Towards Efficient Embodied Reasoning: Mixture-of-Depth Compute Allocation for Vision-Language-Action Model

作者：Weiying Xie, Qingchen Zeng, Zihan Meng, Jiayun Tian, Sibo He, Danian Yang, Jie Du, Yunke Wang, Daixun Li, Hengyi Wang, Jitao Ma, Leyuan Fang, Yunsong Li · 年份：2026 · DOI：10.1145/3770855.3817651 · 研究领域：Computer science、Artificial intelligence、Algorithm