TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models

作者：Jiaying Zhou, Zhihao Zhan, Ruifeng Zhai, Qinhan Lyu, Hao Liu, Keze Wang, Liang Lin, Guangrun Wang · 单位：Sun Yat-sen University, Guangdong Key Lab of Big Data Analysis & Processing, X-Era AI Lab · 会议/期刊：arXiv · 日期：2026-03-25 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Model-agnostic Strategies