PixelVLA: Advancing Pixel-level Understanding in Vision-Language-Action Model

作者：Wenqi Liang, Gan Sun, Yao He, Jiahua Dong, Suyan Dai, Ivan Laptev, Salman Khan, Yang Cong · 单位：University of Trento, School of Automation Science and Engineering, South China University of Technology, Mohamed bin Zayed University of Artificial Intelligence, Australian National University · 会议/期刊：ICLR 2026 · 日期：2025-11-03 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Auxiliary Tasks - Visual Goal Extraction