Joan Bruna

23

Papers

28

Total Citations

Papers (23)

Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos

Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers

Emergence of Linear Truth Encodings in Language Models

NeurIPS 2025arXiv

The Generative Leap: Tight Sample Complexity for Efficiently Learning Gaussian Multi-Index Models

Compositional Reasoning with Transformers, RNNs, and Chain of Thought

NeurIPS 2025arXiv

Axial Neural Networks for Dimension-Free Foundation Models

NeurIPS 2025arXiv

Neural Splines: Fitting 3D Surfaces With Infinitely-Wide Neural Networks

Neural Fields As Learnable Kernels for 3D Reconstruction

Cartoon Explanations of Image Classifiers

Can Graph Neural Networks Count Substructures?

NeurIPS 2020arXiv

A mean-field analysis of two-player zero-sum games

NeurIPS 2020arXiv

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

NeurIPS 2020arXiv

A Dynamical Central Limit Theorem for Shallow Neural Networks

NeurIPS 2020arXiv

Offline RL Without Off-Policy Evaluation

NeurIPS 2021arXiv

On the Sample Complexity of Learning under Geometric Stability

On the Cryptographic Hardness of Learning Single Periodic Neurons

NeurIPS 2021arXiv

When does return-conditioned supervised learning work for offline reinforcement learning?

NeurIPS 2022arXiv

Learning single-index models with shallow neural networks

NeurIPS 2022arXiv

On Non-Linear operators for Geometric Deep Learning

NeurIPS 2022arXiv

Exponential Separations in Symmetric Neural Networks

NeurIPS 2022arXiv

On Single-Index Models beyond Gaussian Data

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

NeurIPS 2023arXiv

Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation

NeurIPS 2023arXiv