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, w
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 52%om-ai-lab/VLM-R1 →
- LinkedLinked via arxiv author · 85%Zhongwei Ren →
“UniVR: Thinking in Visual Space for Unified Visual Reasoning”
- LinkedLinked via arxiv author · 85%Yunchao Wei →
“UniVR: Thinking in Visual Space for Unified Visual Reasoning”
- LinkedLinked via arxiv author · 85%Yao Zhao →
“UniVR: Thinking in Visual Space for Unified Visual Reasoning”
- LinkedLinked via arxiv author · 85%Weibo Gong →
“UniVR: Thinking in Visual Space for Unified Visual Reasoning”
- LinkedLinked via arxiv author · 85%Xiao Liu →
“UniVR: Thinking in Visual Space for Unified Visual Reasoning”
- LinkedLinked via arxiv author · 85%Anran Wang →
“UniVR: Thinking in Visual Space for Unified Visual Reasoning”
- LinkedLinked via arxiv author · 85%Xiangtai Li →
“UniVR: Thinking in Visual Space for Unified Visual Reasoning”