Hello, I'm Oliver Hausdörfer

I am a PhD candidate at Prof. Schoellig’s lab at Technical University of Munich. My main interests include control for complex systems, reinforcement learning, and robotics. Previously, I completed a M.Sc. degree in Robotics at TUM, and wrote my master’s thesis with Prof. Ijspeert. I was at Robert Bosch GmbH and in the Formula Student. Member of AI Grid.


Publications

Communication Compression for Tensor Parallel LLM Inference

Communication Compression for Tensor Parallel LLM Inference

NeurIPS, 2024 Conference (workshop)

Inter-GPU communication compression for Large Language Models leads to up to 2x reduction of time-to-first-token with negligible model performance degradation.

Latent Action Priors From a Single Gait Cycle Demonstration for Online Imitation Learning

Latent Action Priors From a Single Gait Cycle Demonstration for Online Imitation Learning

CoRL, 2024 Conference (workshop)

A single gait cycle of expert demonstration significantly improves achieved reward and visual appearance of the learned gait in locomotion tasks - even for transfer tasks.

Mechanoactivation of Single Stem Cells in Microgels Using a 3D-Printed Stimulation Device

Mechanoactivation of Single Stem Cells in Microgels Using a 3D-Printed Stimulation Device

Small Methods, 2024 Journal Paper

3D-printed chip for mechanoactivation at single-cell level to study intracellular calcium signaling and translocation.

Projects

Robotic Manipulator Builds Lego

Robotic Manipulator Builds Lego

Student Project, 2024

A Franka Emika FR3 robotic manipulator builds lego structures.

TUfast TU Dresden

TUfast TU Dresden

Project, 2021

Teaching and studying tool for TU Dresden with 3500 users. Awarded with the german Digital Changemaker Award.

Miscellaneous

Winning robot competition at the ETH Robotics Summer School

Winning robot competition at the ETH Robotics Summer School

Summer School, 2024

Building a robot for autonomous outdoor exploration and artifact detection

Young scientist award at KIRO 2024

Young scientist award at KIRO 2024

Conference, 2024

KIRO2024 was the first german AI-in-robotics conference

Teaching

Practical course: Hands-On Introduction to Deep Reinforcement Learning

SS 2024

Assignments 1, 2, 3


Check out the Huberman Lab podcast for a healthy lifestyle and science-based tools for everyday life. The Lex Fridman podcast for broadening your worldview and socially concerning topics. I like to look at DailyArt.