Episode
UniVR: Thinking in Visual Space for Unified Visual Reasoning
- Podcast
- Daily Paper Cast
- Published
- Jul 18, 2026
- Duration seconds
- 1097
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/d476143c
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/univr-thinking-in-visual-space-for-unified-visual-reasoning/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/univr-thinking-in-visual-space-for-unified-visual-reasoning.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
š¤ Upvotes: 22 | cs.CV Authors: Zhongwei Ren, Yunchao Wei, Yao Zhao, Weibo Gong, Xiao Liu, Anran Wang, Xiangtai Li, Xiaojie Jin Title: UniVR: Thinking in Visual Space for Unified Visual Reasoning Arxiv: http://arxiv.org/abs/2607.12800v1 Abstract: 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 are open-sourced for further research.