7 papers
Human-in-the-loop Online Rejection Sampling for Robotic Manipulation
Guanxing Lu, Rui Zhao, Haitao Lin +2
Reinforcement learning (RL) is widely used to produce robust robotic manipulation policies, but fine-tuning vision-language-action (VLA) models with RL can be unstable due to inacc…
DSPv2: Improved Dense Policy for Effective and Generalizable Whole-body Mobile Manipulation
Yue Su, Chubin Zhang, Sijin Chen +4
Learning whole-body mobile manipulation via imitation is essential for generalizing robotic skills to diverse environments and complex tasks. However, this goal is hindered by sign…
GWM: Towards Scalable Gaussian World Models for Robotic Manipulation
Guanxing Lu, Baoxiong Jia, Puhao Li +4
Training robot policies within a learned world model is trending due to the inefficiency of real-world interactions. The established image-based world models and policies have show…
VLA-Reasoner: Empowering Vision-Language-Action Models with Reasoning via Online Monte Carlo Tree Search
Wenkai Guo, Guanxing Lu, Haoyuan Deng +3
Vision-Language-Action models (VLAs) achieve strong performance in general robotic manipulation tasks by scaling imitation learning. However, existing VLAs are limited to predictin…
ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World Model
Tengbo Yu, Guanxing Lu, Zaijia Yang +7
Multi-task robotic bimanual manipulation is becoming increasingly popular as it enables sophisticated tasks that require diverse dual-arm collaboration patterns. Compared to uniman…
VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
Guanxing Lu, Wenkai Guo, Chubin Zhang +5
Recent high-capacity vision-language-action (VLA) models have demonstrated impressive performance on a range of robotic manipulation tasks by imitating human demonstrations. Howeve…