Paper Detail
Zhongwei Ren, Yunchao Wei, Yao Zhao, Weibo Gong, Xiao Liu, Anran Wang, Xiangtai Li, Xiaojie Jin
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@misc{ren2026univr,
title = {UniVR: Thinking in Visual Space for Unified Visual Reasoning},
author = {Zhongwei Ren and Yunchao Wei and Yao Zhao and Weibo Gong and Xiao Liu and Anran Wang and Xiangtai Li and Xiaojie Jin},
year = {2026},
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 pr},
url = {https://huggingface.co/papers/2607.12800},
keywords = {code available, huggingface daily},
eprint = {2607.12800},
archiveprefix = {arXiv},
}
{}