7 papers
FolDeX: A Physical-World Benchmark for Long-Horizon Robotic Manipulation of Deformable Objects
Chenhuan Liu, Yi Xu, Feng Wu +7
Embodied AI, including vision-language-action and world-action models, must operate reliably in the physical world. Yet methods that perform well in simulation can degrade substant…
Trajectory-Level Continuous Action Representation for Robotic Manipulation
Tong Yang, Jingkai Jia, Yuecheng Xu +3
We propose CAT, a trajectory-level continuous action representation framework for robotic manipulation. Existing visuomotor systems often entangle action representation with contro…
EDAR: Learning Environment-Dependent Action Representations for Robotic Manipulation
Yuecheng Xu, Tong Yang, Jingkai Jia +3
Learning effective action representations is critical for robotic manipulation, where raw control trajectories are often noisy, redundant, and difficult to model directly. Existing…
Context as Prior: Bayesian-Inspired Intent Inference for Non-Speaking Agents with a Household Cat Testbed
Wenqian Zhang, Zehao Wang
Many agents in real-world environments cannot reliably communicate their goals through language, including household pets, pre-verbal infants, and other non-speaking embodied agent…
LongBench: Evaluating Robotic Manipulation Policies on Real-World Long-Horizon Tasks
Xueyao Chen, Jingkai Jia, Tong Yang +3
Robotic manipulation policies often degrade over extended horizons, yet existing benchmarks provide limited insight into why such failures occur. Most prior benchmarks are either s…
Fast Visuomotor Policy for Robotic Manipulation
Jingkai Jia, Tong Yang, Xueyao Chen +2
We present a fast and effective policy framework for robotic manipulation, named Energy Policy, designed for high-frequency robotic tasks and resource-constrained systems. Unlike e…