Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
Johns Hopkins University · Beijing Step by Step Technology Co., Ltd. · Megvii Technology Inc. · Beijing University of Posts and Telecommunications · University of the Chinese Academy of Sciences · Tsinghua University, Tsinghua University · StepFun · Huazhong University of Science and Technology · Wuhan University of Technology · Fudan University · Stepfun
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
The remarkable reasoning capability of large language models (LLMs) stems from cognitive behaviors that emerge through reinforcement with verifiable rewards. This work investigates how to transfer this principle to Multimodal LLMs (MLLMs) to unlock advanced visual reasoning. We introduce a two-stage paradigm built on Qwen2.5-VL-7B: a massive linguistic cold-start fine-tuning, followed by multimodal reinforcement learning (RL) spanning nearly 1,000 steps—surpassing all previous open-source efforts in scale. This pioneering work reveals three fundamental insights: 1) Behavior transfer emerges surprisingly early in cold start due to linguistic mental imagery. 2) Cold start broadly memorizes visual behaviors, while RL critically discerns and scales up effective patterns. 3) Transfer strategically favors high-utility behaviors such as visual reflection. Our resulting model, Open-Vision-Reasoner (OVR), achieves state-of-the-art performance on a suite of reasoning benchmarks, including 95.3% on MATH500, 51.8% on MathVision and 54.6% on MathVerse. We release our model, data, and training dynamics to catalyze the development of more capable, behavior-aligned multimodal reasoners.