Postdoc. See my papers here.
Working on reinforcement learning and generative models.
Theoretical: Advanced the understanding of optimal transport in machine learning, specifically by rethinking its application to reinforcement learning.
Engineering: Designed neural computer architectures that generate molecules with favorable pharmacokinetics. These models were later validated in real-world applications.
Practical: Developed a CowSwap solver and built various AI layers to optimize token swaps, asset bridging, and other decentralized finance operations.
Education: Created and taught several courses on reinforcement learning and deep generative models, covering a range of topics from GANs to flow-matching.
Open to discussing new ideas and potential collaborations. Feel free to connect.
Social: @machinestein
Last update: June 11, 2025