18 citations · 69 across the 60 of their papers we have counts for
13 papers · 1 filter
CrossMean: Model Merging by Pairing Merged and Expert Activations
Moshe Eliasof
Model merging combines fine-tuned experts into one network without retraining, and closed-form methods compute each merged layer from statistics of its input activations. However,…
Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing
Ferran Hernandez Caralt, Simon Heilig, Adrián Bazaga +3
Empirical claims about the connection between over-squashing and long-range interactions in GNNs, can only be trusted if the benchmarks used to validate them genuinely require long…
Attention Graphons: A Graph Limit Perspective on Graph Transformers
Caio F. Deberaldini Netto, Moshe Eliasof, Luana Ruiz
Graph Transformers produce, for each attention head, a dense matrix of learned pairwise interactions. We ask a fundamental question: do these attention-induced graphs c…
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…
A Critical Audit of Spatiotemporal Forecasting Benchmark Datasets and Models
Kenneth Martin, Simon Heilig, Asja Fischer +3
Graph neural networks (GNNs) are routinely employed for spatiotemporal forecasting, yet their performance across widely used benchmark datasets is inconsistent. Here, we perform an…
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Brown Zaz, Mar Gonzàlez I Català, Ferran Hernandez Caralt +2
In the transductive setting, where the full graph is observed but node labels are only partially available, progress in semi-supervised node classification has largely focused on a…
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…
Bridging Input Feature Spaces Towards Graph Foundation Models
Moshe Eliasof, Krishna Sri Ipsit Mantri, Beatrice Bevilacqua +2
Unlike vision and language domains, graph learning lacks a shared input space, as input features differ across graph datasets not only in semantics, but also in value ranges and di…
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…
Towards Improved Sentence Representations using Token Graphs
Krishna Sri Ipsit Mantri, Carola-Bibiane Schönlieb, Zorah Lähner +1
Obtaining a single-vector representation from a Large Language Model's (LLM) token-level outputs is a critical step for nearly all sentence-level tasks. However, standard pooling m…
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…
Trajectory Stitching for Solving Inverse Problems with Flow-Based Models
Alexander Denker, Moshe Eliasof, Zeljko Kereta +1
Flow-based generative models have emerged as powerful priors for solving inverse problems. One option is to directly optimize the initial latent code (noise), such that the flow ou…
Learning from Historical Activations in Graph Neural Networks
Yaniv Galron, Hadar Sinai, Haggai Maron +1
Graph Neural Networks (GNNs) have demonstrated remarkable success in various domains such as social networks, molecular chemistry, and more. A crucial component of GNNs is the pool…