collaborators

10 papers

cs.CV2026

Any to Full: Prompting Depth Anything for Depth Completion in One Stage

Zhiyuan Zhou, Ruofeng Liu, Taichi Liu +4

Accurate, dense depth estimation is crucial for robotic perception, but commodity sensors often yield sparse or incomplete measurements due to hardware limitations. Existing RGBD-f…

cs.LG2026

Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning

Zhiyuan Zhou, Andy Peng, Charles Xu +4

Expressive continuous control policies, such as diffusion and flow models, form the backbone of recent advances in scaling imitation learning for simulated and real robot control.…

cs.LG2026

Reinforcement Learning with Action Chunking

Qiyang Li, Zhiyuan Zhou, Sergey Levine

We present Q-chunking, a simple yet effective recipe for improving reinforcement learning (RL) algorithms for long-horizon, sparse-reward tasks. Our recipe is designed for the offl…

cs.RO2026

Robust Finetuning of Vision-Language-Action Robot Policies via Parameter Merging

Yajat Yadav, Zhiyuan Zhou, Andrew Wagenmaker +2

Generalist robot policies, trained on large and diverse datasets, have demonstrated the ability to generalize across a wide spectrum of behaviors, enabling a single policy to act i…

cs.RO2025

Learning Spatial-Aware Manipulation Ordering

Yuxiang Yan, Zhiyuan Zhou, Xin Gao +5

Manipulation in cluttered environments is challenging due to spatial dependencies among objects, where an improper manipulation order can cause collisions or blocked access. Existi…

cs.LG2025

: a VLA That Learns From Experience

Physical Intelligence, Ali Amin, Raichelle Aniceto +53

We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience…