Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(多媒体信息处理国家重点实验室,计算机科学学院,北京大学);Beijing Academy of Artificial Intelligence(北京人工智能研究院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院自动化研究所人工智能学院)
Visual reasoning abilities play a crucial role in understanding complex multimodal data, advancing both domain-specific applications and artificial general intelligence (AGI). Existing methods enhance Vision-Language Models (VLMs) through Chain-of-Thought (CoT) supervised fine-tuning using meticulously annotated data. However, this approach may lead to overfitting and cognitive rigidity, limiting the model's generalization ability under domain shifts and reducing real-world applicability. To overcome these limitations, we propose Reason-RFT, a two-stage reinforcement fine-tuning framework for visual reasoning. First, Supervised Fine-Tuning (SFT) with curated CoT data activates the reasoning potential of VLMs. This is followed by reinforcement learning based on Group Relative Policy Optimization (GRPO), which generates multiple reasoning-response pairs to enhance adaptability to domain shifts. To evaluate Reason-RFT, we reconstructed a comprehensive dataset covering visual counting, structural perception, and spatial transformation, serving as a benchmark for systematic assessment across three key dimensions. Experimental results highlight three advantages: (1) performance enhancement, with Reason-RFT achieving state-of-the-art results and outperforming both open-source and proprietary models; (2) generalization superiority, maintaining robust performance under domain shifts across various tasks; and (3) data efficiency, excelling in few-shot learning scenarios and surpassing full-dataset SFT baselines. Reason-RFT introduces a novel training paradigm for visual reasoning and marks a significant step forward in multimodal research. Project website: https://tanhuajie.github.io/ReasonRFT
Walking the Tightrope: Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning
Australian Artificial Intelligence Institute (AAII)(澳大利亚人工智能研究所);Faulty of Engineering and Information Technology(工程与信息技术学院);University of Technology Sydney(悉尼技术大学)
Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFT
Institute of Automation, CAS(中国科学院自动化研究所);School of Artificial Intelligence, UCAS(中国科学技术大学人工智能学院);BAAI FlagEval Team(百度AI旗评团队);BUAA(北京航空航天大学);PKU(北京大学);ZJU(浙江大学)
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
School of Software, Beihang University(北京航空航天大学软件学院);State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(北京大学计算机学院);Beijing Academy of Artificial Intelligence(北京人工智能研究院)
Surgery-R1: Advancing Surgical-VQLA with Reasoning Multimodal Large Language Model via Reinforcement Learning
Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));Hong Kong University of Science and Technology(香港科技大学);Department of Thoracic Surgery, the Seventh Affiliated Hospital, Sun Yat-sen University(中山大学第七附属医院胸外科部门);Bioengineering/Imperial-X, Imperial College London(生物工程/Imperial-X,帝国理工学院伦敦分校);ROAS Thrust, Hong Kong University of Science and Technology (Guangzhou)(ROAS项目,香港科技大学(广州));Department of Electronic and Computer Engineering, Hong Kong SAR(香港特别行政区电子与计算机工程系)
RGBX-R1: Visual Modality Chain-of-Thought Guided Reinforcement Learning for Multimodal Grounding
School of Artificial Intelligence, Tianjin University(天津大学人工智能学院);Low-Altitude Intelligence Lab, Xiong’an National Innovation Center(雄安国家创新中心低空智能实验室);Xiong’an Guochuang Lantian Technology Co., Ltd.(雄安国创莲田科技有限公司);College of Electronic Science and Technology, National University of Defense Technology(国防科技大学电子科学学院)
Geo-R1: Improving Few-Shot Geospatial Referring Expression Understanding with Reinforcement Fine-Tuning
College of Computer Science and Technology of Zhejiang University(浙江大学计算机科学与技术学院);Polytechnic Institute of Zhejiang University(浙江大学Polytechnic学院);Om AI Research(Om AI研究机构);Binjiang Research Institute of Zhejiang University(浙江大学滨江研究机构);School of Software Engineering of Zhejiang University(浙江大学软件工程学院);School of Mathematical Sciences of Zhejiang University(浙江大学数学科学学院);China Academy of Space Technology(中国航天科技研究院);University of Bristol(布里斯托大学)
VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulators
Westlake University(西湖大学);Zhejiang University(浙江大学);OpenHelix Team(OpenHelix团队);Fudan University(复旦大学);Zhengzhou University(郑州大学);BUPT(北京邮电大学);Hebei University of Technology(河北工业大学)
Mesh-RFT: Enhancing Mesh Generation via Fine-grained Reinforcement Fine-Tuning
Hong Kong University of Science and Technology(香港科技大学);Tencent Hunyuan(腾讯文元);University of Science and Technology of China(中国科学技术大学);South China University of Technology(华南理工大学)
Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation
College of Intelligent Robotics and Advanced Manufacturing, Fudan University(复旦大学智能机器人与先进制造学院);Fysics Intelligence Technologies Co., Ltd. (Fysics AI)(菲斯克智能科技有限公司(菲斯克AI));Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);Southeast University(东南大学);School of Computing, National University of Singapore(新加坡国立大学计算机学院)
TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
Beihang University(北洋大学);Beijing Academy of Artificial Intelligence(北京人工智能研究院);State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(北京大学计算机科学学院多媒体信息处理国家重点实验室)
RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning
School of Electrical and Electronic Engineering, Nanyang Technological University(电气电子工程学院,南洋理工大学);MoE Key Laboratory of Interdisciplinary Research of Computation and Economics, Shanghai University of Finance and Economics(教育部计算与经济交叉学科重点实验室,上海财经大学)