From the 1 of 8 linked papers with an AI index.
8 papers
When Does Legacy Data Start to Help? Emergent Transfer in Cross-Configuration Robot Learning
Tao Wang, Hudson Hou, Yingdong Hu +7
The paper investigates when demonstration data collected on an older robot configuration becomes useful for training a newer robot, revealing a three‑phase pattern where legacy dat…
Wh0: Generative World Models as Scalable Sources of Egocentric Human Hand Manipulation Data
Yangtao Chen, Zixuan Chen, Peiyang Wang +4
Scaling dexterous manipulation requires generalization across objects, scenes, and tasks, yet existing data sources face a trade-off between scale and scene/embodiment alignment: t…
Prior Reinforce: Goal-Conditioned Dynamic Manipulation with Limited Trials
Yihang Hu, Pingyue Sheng, Yuyang Liu +2
Embodied robots have achieved strong performance in many real-world manipulation tasks, yet agile dynamic manipulation remains challenging due to high sensitivity to motion paramet…
OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation
Yingdong Hu, Haodong Zhu, Boyuan Zheng +6
Whole-body humanoid loco-manipulation requires coordinating the robot's entire kinematic chain. However, most existing systems typically decouple the upper and lower bodies into se…
A Practical Recipe Towards Improving Sim-and-Real Correlation for VLA Evaluation
Shuo Wang, Hanyuan Xu, Yingdong Hu +2
Simulation has become an essential tool for evaluating and improving vision-language-action (VLA) policies, offering scalable, reproducible, and controllable alternatives to costly…
Point What You Mean: Visually Grounded Instruction Policy
Hang Yu, Juntu Zhao, Yufeng Liu +9
Vision-Language-Action (VLA) models align vision and language with embodied control, but their object referring ability remains limited when relying solely on text prompt, especial…