3 papers
stat.ML2026
Meta Flow Maps enable scalable reward alignment
Peter Potaptchik, Adhi Saravanan, Abbas Mammadov +3
Controlling generative models is computationally expensive. This is because optimal alignment with a reward function--whether via inference-time steering or fine-tuning--requires e…
cs.LG2026
SigmaDock: Untwisting Molecular Docking With Fragment-Based SE(3) Diffusion
Alvaro Prat, Leo Zhang, Charlotte M. Deane +2
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…
cs.LG2026
Manifold Aware Denoising Score Matching (MAD)
Alona Levy-Jurgenson, Alvaro Prat, James Cuin +1
A major focus in designing methods for learning distributions defined on manifolds is to alleviate the need to implicitly learn the manifold so that learning can concentrate on the…