmm-r1/blob/HEAD/openrlhf/models/lmm_kits/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":"f743dbb9eddd7027"}},{"code_sha256_prefix":"58e0906efe862e1e","entry":"get_generation_cls","repo":"tidedra/lmm-r1","repo_kind":"listed","path":"openrlhf/models/lmm_kits/utils.py","file_url":"https://github.com/tidedra/lmm-r1/blob/HEAD/openrlhf/models/lmm_kits/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":"58e0906efe862e1e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}