5 citations · 6 across the 8 of their papers we have counts for
9 papers
Find Something You Can't Do: Agentic Real-World Reinforcement Learning for Self-Improving VLA Models
Yuan Fang, Zechu Li, Haolei Tong +2
Vision--language--action (VLA) models provide strong priors for robotic manipulation but are typically deployed as frozen policies, unable to improve from their own failures. Real-…
Scalable Multi-Task Data Generation via Reinforcement Learning for Language-Conditioned Bimanual Dexterous Manipulation
Zechu Li, Yufeng Jin, Puze Liu +2
A key bottleneck in training generalist policies for bimanual dexterous manipulation is the lack of large-scale, high-quality datasets. Synthetic data generation in simulation prov…
HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning
Zechu Li, Yufeng Jin, Xiaoyang Liu +4
Reinforcement learning (RL) has become a powerful paradigm for robot learning, particularly in sim-to-real settings, but its broader adoption remains limited by the engineering pip…
Nautilus: From One Prompt to Plug-and-Play Robot Learning
Yufeng Jin, Jianfei Guo, Xiaogang Jia +8
Robot learning research is fragmented across policy families, benchmark suites, and real robots; each implementation is entangled with the others in a complex combination matrix, m…
SE(3)-PoseFlow: Estimating 6D Pose Distributions for Uncertainty-Aware Robotic Manipulation
Yufeng Jin, Niklas Funk, Vignesh Prasad +4
Object pose estimation is a fundamental problem in robotics and computer vision, yet it remains challenging due to partial observability, occlusions, and object symmetries, which i…
Morphologically Symmetric Reinforcement Learning for Ambidextrous Bimanual Manipulation
Zechu Li, Yufeng Jin, Daniel Ordonez Apraez +3
Humans naturally exhibit bilateral symmetry in their gross manipulation skills, effortlessly mirroring simple actions between left and right hands. Bimanual robots-which also featu…
DIME:Diffusion-Based Maximum Entropy Reinforcement Learning
Onur Celik, Zechu Li, Denis Blessing +5
Maximum entropy reinforcement learning (MaxEnt-RL) has become the standard approach to RL due to its beneficial exploration properties. Traditionally, policies are parameterized us…
Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient
Zechu Li, Rickmer Krohn, Tao Chen +3
Deep reinforcement learning (RL) algorithms typically parameterize the policy as a deep network that outputs either a deterministic action or a stochastic one modeled as a Gaussian…
Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation
Marcel Torne, Anthony Simeonov, Zechu Li +4
Imitation learning methods need significant human supervision to learn policies robust to changes in object poses, physical disturbances, and visual distractors. Reinforcement lear…