6 papers
APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
Kechun Xu, Zhenjie Zhu, Anzhe Chen +2
Vision-Language-Action (VLA) models that couple pretrained Vision-Language Models (VLMs) with continuous action experts have achieved strong manipulation performance, yet generaliz…
D-REX: Differentiable Real-to-Sim-to-Real Engine for Learning Dexterous Grasping
Haozhe Lou, Mingtong Zhang, Haoran Geng +9
Simulation provides a cost-effective and flexible platform for data generation and policy learning to develop robotic systems. However, bridging the gap between simulation and real…
Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy
Kechun Xu, Zhenjie Zhu, Anzhe Chen +7
The pursuit of out-of-distribution generalization in Vision-Language-Action (VLA) models is often hindered by catastrophic forgetting of the Vision-Language Model (VLM) backbone du…
Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter
Kechun Xu, Xunlong Xia, Kaixuan Wang +6
We study the task of language-conditioned pick and place in clutter, where a robot should grasp a target object in open clutter and move it to a specified place. Some approaches le…
Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions
He Zhu, Quyu Kong, Kechun Xu +5
Grounding 3D object affordance is a task that locates objects in 3D space where they can be manipulated, which links perception and action for embodied intelligence. For example, f…
Grasp, See, and Place: Efficient Unknown Object Rearrangement with Policy Structure Prior
Kechun Xu, Zhongxiang Zhou, Jun Wu +3
We focus on the task of unknown object rearrangement, where a robot is supposed to re-configure the objects into a desired goal configuration specified by an RGB-D image. Recent wo…