Joan Bruna

papers

1,138

total citations

papers (24)

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

NEURIPS 2022arXiv

citations

Neural Fields As Learnable Kernels for 3D Reconstruction

CVPR 2022arXiv

citations

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

CVPR 2021arXiv

citations

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

NEURIPS 2020arXiv

citations

On the Cryptographic Hardness of Learning Single Periodic Neurons

NEURIPS 2021arXiv

citations

A Dynamical Central Limit Theorem for Shallow Neural Networks

NEURIPS 2020arXiv

citations

Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation

NEURIPS 2023arXiv

citations

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

NEURIPS 2020arXiv

citations

Cartoon Explanations of Image Classifiers

ECCV 2022arXiv

citations

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

NEURIPS 2023arXiv

citations

Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos

ICML 2025arXiv

citations

Exponential Separations in Symmetric Neural Networks

NEURIPS 2022arXiv

citations

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

ICLR 2025arXiv

citations

Symmetric Single Index Learning

ICLR 2024arXiv

citations

On Non-Linear operators for Geometric Deep Learning

NEURIPS 2022arXiv

citations

Emergence of Linear Truth Encodings in Language Models

NEURIPS 2025arXiv

citations

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

NEURIPS 2025

citations

Compositional Reasoning with Transformers, RNNs, and Chain of Thought

NEURIPS 2025arXiv

citations

Axial Neural Networks for Dimension-Free Foundation Models

NEURIPS 2025arXiv

citations

On Single-Index Models beyond Gaussian Data

NEURIPS 2023

citations

On the Sample Complexity of Learning under Geometric Stability

NEURIPS 2021

citations

Joan Bruna

papers (24)

Can Graph Neural Networks Count Substructures?

Offline RL Without Off-Policy Evaluation

Learning single-index models with shallow neural networks

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

Neural Fields As Learnable Kernels for 3D Reconstruction

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

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

On the Cryptographic Hardness of Learning Single Periodic Neurons

A Dynamical Central Limit Theorem for Shallow Neural Networks

Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

Cartoon Explanations of Image Classifiers

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos

Exponential Separations in Symmetric Neural Networks

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

Symmetric Single Index Learning

On Non-Linear operators for Geometric Deep Learning

Emergence of Linear Truth Encodings in Language Models

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

Compositional Reasoning with Transformers, RNNs, and Chain of Thought

Axial Neural Networks for Dimension-Free Foundation Models

On Single-Index Models beyond Gaussian Data

On the Sample Complexity of Learning under Geometric Stability

papers (24)

Can Graph Neural Networks Count Substructures?

Offline RL Without Off-Policy Evaluation

Learning single-index models with shallow neural networks

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

Neural Fields As Learnable Kernels for 3D Reconstruction

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

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

On the Cryptographic Hardness of Learning Single Periodic Neurons

A Dynamical Central Limit Theorem for Shallow Neural Networks

Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

Cartoon Explanations of Image Classifiers

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos

Exponential Separations in Symmetric Neural Networks

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

Symmetric Single Index Learning

On Non-Linear operators for Geometric Deep Learning

Emergence of Linear Truth Encodings in Language Models

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

Compositional Reasoning with Transformers, RNNs, and Chain of Thought

Axial Neural Networks for Dimension-Free Foundation Models

On Single-Index Models beyond Gaussian Data

On the Sample Complexity of Learning under Geometric Stability