Awesome Robotics Manipulation · full_paper

Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone

作者：Jiacheng Ye, Shansan Gong, Jiahui Gao, ♢ Junming Fan, Shuang Wu, Wei Bi Haoli Bai, Lifeng Shang, Lingpeng Kong · 单位：The University of Hong Kong, Huawei Technologies · 会议/期刊：arXiv · 日期：2025-12-27 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D LLM-based Vision Language Action Models

视觉语言动作扩散策略语言条件机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone figure
AlphaXiv 中文论文页面（可滚动查看）