Publications

Stochastic Online Optimization for Cyber-Physical and Robotic Systems

Hao Ma, Melanie Zeilinger, Michael Muehlebach

Published in Machine Learning, 2025

Paper | Bibtex | Demo

Efficient Model-Based Reinforcement Learning for Robot Control via Online Learning

Fang Nan, Hao Ma, Qinghua Guan, Josie Hughes, Michael Muehlebach, Marco Hutter

Published in The International Journal of Robotics Research, 2025

An online model-based reinforcement learning algorithm for efficient real-world robot control using dynamics models learned from interaction data.

Paper | Bibtex

Reinforcement learning with model-based feedforward inputs for robotic table tennis

Hao Ma, Dieter Büchler, Bernhard Schölkopf, Michael Muehlebach

Published in Autonomous Robots, 2023

Paper | Bibtex | Demo

SALAAD: Sparse And Low-Rank Adaptation via ADMM for Large Language Model Inference

Hao Ma, Melis Ilayda Bal, Liang Zhang, Bingcong Li, Niao He, Melanie Zeilinger, Michael Muehlebach

Published in International Conference on Machine Learning, 2026

A plug-and-play sparse and low-rank adaptation framework for large language model inference under heterogeneous memory budgets.

Paper | Bibtex

Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racing

Hao Ma, Sabrina Bodmer, Andrea Carron, Melanie Zeilinger, Michael Muehlebach

Published in Conference on Robot Learning, 2025

Paper | Bibtex | Demo | Dataset

Safe & Accurate at Speed with Tendons: A Robot Arm for Exploring Dynamic Motion

Simon Guist, Jan Schneider, Hao Ma, Le Chen, Vincent Berenz, Julian Martus, Heiko Ott, Felix Grüninger, Michael Muehlebach, Jonathan Fiene, Bernhard Schölkopf, Dieter Büchler

Published in Robotics: Science and Systems, 2024

Paper | Project | Bibtex

Data-Efficient Online Learning of Ball Placement in Robot Table Tennis

Philip Tobuschat, Hao Ma, Dieter Büchler, Bernhard Schölkopf, Michael Muehlebach

Published in International Conference on Intelligent Robots and Systems, 2023

Paper | Bibtex | Demo

Black-Box vs. Grey-Box: A Case Study on Learning Table Tennis Ball Trajectory Prediction with Spin and Impacts

Jan Achterhold, Philip Tobuschat, Hao Ma, Dieter Büchler, Michael Muehlebach and Joerg Stueckler

Published in Learning for Dynamics and Control Conference, 2023

Paper | Bibtex

A Learning-based Iterative Control Framework for Controlling a Robot Arm with Pneumatic Artificial Muscles

Hao Ma, Dieter Büchler, Bernhard Schölkopf, Michael Muehlebach

Published in Robotics: Science and Systems, 2022

Paper | Bibtex

Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control

Sabrina Bodmer, René Zurbrügg, Tifanny Portela, Hao Ma, Alexandre Didier, Marco Hutter, Colin Jones, Melanie Zeilinger

Published in arXiv preprint, 2026

Inference-time optimization grounds diffusion policies in robot reachability, collision-avoidance, and controller-level feasibility constraints without retraining.

Paper | Bibtex