Ondrej Biza
I am a researcher at the Robotics and AI Institute (formerly Boston Dynamics AI Institute) in Cambridge, MA.
My research goal is to build generalist robots for household and industrial settings. Most recently, I have been working on autonomous real-world reinforcement learning. I am especially interested in developing general-purpose reward models that can supervised real-world robot learning. Further, I have been investigating policy learning methods that combine behavior cloning pre-training and reinforcement learning fine-tuning.
I was fortunate to intern at Google Brain in 2022 and the Boston Dynamics AI Institute in 2023-2024. I recevied my PhD in Computer Science from Northeastern University in 2024 and my undergraduate degree from Czech Technical University in 2019.
at gmail dot com
news
- December, 2025 We presented ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks at NeurIPS'25 in San Diego.
- May, 2025 I presented On-Robot Reinforcement Learning with Goal-Contrastive Rewards at ICRA'25 in Atlanta.
- Oct, 2024 I joined the Boston Dynamics AI Institute as a researcher.
- Sep, 2024 I defended my PhD thesis!
selected publications
On-Robot Reinforcement Learning with Goal-Contrastive Rewards
Ondrej Biza, Thomas Weng, Lingfeng Sun, Karl Schmeckpeper, Tarik Kelestemur, Yecheng Jason Ma, Robert Platt, Jan-Willem van de Meent, Lawson L. S. Wong. In ICRA, 2025.
