| 2025 | ICCV | Beyond [cls]: Exploring the True Potential of Masked Image Modeling Representations. | Marcin Przewiezlikowski, Randall Balestriero, Wojciech Jasinski, Marek Smieja, Bartosz Zielinski |
| 2025 | ICLR | No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data. | Daniel Cai, Randall Balestriero |
| 2025 | ICLR | Cross-Entropy Is All You Need To Invert the Data Generating Process. | Patrik Reizinger, Alice Bizeul, Attila Juhos, Julia E. Vogt, Randall Balestriero, Wieland Brendel, David A. Klindt |
| 2025 | ICLR | X-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs. | Vlad Sobal, Mark Ibrahim, Randall Balestriero, Vivien Cabannes, Diane Bouchacourt, Pietro Astolfi, Kyunghyun Cho, Yann LeCun |
| 2025 | ICML | Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research. | Patrik Reizinger, Randall Balestriero, David A. Klindt, Wieland Brendel |
| 2025 | ICML | Mitigating over-Exploration in Latent Space Optimization using les. | Omer Ronen, Ahmed Imtiaz Humayun, Richard G. Baraniuk, Randall Balestriero, Bin Yu |
| 2025 | MICCAI | General Methods Make Great Domain-Specific Foundation Models: A Case-Study on Fetal Ultrasound. | Jakob Ambsdorf, Asbjrn Munk, Sebastian Nrgaard Llambias, Anders Nymark Christensen, Kamil Wojciech Mikolaj, Randall Balestriero, Martin Grnnebk Tolsgaard, Aasa Feragen, Mads Nielsen |
| 2024 | ICML | Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation. | Randall Balestriero, Romain Cosentino, Sarath Shekkizhar |
| 2024 | ICML | How Learning by Reconstruction Produces Uninformative Features For Perception. | Randall Balestriero, Yann LeCun |
| 2024 | ICML | Deep Networks Always Grok and Here is Why. | Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk |
| 2023 | CVPR | SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries. | Ahmed Imtiaz Humayun, Randall Balestriero, Guha Balakrishnan, Richard G. Baraniuk |
| 2023 | ICASSP | Fast and Exact Enumeration of Deep Networks Partitions Regions. | Randall Balestriero, Yann LeCun |
| 2023 | ICASSP | Police: Provably Optimal Linear Constraint Enforcement For Deep Neural Networks. | Randall Balestriero, Yann LeCun |
| 2023 | ICASSP | On Minimal Variations for Unsupervised Representation Learning. | Vivien Cabannes, Alberto Bietti, Randall Balestriero |
| 2023 | ICCV | Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need. | Vivien Cabannes, Lon Bottou, Yann LeCun, Randall Balestriero |
| 2023 | ICLR | The hidden uniform cluster prior in self-supervised learning. | Mido Assran, Randall Balestriero, Quentin Duval, Florian Bordes, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael G. Rabbat, Nicolas Ballas |
| 2023 | ICLR | ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations. | Badr Youbi Idrissi, Diane Bouchacourt, Randall Balestriero, Ivan Evtimov, Caner Hazirbas, Nicolas Ballas, Pascal Vincent, Michal Drozdzal, David Lopez-Paz, Mark Ibrahim |
| 2023 | ICML | The SSL Interplay: Augmentations, Inductive Bias, and Generalization. | Vivien Cabannes, Bobak Toussi Kiani, Randall Balestriero, Yann LeCun, Alberto Bietti |
| 2023 | ICML | RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their Rank. | Quentin Garrido, Randall Balestriero, Laurent Najman, Yann LeCun |
| 2022 | ACSSC | Spatial Transformer K-Means. | Romain Cosentino, Randall Balestriero, Yanis Bahroun, Anirvan M. Sengupta, Richard G. Baraniuk, Behnaam Aazhang |
| 2022 | CVPR | Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values. | Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk |
| 2022 | ICASSP | DeepHull: Fast Convex Hull Approximation in High Dimensions. | Randall Balestriero, Zichao Wang, Richard G. Baraniuk |
| 2022 | ICASSP | No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds. | Ahmed Imtiaz Humayun, Randall Balestriero, Anastasios Kyrillidis, Richard G. Baraniuk |
| 2022 | ICLR | MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining. | Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk |
| 2021 | ICASSP | Wearing A Mask: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels. | Sina Alemohammad, Hossein Babaei, Randall Balestriero, Matt Y. Cheung, Ahmed Imtiaz Humayun, Daniel LeJeune, Naiming Liu, Lorenzo Luzi, Jasper Tan, Zichao Wang, Richard G. Baraniuk |
| 2021 | ICLR | The Recurrent Neural Tangent Kernel. | Sina Alemohammad, Zichao Wang, Randall Balestriero, Richard G. Baraniuk |
| 2019 | ICLR | From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference. | Randall Balestriero, Richard G. Baraniuk |
| 2019 | ICLR | A Max-Affine Spline Perspective of Recurrent Neural Networks. | Zichao Wang, Randall Balestriero, Richard G. Baraniuk |
| 2018 | ICML | A Spline Theory of Deep Networks. | Randall Balestriero, Richard G. Baraniuk |
| 2018 | ICML | Spline Filters For End-to-End Deep Learning. | Randall Balestriero, Romain Cosentino, Herv Glotin, Richard G. Baraniuk |
| 2017 | ICLR | Fast Chirplet Transform Injects Priors in Deep Learning of Animal Calls and Speech. | Herv Glotin, Julien Ricard, Randall Balestriero |
| 2015 | ICDM | Scattering Decomposition for Massive Signal Classification: From Theory to Fast Algorithm and Implementation with Validation on International Bioacoustic Benchmark. | Randall Balestriero, Herv Glotin |