Alvaro Prat — accepted AI-conference papers

2026

Meta Flow Maps enable scalable reward alignment

Peter Potaptchik, Adhi Saravanan, Abbas Mammadov, Alvaro Prat, Michael Albergo, Yee-Whye Teh

ICML 2026poster

Controlling generative models—whether via inference-time steering or fine-tuning—is expensive. Control relies on estimating the value function—typically necessitating costly trajectory simulations. To eliminate this bottleneck, we introduce *Meta Flow Maps (MFMs)*, stochastic extensions of consisten…

Cited by 0 Source ↗Scholar ↗

2026

SigmaDock: Untwisting Molecular Docking with Fragment-Based SE(3) Diffusion

Alvaro Prat, Leo Zhang, Charlotte Deane, Yee Whye Teh, Garrett M Morris

ICLR 2026poster

Determining the binding pose of a ligand to a protein, known as molecular docking, is a fundamental task in drug discovery. Generative approaches promise faster, improved, and more diverse pose sampling than physics-based methods, but are often hindered by chemically implausible outputs, poor genera…

Cited by 0 Source ↗code ↗Scholar ↗