4 papers
The Neverwhere Visual Parkour Benchmark Suite
Ziyu Chen, Henghui Bao, Haoran Chang +12
State-of-the-art visual locomotion controllers are increasingly capable at handling complex visual environments, making evaluating their real-world performance before deployment in…
HumDex: Humanoid Dexterous Manipulation Made Easy
Liang Heng, Yihe Tang, Jiajun Xu +3
This paper investigates humanoid whole-body dexterous manipulation, where the efficient collection of high-quality demonstration data remains a central bottleneck. Existing teleope…
Towards Embodiment Scaling Laws in Robot Locomotion
Bo Ai, Liu Dai, Nico Bohlinger +7
Cross-embodiment generalization underpins the vision of building generalist embodied agents for any robot, yet its enabling factors remain poorly understood. We investigate embodim…
Value Explicit Pretraining for Learning Transferable Representations
Kiran Lekkala, Henghui Bao, Sumedh A. Sontakke +2
Understanding visual inputs for a given task amidst varied changes is a key challenge posed by visual reinforcement learning agents. We propose \textit{Value Explicit Pretraining}…