5 papers
VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model
Yihao Wang, Pengxiang Ding, Lingxiao Li +13
Vision-Language-Action (VLA) models typically bridge the gap between perceptual and action spaces by pre-training a large-scale Vision-Language Model (VLM) on robotic data. While t…
Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions
Wei Zhao, Gongsheng Li, Zhefei Gong +3
Vision-Language-Action (VLA) models have recently become highly prominent in the field of robotics. Leveraging vision-language foundation models trained on large-scale internet dat…
VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation
Wei Zhao, Pengxiang Ding, Min Zhang +4
Vision-language-action models (VLAs) have become increasingly popular in robot manipulation for their end-to-end design and remarkable performance. However, existing VLAs rely heav…
Rethinking Latent Redundancy in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation
Shuanghao Bai, Wanqi Zhou, Pengxiang Ding +3
Behavior Cloning (BC) is a widely adopted visual imitation learning method in robot manipulation. Current BC approaches often enhance generalization by leveraging large datasets an…
CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction
Zhefei Gong, Pengxiang Ding, Shangke Lyu +5
In robotic visuomotor policy learning, diffusion-based models have achieved significant success in improving the accuracy of action trajectory generation compared to traditional au…