14 papers
Chunk-wise Model-based Policy Optimization
Weixi Song, Donglin Wang, Yong-Lu Li
Model-based reinforcement learning has shown superior sample efficiency by leveraging the learned latent dynamics either in the form of derivative-free planning/imagined rollout tr…
RoboICL: Embodied In-Context Learning with GPT-6 Astra
Fangcheng Liu, Yeqing Shen, Anda Cheng +7
General-purpose vision-language models offer a promising way to zero-shot robot control: \gptastra{} excels at open-ended and language- or image-conditioned manipulation but remain…
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…
UniviewVLA: A Unified Multiview Vision-Language-Action Model with World Modeling
Tao Xu, Runhao Zhang, Zhijian Huang +7
Occluded tasks remain a bottleneck in robot manipulation. Existing solutions either deploy additional physical cameras requiring training-inference camera parity, or rely on explic…
ATHENA: Accelerated Multi-Task Heterogeneous Influence Functions for Robot Data Curation
Tao Xu, Jiaxin Wang, Runhao Zhang +7
In robot imitation learning, influence functions provide a principled approach to quantify each demonstration's effect on robot task outcomes, yet scaling them to billion-parameter…
AetheRock: An Arm-Worn Robot Teaching System for Force-Guided Vision-Tactile Learning
Hong Li, Yue Xu, Yihan Tang +8
Force and tactile sensing are indispensable in contact-rich manipulation. However, force-aware robot learning faces critical challenges due to the incompatible assembly of tactile…
EgoGuide: Egocentric Guidance for Efficient Robot-Free Demonstration Collection and Learning
Yue Xu, Mingtao Nie, Tianle Li +4
Robot learning from real-world demonstrations is currently constrained by data scaling. Universal Manipulation Interface (UMI) provides an efficient robot-free data collection inte…
Revisiting Articulated Parts Perception in Robot Manipulation
Xiaoqian Wu, Yejie Guo, Xiaoyang Chen +3
We are surrounded by various objects with movable, articulated parts, e.g., box, handle, door. An accurate and generalizable perception of articulated parts is essential to enhance…
OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control
Yunshen Wang, Shaohang Zhu, Peiyuan Zhi +7
High-fidelity motion tracking serves as the ultimate litmus test for generalizable, human-level motor skills. However, current policies often hit a "generality barrier": as motion…
The Great March 100: 100 Detail-oriented Tasks for Evaluating Embodied AI Agents
Ziyu Wang, Chenyuan Liu, Yushun Xiang +16
Recently, with the rapid development of robot learning and imitation learning, numerous datasets and methods have emerged. However, these datasets and their task designs often lack…
Diagnose, Correct, and Learn from Manipulation Failures via Visual Symbols
Xianchao Zeng, Xinyu Zhou, Youcheng Li +5
Vision-Language-Action (VLA) models have recently achieved remarkable progress in robotic manipulation, yet they remain limited in failure diagnosis and learning from failures. Add…
RoboHiMan: A Hierarchical Evaluation Paradigm for Compositional Generalization in Long-Horizon Manipulation
Yangtao Chen, Zixuan Chen, Nga Teng Chan +6
Enabling robots to flexibly schedule and compose learned skills for novel long-horizon manipulation under diverse perturbations remains a core challenge. Early explorations with en…
exUMI: Extensible Robot Teaching System with Action-aware Task-agnostic Tactile Representation
Yue Xu, Litao Wei, Pengyu An +2
Tactile-aware robot learning faces critical challenges in data collection and representation due to data scarcity and sparsity, and the absence of force feedback in existing system…
SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning
Hanzhen Wang, Jiaming Xu, Yushun Xiang +4
Pruning is a typical acceleration technique for compute-bound models by removing computation on unimportant values. Recently, it has been applied to accelerate Vision-Language-Acti…