DoMinO: Discrete Flow-Matching Policy Optimization
Apr 1, 2026
·
1 min read
Role: Project Co-Lead · Northwestern University (Remote) · Feb 2026 – Apr 2026
DoMinO is a reinforcement learning framework for fine-tuning discrete flow-matching models toward a reward.
What I did
- Co-developed the framework. DoMinO formulates discrete flow-matching inference as an inner Markov decision process, which enables exact trajectory log-likelihood optimization.
- Implemented the fine-tuning methods. REINFORCE- and PPO-based fine-tuning with cross-entropy and generalized KL regularization, to mitigate reward hacking and preserve sequence naturalness.
- Evaluated on biological sequence design. On regulatory DNA and protein design, DoMinO outperformed prior state-of-the-art baselines by 10.6% on DNA predicted activity and 15.4% on protein pred-ddG.
Paper: Discrete Flow Matching Policy Optimization. See also the research overview.
Authors
M.S. Student in Electrical and Computer Engineering
I am an M.S. student in Electrical and Computer Engineering at UC San Diego, with a B.S. in Electrical Engineering from National Taiwan University. I build AI agents and reinforcement learning methods for scientific discovery, including multi-agent systems for biomedical feature discovery and policy optimization for discrete generative models, and I previously worked as an LLM engineer intern at the Inventec Artificial Intelligence Center.