Douglas Chen — accepted AI-conference papers

2026

Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps

Peter Holderrieth, Douglas Chen, Luca Eyring, Ishin Shah, Giri Anantharaman, Yutong He +4

ICML 2026poster

Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called reward alignment. We argue that efficient reward alignment should be a property of the generative model itself, not an af…

Cited by 0 Source ↗Scholar ↗

2026

Sample Efficient Full-Finetuning of Generative Control Policies

Sarvesh Patil, Mitsuhiko Nakamoto, Shashwat Saxena, Manan Agarwal, Giri Anantharaman, Cleah Winston +11

ICML 2026poster

Generative control policies (GCPs), such as diffusion- and flow-based control policies, have emerged as effective parameterizations for robot learning. Yet there remains substantial debate over how to sample efficiently fine-tune them via reinforcement learning. A prevailing view holds that fine-tun…

Cited by 0 Source ↗Scholar ↗