Embodied AI TopConf · NeuIPS2025

ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning

NeuIPS2025 / Vision-Language-Action Model

VLA规划/推理触觉感知
新标签打开 AlphaXiv新标签打开 Project
ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning figure
AlphaXiv 中文论文页面（可滚动查看）