7 papers
Foresight Residual RL for Long-Horizon Robot Manipulation with Vision-Language-Action Models
Yuhan Liu, Xinyu Zhang, Litao Liu +1
Vision-Language-Action (VLA) policies offer strong general-purpose manipulation priors, but often fail on tight-tolerance, contact-rich assembly due to long-horizon credit assignme…
Glove2Hand: Synthesizing Natural Hand-Object Interaction from Multi-Modal Sensing Gloves
Xinyu Zhang, Ziyi Kou, Chuan Qin +7
Understanding hand-object interaction (HOI) is fundamental to computer vision, robotics, and AR/VR. However, conventional hand videos often lack essential physical information such…
Motion Blender Gaussian Splatting for Dynamic Scene Reconstruction
Xinyu Zhang, Haonan Chang, Yuhan Liu +1
Gaussian splatting has emerged as a powerful tool for high-fidelity reconstruction of dynamic scenes. However, existing methods primarily rely on implicit motion representations, s…
Failure Forecasting Boosts Robustness of Sim2Real Rhythmic Insertion Policies
Yuhan Liu, Xinyu Zhang, Haonan Chang +1
This paper addresses the challenges of Rhythmic Insertion Tasks (RIT), where a robot must repeatedly perform high-precision insertions, such as screwing a nut into a bolt with a wr…
Autoregressive Action Sequence Learning for Robotic Manipulation
Xinyu Zhang, Yuhan Liu, Haonan Chang +2
Designing a universal policy architecture that performs well across diverse robots and task configurations remains a key challenge. In this work, we address this by representing ro…
Scaling Manipulation Learning with Visual Kinematic Chain Prediction
Xinyu Zhang, Yuhan Liu, Haonan Chang +1
Learning general-purpose models from diverse datasets has achieved great success in machine learning. In robotics, however, existing methods in multi-task learning are typically co…