Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement Learning (RL)Visual ReasoningSimilar Papers 제목 키워드 기반
VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning
Large vision-language models exhibit inherent capabilities to handle diverse visual perception tasks. In this paper, we introduce VisionReasoner, a unified framework capable of reasoning and solving multiple visual perce…
2D Object DetectionObject CountingReasoning SegmentationReferring Expression Segmentation+4From Chaos to Order: The Atomic Reasoner Framework for Fine-grained Reasoning in Large Language Models
Recent advances in large language models (LLMs) have shown remarkable progress, yet their capacity for logical ``slow-thinking'' reasoning persists as a critical research frontier. Current inference scaling paradigms suf…
Logical ReasoningGeoReasoner: Reasoning On Geospatially Grounded Context For Natural Language Understanding
In human reading and communication, individuals tend to engage in geospatial reasoning, which involves recognizing geographic entities and making informed inferences about their interrelationships. To mimic such cognitiv…
Entity TypingLanguage ModelingLanguage ModellingNatural Language Understanding+1NeuReasoner: Theory-grounded Mapping of Reasoning Elicitation Boundaries
A growing body of work suggests that the reasoning capabilities of large language models are largely latent in their base form, with post-training primarily amplifying rather than introducing them. However, this evidence…
Arithmetic ReasoningCode GenerationDecision MakingWeb-CogReasoner: Towards Multimodal Knowledge-Induced Cognitive Reasoning for Web Agents
Multimodal large-scale models have significantly advanced the development of web agents, enabling perception and interaction with digital environments akin to human cognition. In this paper, we argue that web agents must…