VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference

作者：Jiaming Tang, Yufei Sun, Yilong Zhao, Shang Yang, Yujun Lin, Zhuoyang Zhang, James Hou, Yao Lu, Zhijian Liu, Song Han · 单位：MIT, NVIDIA, Tsinghua University, UC Berkeley, UCSD, Caltech · 会议/期刊：arXiv · 日期：2025-11-30 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Inference Acceleration