Awesome Robotics Manipulation · full_paper

MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent

作者：作者信息待提取 · 单位：UQMM Lab, The University of Queensland · 会议/期刊：CVPR 2026 · 日期：2025-11-24 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / Small Model

视觉语言动作基础模型机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent figure
AlphaXiv 中文论文页面（可滚动查看）