Awesome Robotics Manipulation · full_paper

TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models

作者：Hokyun Im, Euijin Jeong, Andrey Kolobov, Jianlong Fu, Youngwoon Lee · 单位：Department of Artificial Intelligence, Yonsei University, Microsoft Research · 会议/期刊：ICLR 2026 · 日期：2025-11-07 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Non-LLM-based Vision Language Action Models

数据需求量大视觉语言动作语言条件双臂机器人学习操作
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Project
TwinVLA: Data-Efficient Bimanual Manipulation with Twin Single-Arm Vision-Language-Action Models figure
AlphaXiv 中文论文页面（可滚动查看）