Balestriero, Randall

63 publications

ICLR 2025 $\mathbb{X}$-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

ICCV 2025 Beyond [cls]: Exploring the True Potential of Masked Image Modeling Representations Marcin Przewięźlikowski, Randall Balestriero, Wojciech Jasiński, Marek Śmieja, Bartosz Zieliński

ICLR 2025 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 Klindt

NeurIPS 2025 Curvature Tuning: Provable Training-Free Model Steering from a Single Parameter Leyang Hu, Matteo Gamba, Randall Balestriero

NeurIPS 2025 Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum Wenquan Lu, Jiaqi Zhang, Hugues Van Assel, Randall Balestriero

NeurIPS 2025 FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed Jiaqi Zhang, Juntuo Wang, Zhixin Sun, John Zou, Randall Balestriero

ICCV 2025 From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations Anthony Bisulco, Rahul Ramesh, Randall Balestriero, Pratik Chaudhari

NeurIPS 2025 Joint‑Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self‑Supervised Learning Hugues Van Assel, Mark Ibrahim, Tommaso Biancalani, Aviv Regev, Randall Balestriero

NeurIPS 2025 Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models Vlad Sobal, Wancong Zhang, Kyunghyun Cho, Randall Balestriero, Tim G. J. Rudner, Yann LeCun

ICML 2025 Mitigating Over-Exploration in Latent Space Optimization Using Les Omer Ronen, Ahmed Imtiaz Humayun, Richard Baraniuk, Randall Balestriero, Bin Yu

ICLR 2025 No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data Daniel Cai, Randall Balestriero

TMLR 2025 Occam’s Razor for SSL: Memory-Efficient Parametric Instance Discrimination Eric Gan, Patrik Reizinger, Alice Bizeul, Attila Juhos, Mark Ibrahim, Randall Balestriero, David Klindt, Wieland Brendel, Baharan Mirzasoleiman

ICML 2025 Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research Patrik Reizinger, Randall Balestriero, David Klindt, Wieland Brendel

ICLRW 2025 Stress-Testing Offline Reward-Free Reinforcement Learning: A Case for Planning with Latent Dynamics Models Vlad Sobal, Wancong Zhang, Kyunghyun Cho, Randall Balestriero, Tim G. J. Rudner, Yann LeCun

ICMLW 2024 $\mathbb{X}$-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

NeurIPSW 2024 $\mathbb{X}$-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

NeurIPSW 2024 A Graph Matching Approach to Balanced Data Sub-Sampling for Self-Supervised Learning Hugues Van Assel, Randall Balestriero

NeurIPSW 2024 Anomaly Detection in the Wild: Can SSL Handle Strong Distribution Imbalances? Daniel Otero, Rafael Mateus, Randall Balestriero

NeurIPSW 2024 Anomaly Detection in the Wild: Can SSL Handle Strong Distribution Imbalances? Daniel Otero, Rafael Mateus, Randall Balestriero

ICML 2024 Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation Randall Balestriero, Romain Cosentino, Sarath Shekkizhar

NeurIPSW 2024 DIETing: Self-Supervised Learning with Instance Discrimination Learns Identifiable Features Attila Juhos, Alice Bizeul, Patrik Reizinger, Randall Balestriero, David Klindt, Mark Ibrahim, Julia E Vogt, Wieland Brendel

NeurIPSW 2024 DIETing: Self-Supervised Learning with Instance Discrimination Learns Identifiable Features Attila Juhos, Alice Bizeul, Patrik Reizinger, David Klindt, Randall Balestriero, Mark Ibrahim, Julia E Vogt, Wieland Brendel

ICML 2024 Deep Networks Always Grok and Here Is Why Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk

ICMLW 2024 Deep Networks Always Grok and Here Is Why Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk

NeurIPSW 2024 For Perception Tasks: The Cost of LLM Pretraining by Next-Token Prediction Outweigh Its Benefits Randall Balestriero, Hai Huang

ICMLW 2024 Grokking and the Geometry of Circuit Formation Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk

ICML 2024 How Learning by Reconstruction Produces Uninformative Features for Perception Randall Balestriero, Yann Lecun

NeurIPSW 2024 Occam's Razor for Self Supervised Learning: What Is Sufficient to Learn Good Representations? Mark Ibrahim, David Klindt, Randall Balestriero

ICMLW 2024 ScaLES: Scalable Latent Exploration Score for Pre-Trained Generative Networks Omer Ronen, Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk, Bin Yu

NeurIPSW 2024 Self-Supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps Xue Xia, Randall Balestriero, Tao Zhang, Lorenz Hurni

NeurIPSW 2024 The Birth of Self Supervised Learning: A Supervised Theory Randall Balestriero, Yann LeCun

NeurIPS 2024 UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling Haider Al-Tahan, Quentin Garrido, Randall Balestriero, Diane Bouchacourt, Caner Hazirbas, Mark Ibrahim

NeurIPSW 2024 Visualizing Linear RNNs Through Unrolling Josue Casco-Rodriguez, Tyler Burley, Cj Barberan, Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk

ICCV 2023 Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need Vivien Cabannes, Leon Bottou, Yann Lecun, Randall Balestriero

NeurIPS 2023 An Information Theory Perspective on Variance-Invariance-Covariance Regularization Ravid Shwartz-Ziv, Randall Balestriero, Kenji Kawaguchi, Tim G. J. Rudner, Yann LeCun

TMLR 2023 Guillotine Regularization: Why Removing Layers Is Needed to Improve Generalization in Self-Supervised Learning Florian Bordes, Randall Balestriero, Quentin Garrido, Adrien Bardes, Pascal Vincent

ICLR 2023 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

ICMLW 2023 Provable Instance Specific Robustness via Linear Constraints Ahmed Imtiaz Humayun, Josue Casco-Rodriguez, Randall Balestriero, Richard Baraniuk

ICML 2023 RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their Rank Quentin Garrido, Randall Balestriero, Laurent Najman, Yann Lecun

CVPR 2023 SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries Ahmed Imtiaz Humayun, Randall Balestriero, Guha Balakrishnan, Richard G. Baraniuk

ICLR 2023 The Hidden Uniform Cluster Prior in Self-Supervised Learning Mido Assran, Randall Balestriero, Quentin Duval, Florian Bordes, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael Rabbat, Nicolas Ballas

ICML 2023 The SSL Interplay: Augmentations, Inductive Bias, and Generalization Vivien Cabannes, Bobak Kiani, Randall Balestriero, Yann Lecun, Alberto Bietti

ICLRW 2023 The SSL Interplay: Augmentations, Inductive Bias, and Generalization Vivien Cabannes, Bobak Kiani, Randall Balestriero, Yann LeCun, Alberto Bietti

ICLRW 2023 Understanding the Class-Specific Effects of Data Augmentations Polina Kirichenko, Randall Balestriero, Mark Ibrahim, Shanmukha Ramakrishna Vedantam, Hamed Firooz, Andrew Gordon Wilson

NeurIPS 2023 Understanding the Detrimental Class-Level Effects of Data Augmentation Polina Kirichenko, Mark Ibrahim, Randall Balestriero, Diane Bouchacourt, Shanmukha Ramakrishna Vedantam, Hamed Firooz, Andrew G Wilson

NeurIPS 2022 A Data-Augmentation Is Worth a Thousand Samples: Analytical Moments and Sampling-Free Training Randall Balestriero, Ishan Misra, Yann LeCun

NeurIPS 2022 Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods Randall Balestriero, Yann LeCun

NeurIPSW 2022 Exact Visualization of Deep Neural Network Geometry and Decision Boundary Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk

TMLR 2022 High Fidelity Visualization of What Your Self-Supervised Representation Knows About Florian Bordes, Randall Balestriero, Pascal Vincent

ICLR 2022 MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk

TMLR 2022 Max-Affine Spline Insights into Deep Network Pruning Haoran You, Randall Balestriero, Zhihan Lu, Yutong Kou, Huihong Shi, Shunyao Zhang, Shang Wu, Yingyan Lin, Richard Baraniuk

CVPR 2022 Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values Ahmed Imtiaz Humayun, Randall Balestriero, Richard Baraniuk

NeurIPS 2022 The Effects of Regularization and Data Augmentation Are Class Dependent Randall Balestriero, Leon Bottou, Yann LeCun

ICMLW 2022 What Do We Maximize in Self-Supervised Learning? Ravid Shwartz-Ziv, Randall Balestriero, Yann LeCun

NeurIPS 2022 projUNN: Efficient Method for Training Deep Networks with Unitary Matrices Bobak Kiani, Randall Balestriero, Yann LeCun, Seth Lloyd

ICLR 2021 The Recurrent Neural Tangent Kernel Sina Alemohammad, Zichao Wang, Randall Balestriero, Richard Baraniuk

NeurIPS 2020 Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks Randall Balestriero, Sebastien Paris, Richard Baraniuk

ICLR 2019 A Max-Affine Spline Perspective of Recurrent Neural Networks Zichao Wang, Randall Balestriero, Richard Baraniuk

ICLR 2019 From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference Randall Balestriero, Richard Baraniuk

NeurIPS 2019 The Geometry of Deep Networks: Power Diagram Subdivision Randall Balestriero, Romain Cosentino, Behnaam Aazhang, Richard Baraniuk

ICML 2018 A Spline Theory of Deep Learning Randall Balestriero, Baraniuk

ICML 2018 Spline Filters for End-to-End Deep Learning Randall Balestriero, Romain Cosentino, Herve Glotin, Richard Baraniuk

ICLR 2017 Fast Chirplet Transform Injects Priors in Deep Learning of Animal Calls and Speech Hervé Glotin, Julien Ricard, Randall Balestriero