collaborators

9 papers

cs.LG2026

The Multiscale Single-Index Model: A Stylized Model for Hierarchical Feature Learning

Joan Bruna

We consider the Multiscale Single-Index Model (MSIM), first introduced in \cite{oymak2021learning}, as a stylized model for hierarchical learning with \emph{scale separation}. Each…

cs.LG2026

Lost in Tokenization: Fundamental Trade-offs in Graph Tokenization for Transformers

Maya Bechler-Speicher, Gilad Yehudai, Gil Harari +3

Transformers have become a central architecture for graph learning, but their application to graphs requires first choosing a tokenization: a graph-to-token map that determines whi…

stat.ML2026

Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks

Margalit Glasgow, Joan Bruna

We consider one-hidden layer neural networks trained in the feature-learning regime using gradient descent, and relate the output of the finite-width network to it…

cs.CL2026

Geometric Factual Recall in Transformers

Shauli Ravfogel, Gilad Yehudai, Joan Bruna +1

How do transformer language models memorize factual associations? A common view casts internal weight matrices as associative memories over pairs of embeddings, requiring parameter…

cs.LG2025

Geometry and Optimization of Shallow Polynomial Networks

Yossi Arjevani, Joan Bruna, Joe Kileel +2

We study shallow neural networks with monomial activations and output dimension one. The function space for these models can be identified with a set of symmetric tensors with boun…

cs.LG2025

Axial Neural Networks for Dimension-Free Foundation Models

Hyunsu Kim, Jonggeon Park, Joan Bruna +2

The advent of foundation models in AI has significantly advanced general-purpose learning, enabling remarkable capabilities in zero-shot inference and in-context learning. However,…