Adaptive Action Chunking at Inference-time for Vision-Language-Action Models

作者：Yuanchang Liang, Xiaobo Wang, Kai Wang, Shuo Wang, Xiaojiang Peng, Haoyu Chen, David Kim Huat Chua, Prahlad Vadakkepat · 单位：National University of Singapore, Shenzhen University of Advanced Technology, Mininglamp Technology, Shenzhen Technology University, City University of Hong Kong · 会议/期刊：CVPR 2026 · 日期：2026-04-05 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Model-agnostic Strategies