2 citations · 2 across the 26 of their papers we have counts for
20 papers · 1 filter
GeoCFM: Positive-Only Conditional Flow Matching for Mineral Occurrence Sampling
Moshe Eliasof, Eldad Haber
Critical mineral discovery is a positive-only problem: deposits are observed as sparse locations, while unlabeled regions are not reliable negatives, and similar geophysical signat…
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…
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…
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…
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…
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…
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…
Learning to Advect: A Neural Semi-Lagrangian Architecture for Weather Forecasting
Carlos A. Pereira, Stéphane Gaudreault, Valentin Dallerit +9
Machine-learning approaches to weather forecasting often employ a monolithic architecture in which distinct physical mechanisms, such as advection, diffusive mixing, thermodynamic…
TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows
Moshe Eliasof, Eldad Haber, Carola-Bibiane Schönlieb
We introduce TANGO -- a dynamical systems inspired framework for graph representation learning that governs node feature evolution through a learned energy landscape and its associ…
Fast and Flexible Probabilistic Forecasting of Dynamical Systems using Flow Matching and Physical Perturbation
Siddharth Rout, Eldad Haber, Stephane Gaudreault
Learning dynamical systems from incomplete or noisy data is inherently ill-posed, as a single observation may correspond to multiple plausible futures. While physics-based ensemble…
Graph Flow Matching: Enhancing Image Generation with Neighbor-Aware Flow Fields
Md Shahriar Rahim Siddiqui, Moshe Eliasof, Eldad Haber
Flow matching casts sample generation as learning a continuous-time velocity field that transports noise to data. Existing flow matching networks typically predict each point's vel…
Towards Efficient Training of Graph Neural Networks: A Multiscale Approach
Eshed Gal, Moshe Eliasof, Carola-Bibiane Schönlieb +3
Graph Neural Networks (GNNs) have become powerful tools for learning from graph-structured data, finding applications across diverse domains. However, as graph sizes and connectivi…
Iterative Flow Matching: Path Correction and Gradual Refinement for Enhanced Generative Modeling
Eldad Haber, Shadab Ahamed, Md. Shahriar Rahim Siddiqui +2
Generative models for image generation are now commonly used for a wide variety of applications, ranging from guided image generation for entertainment to solving inverse problems.…
Multiscale Training of Convolutional Neural Networks
Shadab Ahamed, Niloufar Zakariaei, Eldad Haber +1
Training convolutional neural networks (CNNs) on high-resolution images is often bottlenecked by the cost of evaluating gradients of the loss on the finest spatial mesh. To address…
Learning Regularization for Graph Inverse Problems
Moshe Eliasof, Md Shahriar Rahim Siddiqui, Carola-Bibiane Schönlieb +1
In recent years, Graph Neural Networks (GNNs) have been utilized for various applications ranging from drug discovery to network design and social networks. In many applications, i…
Advection Augmented Convolutional Neural Networks
Niloufar Zakariaei, Siddharth Rout, Eldad Haber +1
Many problems in physical sciences are characterized by the prediction of space-time sequences. Such problems range from weather prediction to the analysis of disease propagation a…
Graph Neural Reaction Diffusion Models
Moshe Eliasof, Eldad Haber, Eran Treister
The integration of Graph Neural Networks (GNNs) and Neural Ordinary and Partial Differential Equations has been extensively studied in recent years. GNN architectures powered by ne…
Paired Autoencoders for Likelihood-free Estimation in Inverse Problems
Matthias Chung, Emma Hart, Julianne Chung +2
We consider the solution of nonlinear inverse problems where the forward problem is a discretization of a partial differential equation. Such problems are notoriously difficult to…
Quadratic Binary Optimization with Graph Neural Networks
Moshe Eliasof, Eldad Haber
We investigate a link between Graph Neural Networks (GNNs) and Quadratic Unconstrained Binary Optimization (QUBO) problems, laying the groundwork for GNNs to approximate solutions…
An Over Complete Deep Learning Method for Inverse Problems
Moshe Eliasof, Eldad Haber, Eran Treister
Obtaining meaningful solutions for inverse problems has been a major challenge with many applications in science and engineering. Recent machine learning techniques based on proxim…