arXiv 2610.21783 · cs.CV · 2026-10-15
Learning to Think and Explore in 3D World
Yijiang Li, Bingyang Wang, Nuno Vasconcelos
University of California at San Diego
在最新榜 #190 本站收录于 2026-10-21
一句话要点
让视觉语言模型像人一样一次看一张图，在 3D 环境中边推理边移动视角再作答，用 RL 训练。
Trains VLMs with RL to reason and actively move their viewpoint in 3D, seeing one image at a time like a human.
阅读 arXiv 原文 PDF Hugging Face 讨论 项目页
主题与学科
同主题：多模态
- MJev-Spatial: System One Spatial Intelligence via Native Attention Matching ▲560
- LoopVL: Recurrent Visual Intelligence ▲417
- VideoJev: System One Model for Video Understanding and Interaction ▲375
- S-Space: Exploring Spatial Workspace in Multimodal Language Models ▲270
- UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement ▲266
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。