collaborators

8 papers

cs.LG2026

Score-Based Stabilization for Time-Dependent Problems

Eshed Gal, Eldad Haber, Uri Ascher

We propose a score-based stabilization framework for numerical simulation of partial differential equations, in which a learned score model defines a stabilization operator applied…

cs.LG2026

Probabilistic Gaussian Homotopy: A Probability-Space Continuation Framework for Nonconvex Optimization

Eshed Gal, Samy Wu Fung, Eldad Haber

We introduce Probabilistic Gaussian Homotopy (PGH), a probability-space continuation framework for nonconvex optimization. Unlike classical Gaussian homotopy, which smooths the obj…

cs.LG2026

Preconditioned Flow Matching

Shadab Ahamed, Eshed Gal, Md Shahriar Rahim Siddiqui +3

Flow matching (FM) learns vector fields by regressing stochastic velocity targets along intermediate distributions . We identify a geometric optimization bottleneck in this re…

cs.LG2026

Target-Aware Data Augmentation for SAT Prediction

Eshed Gal, Uri Ascher, Eldad Haber

Learning-based approaches to NP-hard problems have shown increasing promise, but their progress is fundamentally constrained by the high cost of generating labeled training data. I…

cs.LG2026

Conservative Flows: A New Paradigm of Generative Models

Eshed Gal, Md Shahriar Rahim Siddiqui, Moshe Eliasof +1

Modern generative modeling is dominated by transport from a noise prior to data. We propose an alternative paradigm in which generation is performed by a discrete stochastic dynami…

cs.LG2026

PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers

Eshed Gal, Moshe Eliasof, Siddharth Rout +1

The success of vision transformers-especially for generative modeling-is limited by the quadratic cost and weak spatial inductive bias of self-attention. We propose PDE-SSM, a spat…