UniVR: Thinking in Visual Space for Unified Visual Reasoning
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 m...
| Authors | Zhongwei Ren, Yunchao Wei, Yao Zhao et al. |
|---|---|
| Primary category | cs.CV |
| Published | 14 July 2026 |
| Last updated at source | 14 July 2026 |
Connected in the knowledge graph
- ByteDance/VR-X-SFT-RLDataset · cited by
Models and datasets referencing this paper
- ByteDance/VR-X-SFT-RLDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.