collaborators

5 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

Exact Posterior Score Estimation for Solving Linear Inverse Problems

Abbas Mammadov, Ozgur Kara, Kaan Oktay +5

Diffusion and flow-based models learn powerful data priors by training a denoiser to reverse Gaussian corruption. To use this prior to solve a linear inverse problem, one needs to…

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.CV2026

Variational Flow Maps: Make Some Noise for One-Step Conditional Generation

Abbas Mammadov, So Takao, Bohan Chen +4

Flow maps enable high-quality image generation in a single forward pass. However, unlike iterative diffusion models, their lack of an explicit sampling trajectory impedes incorpora…

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…