SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation

作者：Wei Li, Renshan Zhang, Rui Shao, Zhijian Fang, Kaiwen Zhou, Zhuotao Tian, Liqiang Nie · 单位：Harbin Institute of Technology, Shenzhen, Huawei Noah’s Ark Lab · 会议/期刊：AAAI 2026 · 日期：2025-11-13 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Model-agnostic Strategies