5 papers
Sparse Autoencoders Reveal Interpretable and Steerable Features in VLA Models
Aiden Swann, Lachlain McGranahan, Hugo Buurmeijer +2
Vision-Language-Action (VLA) models have emerged as a promising approach for general-purpose robot manipulation. However, little research has mechanistically explored when and why…
Learning Humanoid Navigation from Human Data
Weizhuo Wang, Yanjie Ze, C. Karen Liu +1
We present EgoNav, a system that enables a humanoid robot to traverse diverse, unseen environments by learning entirely from 5 hours of human walking data, with no robot data or fi…
Diffusion-SAFE: Diffusion-Native Human-to-Robot Driving Handover for Shared Autonomy
Yunxin Fan, Monroe Kennedy
Shared autonomy in driving requires anticipating human behavior, flagging risk before it becomes unavoidable, and transferring control safely and smoothly. We propose Diffusion-SAF…
Locomotion Beyond Feet
Tae Hoon Yang, Haochen Shi, Jiacheng Hu +10
Most locomotion methods for humanoid robots focus on leg-based gaits, yet natural bipeds frequently rely on hands, knees, and elbows to establish additional contacts for stability…
Understanding and Imitating Human-Robot Motion with Restricted Visual Fields
Maulik Bhatt, HongHao Zhen, Monroe Kennedy +1
When working around other agents such as humans, it is important to model their perception capabilities to predict and make sense of their behavior. In this work, we consider agent…