activity
20242026
collaborators

7 papers

cs.RO2026

RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning

Kun Lei, Huanyu Li, Dongjie Yu +6

Real-world robotic manipulation in homes and factories demands reliability, efficiency, and robustness that approach or surpass those of skilled human operators. We present RL-100,…

cs.RO2026

DA-MMP: Learning Coordinated and Accurate Throwing with Dynamics-Aware Motion Manifold Primitives

Chi Chu, Huazhe Xu

Dynamic manipulation is a key capability for advancing robot performance, enabling skills such as tossing. While recent learning-based approaches have pushed the field forward, mos…

cs.RO2026

Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation

Huanyu Li, Kun Lei, Sheng Zang +5

Post-training algorithms based on deep reinforcement learning can push the limits of robotic models for specific objectives, such as generalizability, accuracy, and robustness. How…

cs.LG2025

Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints

Zilin Kang, Chonghua Liao, Tingqiang Xu +1

We propose ERA, a new paradigm that constrains the sampling entropy above given thresholds by applying specially designed activations to the outputs of models. Our approach demonst…

cs.RO2025

Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation

Han Xue, Jieji Ren, Wendi Chen +5

Humans can accomplish complex contact-rich tasks using vision and touch, with highly reactive capabilities such as fast response to external changes and adaptive control of contact…

cs.LG2025

Looking Backward: Retrospective Backward Synthesis for Goal-Conditioned GFlowNets

Haoran He, Can Chang, Huazhe Xu +1

Generative Flow Networks (GFlowNets), a new family of probabilistic samplers, have demonstrated remarkable capabilities to generate diverse sets of high-reward candidates, in contr…