UniVR: Thinking in Visual Space for Unified Visual Reasoning
Summary
UniVR introduces VR-GRPO, a reinforcement learning paradigm for unified visual reasoning, learning complex reasoning and physical dynamics from pure visual demonstrations, achieving up to 25% improvement on the VR-X benchmark.
View Cached Full Text
Cached at: 07/20/26, 09:42 AM
Paper page - UniVR: Thinking in Visual Space for Unified Visual Reasoning
Source: https://huggingface.co/papers/2607.12800 Learning broad world knowledge directly from raw visual data is a fundamental capability of intelligence. We introduce UniVR, the first investigation into simultaneously learning complex reasoning, fine-grained physical dynamics, and long-term planning from pure visual demonstrations. At its core, UniVR features VR-GRPO, a reinforcement learning paradigm with complementary global and step-level rewards. This approach enforces logical coherence and physical consistency throughout the reasoning process without requiring task-specific heuristics or image-text pairs. To train and evaluate UniVR, we construct VR-X, a large-scale benchmark curated from 16 diverse sources spanning long-horizon manipulation, spatial puzzles, and physical reasoning. It is the first comprehensive suite to assess these heterogeneous capabilities under a purely visual protocol. Remarkably, UniVR achieves up to a 25% improvement on VR-X, and its superior visual reasoning also boosts performance on various multimodal understanding benchmarks. These findings underscore the vast potential of reasoning within visual spaces, with all code, data, and models to be open-sourced for further research.
Similar Articles
VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning
VBVR-Pro introduces a closed-loop testbed for scalable and verifiable native visual reasoning through generation, featuring task scaling, verifiable rewards, and mechanism studies across diverse visual substrates.
Learning Adaptive Reasoning Paths for Efficient Visual Reasoning
AVR is an adaptive visual reasoning framework that dynamically selects optimal reasoning formats to reduce token usage by 50-90% while maintaining accuracy in visual reasoning tasks. The method addresses reasoning path redundancy by decomposing visual reasoning into three cognitive functions and using FS-GRPO training to encourage efficient format selection.
UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards
UniDoc-RL presents a reinforcement learning framework for Large Vision-Language Models that optimizes retrieval, reranking, and visual reasoning through hierarchical decision-making and dense multi-reward supervision, achieving up to 17.7% improvements over prior RL-based methods on visual RAG tasks.
SVR-R1: Bootstrapping Multi-modal Reasoning with Self-verification in Reinforcement Learning
Introduces SVR-R1, a multi-turn reinforcement learning framework that uses the model's own verification as a learning signal for multi-modal reasoning, achieving significant accuracy improvements over standard GRPO baselines on vision-language reasoning benchmarks.
iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning
Introduces iVGR, a reinforcement learning framework that internalizes visual localization into textual reasoning for multimodal language models, eliminating the need for explicit visual grounding during inference while improving fine-grained perception performance.