| 2025 | COLT | Mean-field analysis of polynomial-width two-layer neural network beyond finite time horizon. | Margalit Glasgow, Denny Wu, Joan Bruna |
| 2025 | ICLR | Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers. | Lei Chen, Joan Bruna, Alberto Bietti |
| 2025 | ICLR | Quality over Quantity in Attention Layers: When Adding More Heads Hurts. | Noah Amsel, Gilad Yehudai, Joan Bruna |
| 2025 | ICML | Thermalizer: Stable autoregressive neural emulation of spatiotemporal chaos. | Christian Pedersen, Laure Zanna, Joan Bruna |
| 2024 | COLT | Computational-Statistical Gaps in Gaussian Single-Index Models (Extended Abstract). | Alex Damian, Loucas Pillaud-Vivien, Jason D. Lee, Joan Bruna |
| 2024 | ICLR | Symmetric Single Index Learning. | Aaron Zweig, Joan Bruna |
| 2023 | ICML | Beyond the Edge of Stability via Two-step Gradient Updates. | Lei Chen, Joan Bruna |
| 2023 | ICML | Conditionally Strongly Log-Concave Generative Models. | Florentin Guth, Etienne Lempereur, Joan Bruna, Stphane Mallat |
| 2022 | COLT | Lattice-Based Methods Surpass Sum-of-Squares in Clustering. | Ilias Zadik, Min Jae Song, Alexander S. Wein, Joan Bruna |
| 2022 | CVPR | Neural Fields as Learnable Kernels for 3D Reconstruction. | Francis Williams, Zan Gojcic, Sameh Khamis, Denis Zorin, Joan Bruna, Sanja Fidler, Or Litany |
| 2022 | ECCV | Cartoon Explanations of Image Classifiers. | Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok |
| 2022 | ICLR | On feature learning in neural networks with global convergence guarantees. | Zhengdao Chen, Eric Vanden-Eijnden, Joan Bruna |
| 2022 | ICML | Extended Unconstrained Features Model for Exploring Deep Neural Collapse. | Tom Tirer, Joan Bruna |
| 2021 | AAAI | A Permutation-Equivariant Neural Network Architecture For Auction Design. | Jad Rahme, Samy Jelassi, Joan Bruna, S. Matthew Weinberg |
| 2021 | CVPR | Neural Splines: Fitting 3D Surfaces With Infinitely-Wide Neural Networks. | Francis Williams, Matthew Trager, Joan Bruna, Denis Zorin |
| 2021 | ICASSP | Learning the Relevant Substructures for Tasks on Graph Data. | Lei Chen, Zhengdao Chen, Joan Bruna |
| 2021 | ICLR | On Graph Neural Networks versus Graph-Augmented MLPs. | Lei Chen, Zhengdao Chen, Joan Bruna |
| 2021 | ICML | Offline Contextual Bandits with Overparameterized Models. | David Brandfonbrener, William F. Whitney, Rajesh Ranganath, Joan Bruna |
| 2021 | ICML | On Energy-Based Models with Overparametrized Shallow Neural Networks. | Carles Domingo-Enrich, Alberto Bietti, Eric Vanden-Eijnden, Joan Bruna |
| 2021 | ICML | A Functional Perspective on Learning Symmetric Functions with Neural Networks. | Aaron Zweig, Joan Bruna |
| 2021 | STOC | Continuous LWE. | Joan Bruna, Oded Regev, Min Jae Song, Yi Tang |
| 2020 | ICASSP | Stability of Graph Neural Networks to Relative Perturbations. | Fernando Gama, Alejandro Ribeiro, Joan Bruna |
| 2020 | ICLR | Geometric Insights into the Convergence of Nonlinear TD Learning. | David Brandfonbrener, Joan Bruna |
| 2020 | ICLR | Pure and Spurious Critical Points: a Geometric Study of Linear Networks. | Matthew Trager, Kathln Kohn, Joan Bruna |
| 2020 | ICML | Extra-gradient with player sampling for faster convergence in n-player games. | Samy Jelassi, Carles Domingo-Enrich, Damien Scieur, Arthur Mensch, Joan Bruna |
| 2020 | ICML | A Rate-Distortion Framework for Explaining Black-Box Model Decisions. | Stefan Kolek, Duc Anh Nguyen, Ron Levie, Joan Bruna, Gitta Kutyniok |
| 2020 | UAI | Provably Efficient Third-Person Imitation from Offline Observation. | Aaron Zweig, Joan Bruna |
| 2019 | CVPR | Deep Geometric Prior for Surface Reconstruction. | Francis Williams, Teseo Schneider, Cludio T. Silva, Denis Zorin, Joan Bruna, Daniele Panozzo |
| 2019 | ICLR | Supervised Community Detection with Line Graph Neural Networks. | Zhengdao Chen, Lisha Li, Joan Bruna |
| 2019 | ICLR | Diffusion Scattering Transforms on Graphs. | Fernando Gama, Alejandro Ribeiro, Joan Bruna |
| 2019 | ICML | Approximating Orthogonal Matrices with Effective Givens Factorization. | Thomas Frerix, Joan Bruna |
| 2019 | ICML | Neuron birth-death dynamics accelerates gradient descent and converges asymptotically. | Grant M. Rotskoff, Samy Jelassi, Joan Bruna, Eric Vanden-Eijnden |
| 2018 | CVPR | Surface Networks. | Ilya Kostrikov, Zhongshi Jiang, Daniele Panozzo, Denis Zorin, Joan Bruna |
| 2018 | ICLR | Divide and Conquer Networks. | Alex Nowak, David Folqu, Joan Bruna |
| 2018 | ICMLA | Graph Neural Networks for IceCube Signal Classification. | Nicholas Choma, Federico Monti, Lisa Gerhardt, Tomasz Palczewski, Zahra Ronaghi, Prabhat, Wahid Bhimji, Michael M. Bronstein, Spencer R. Klein, Joan Bruna |
| 2017 | ICLR | Topology and Geometry of Half-Rectified Network Optimization. | C. Daniel Freeman, Joan Bruna |
| 2017 | ICLR | Understanding Trainable Sparse Coding with Matrix Factorization. | Thomas Moreau, Joan Bruna |
| 2015 | ICASSP | Source separation with scattering Non-Negative Matrix Factorization. | Joan Bruna, Pablo Sprechmann, Yann LeCun |
| 2015 | ICCV | Unsupervised Learning of Spatiotemporally Coherent Metrics. | Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun |
| 2011 | CVPR | Classification with scattering operators. | Joan Bruna, Stphane Mallat |
| 2010 | ESANN | Geometric models with co-occurrence groups. | Joan Bruna, Stphane Mallat |