Randall Balestriero

167 papers A* 27Misc 6Journal 123Unranked 11

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Lightweight Library for Energy-Based Joint-Embedding Predictive Architectures. CoRR Basile Terver, Randall Balestriero, Megi Dervishi, David Fan, Quentin Garrido, Tushar Nagarajan, Koustuv Sinha, Wancong Zhang, Mike Rabbat, Yann LeCun, Amir Bar
2026	J	`jnl`	Causal-JEPA: Learning World Models through Object-Level Latent Interventions. CoRR Heejeong Nam, Quentin Le Lidec, Lucas Maes, Yann LeCun, Randall Balestriero
2026	J	`jnl`	Interpreting Physics in Video World Models. CoRR Sonia Joseph, Quentin Garrido, Randall Balestriero, Matthew Kowal, Thomas Fel, Shahab Bakhtiari, Blake A. Richards, Mike Rabbat
2026	J	`jnl`	LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels. CoRR Lucas Maes, Quentin Le Lidec, Damien Scieur, Yann LeCun, Randall Balestriero
2026	J	`jnl`	Prompt Augmentation Scales up GRPO Training on Mathematical Reasoning. CoRR Wenquan Lu, Hai Huang, Randall Balestriero
2026	J	`jnl`	Radial-VCReg: More Informative Representation Learning Through Radial Gaussianization. CoRR Yilun Kuang, Yash Dagade, Deep Chakraborty, Erik G. Learned-Miller, Randall Balestriero, Tim G. J. Rudner, Yann LeCun
2026	J	`jnl`	Rectified LpJEPA: Joint-Embedding Predictive Architectures with Sparse and Maximum-Entropy Representations. CoRR Yilun Kuang, Yash Dagade, Tim G. J. Rudner, Randall Balestriero, Yann LeCun
2026	J	`jnl`	Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA. CoRR Hai Huang, Yann LeCun, Randall Balestriero
2026	J	`jnl`	Temporal Straightening for Latent Planning. CoRR Ying Wang, Oumayma Bounou, Gaoyue Zhou, Randall Balestriero, Tim G. J. Rudner, Yann LeCun, Mengye Ren
2026	J	`jnl`	VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation. CoRR Hongyang Du, Junjie Ye, Xiaoyan Cong, Runhao Li, Jingcheng Ni, Aman Agarwal, Zeqi Zhou, Zekun Li, Randall Balestriero, Yue Wang
2026	J	`jnl`	stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation. CoRR Lucas Maes, Quentin Le Lidec, Dan Haramati, Nassim Massaudi, Damien Scieur, Yann LeCun, Randall Balestriero
2025	J	`jnl`	An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research. CoRR Patrik Reizinger, Randall Balestriero, David A. Klindt, Wieland Brendel
2025	J	`jnl`	Beyond and Free from Diffusion: Invertible Guided Consistency Training. CoRR Chia-Hong Hsu, Shiu-Hong Kao, Randall Balestriero
2025	A*	`conf`	Cross-Entropy Is All You Need To Invert the Data Generating Process. ICLR Patrik Reizinger, Alice Bizeul, Attila Juhos, Julia E. Vogt, Randall Balestriero, Wieland Brendel, David A. Klindt
2025	J	`jnl`	Curvature Tuning: Provable Training-free Model Steering From a Single Parameter. CoRR Leyang Hu, Randall Balestriero
2025	J	`jnl`	DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining. CoRR Bryan Rodas, Natalie Montesino, Jakob Ambsdorf, David A. Klindt, Randall Balestriero
2025	J	`jnl`	Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum. CoRR Wenquan Lu, Jiaqi Zhang, Hugues Van Assel, Randall Balestriero
2025	J	`jnl`	Eidetic Learning: an Efficient and Provable Solution to Catastrophic Forgetting. CoRR Nicholas Dronen, Randall Balestriero
2025	J	`jnl`	FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed. CoRR Jiaqi Zhang, Juntuo Wang, Zhixin Sun, John Zou, Randall Balestriero
2025	J	`jnl`	From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations. CoRR Anthony Bisulco, Rahul Ramesh, Randall Balestriero, Pratik Chaudhari
2025	J	`jnl`	Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density. CoRR Randall Balestriero, Nicolas Ballas, Mike Rabbat, Yann LeCun
2025	—	`conf`	General Methods Make Great Domain-Specific Foundation Models: A Case-Study on Fetal Ultrasound. MICCAI (7) Jakob Ambsdorf, Asbjørn Munk, Sebastian Nørgaard Llambias, Anders Nymark Christensen, Kamil Wojciech Mikolaj, Randall Balestriero, Martin Grønnebæk Tolsgaard, Aasa Feragen, Mads Nielsen
2025	J	`jnl`	General Methods Make Great Domain-specific Foundation Models: A Case-study on Fetal Ultrasound. CoRR Jakob Ambsdorf, Asbjørn Munk, Sebastian Nørgaard Llambias, Anders Nymark Christensen, Kamil Wojciech Mikolaj, Randall Balestriero, Martin Grønnebæk Tolsgaard, Aasa Feragen, Mads Nielsen
2025	J	`jnl`	GrokAlign: Geometric Characterisation and Acceleration of Grokking. CoRR Thomas Walker, Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk
2025	J	`jnl`	Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry. CoRR Thomas Fel, Binxu Wang, Michael A. Lepori, Matthew Kowal, Andrew Lee, Randall Balestriero, Sonia Joseph, Ekdeep Singh Lubana, Talia Konkle, Demba E. Ba, Martin Wattenberg
2025	J	`jnl`	Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning. CoRR Hugues Van Assel, Mark Ibrahim, Tommaso Biancalani, Aviv Regev, Randall Balestriero
2025	J	`jnl`	LLM-JEPA: Large Language Models Meet Joint Embedding Predictive Architectures. CoRR Hai Huang, Yann LeCun, Randall Balestriero
2025	J	`jnl`	LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics. CoRR Randall Balestriero, Yann LeCun
2025	J	`jnl`	Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models. CoRR Vlad Sobal, Wancong Zhang, Kynghyun Cho, Randall Balestriero, Tim G. J. Rudner, Yann LeCun
2025	J	`jnl`	LoRA Users Beware: A Few Spurious Tokens Can Manipulate Your Finetuned Model. CoRR Pradyut Sekhsaria, Marcel Mateos Salles, Hai Huang, Randall Balestriero
2025	J	`jnl`	MapSAM2: Adapting SAM2 for Automatic Segmentation of Historical Map Images and Time Series. CoRR Xue Xia, Randall Balestriero, Tao Zhang, Yixin Zhou, Andrew Ding, Dev Saini, Lorenz Hurni
2025	A*	`conf`	Mitigating over-Exploration in Latent Space Optimization using les. ICML Omer Ronen, Ahmed Imtiaz Humayun, Richard G. Baraniuk, Randall Balestriero, Bin Yu
2025	J	`jnl`	Next Token Perception Score: Analytical Assessment of your LLM Perception Skills. CoRR Yu-Ang Cheng, Leyang Hu, Hai Huang, Randall Balestriero
2025	A*	`conf`	No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data. ICLR Daniel Cai, Randall Balestriero
2025	J	`jnl`	No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data. CoRR Daniel Cai, Randall Balestriero
2025	J	`jnl`	Occam's Razor for SSL: Memory-Efficient Parametric Instance Discrimination. Trans. Mach. Learn. Res. Eric Gan, Patrik Reizinger, Alice Bizeul, Attila Juhos, Mark Ibrahim, Randall Balestriero, David A. Klindt, Wieland Brendel, Baharan Mirzasoleiman
2025	J	`jnl`	OpenApps: Simulating Environment Variations to Measure UI-Agent Reliability. CoRR Karen Ullrich, Jingtong Su, Claudia Shi, Arjun Subramonian, Amir Bar, Ivan Evtimov, Nikolaos Tsilivis, Randall Balestriero, Julia Kempe, Mark Ibrahim
2025	—	`conf`	Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research. ICML (Position Papers) Patrik Reizinger, Randall Balestriero, David A. Klindt, Wieland Brendel
2025	J	`jnl`	SAFE: A Novel Approach to AI Weather Evaluation through Stratified Assessments of Forecasts over Earth. CoRR Nick Masi, Randall Balestriero
2025	J	`jnl`	SplInterp: Improving our Understanding and Training of Sparse Autoencoders. CoRR Jeremy Budd, Javier Ideami, Benjamin Macdowall Rynne, Keith Duggar, Randall Balestriero
2025	J	`jnl`	Task Priors: Enhancing Model Evaluation by Considering the Entire Space of Downstream Tasks. CoRR Niket Patel, Randall Balestriero
2025	J	`jnl`	Why and How Auxiliary Tasks Improve JEPA Representations. CoRR Jiacan Yu, Siyi Chen, Mingrui Liu, Nono Horiuchi, Vladimir Braverman, Zicheng Xu, Dan Haramati, Randall Balestriero
2025	A*	`conf`	X-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs. ICLR Vlad Sobal, Mark Ibrahim, Randall Balestriero, Vivien Cabannes, Diane Bouchacourt, Pietro Astolfi, Kyunghyun Cho, Yann LeCun
2025	J	`jnl`	Your Attention Matters: to Improve Model Robustness to Noise and Spurious Correlations. CoRR Camilo Tamayo-Rousseau, Yunjia Zhao, Yiqun Zhang, Randall Balestriero
2025	J	`jnl`	stable-pretraining-v1: Foundation Model Research Made Simple. CoRR Randall Balestriero, Hugues Van Assel, Sami BuGhanem, Lucas Maes
2024	J	`jnl`	ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws. CoRR Hai Huang, Randall Balestriero
2024	J	`jnl`	Beyond [cls]: Exploring the true potential of Masked Image Modeling representations. CoRR Marcin Przewiezlikowski, Randall Balestriero, Wojciech Jasinski, Marek Smieja, Bartosz Zielinski
2024	A*	`conf`	Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation. ICML Randall Balestriero, Romain Cosentino, Sarath Shekkizhar
2024	J	`jnl`	Cross-Entropy Is All You Need To Invert the Data Generating Process. CoRR Patrik Reizinger, Alice Bizeul, Attila Juhos, Julia E. Vogt, Randall Balestriero, Wieland Brendel, David A. Klindt
2024	A*	`conf`	Deep Networks Always Grok and Here is Why. ICML Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk
2024	J	`jnl`	Deep Networks Always Grok and Here is Why. CoRR Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk
2024	J	`jnl`	DeepTensor: Low-Rank Tensor Decomposition With Deep Network Priors. IEEE Trans. Pattern Anal. Mach. Intell. Vishwanath Saragadam, Randall Balestriero, Ashok Veeraraghavan, Richard G. Baraniuk
2024	J	`jnl`	Fast and Exact Enumeration of Deep Networks Partitions Regions. CoRR Randall Balestriero, Yann LeCun
2024	J	`jnl`	GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning. CoRR Aarash Feizi, Randall Balestriero, Adriana Romero-Soriano, Reihaneh Rabbany
2024	A*	`conf`	How Learning by Reconstruction Produces Uninformative Features For Perception. ICML Randall Balestriero, Yann LeCun
2024	J	`jnl`	Learning by Reconstruction Produces Uninformative Features For Perception. CoRR Randall Balestriero, Yann LeCun
2024	J	`jnl`	Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations? CoRR Mark Ibrahim, David A. Klindt, Randall Balestriero
2024	J	`jnl`	On the Geometry of Deep Learning. CoRR Randall Balestriero, Ahmed Imtiaz Humayun, Richard G. Baraniuk
2024	J	`jnl`	ScaLES: Scalable Latent Exploration Score for Pre-Trained Generative Networks. CoRR Omer Ronen, Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk, Bin Yu
2024	J	`jnl`	Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods. CoRR Daniel Otero, Rafael Mateus, Randall Balestriero
2024	J	`jnl`	Self-supervised Video Instance Segmentation Can Boost Geographic Entity Alignment in Historical Maps. CoRR Xue Xia, Randall Balestriero, Tao Zhang, Lorenz Hurni
2024	J	`jnl`	The Fair Language Model Paradox. CoRR Andrea Pinto, Tomer Galanti, Randall Balestriero
2024	J	`jnl`	Understanding the Detrimental Class-level Effects of Data Augmentation. CoRR Polina Kirichenko, Mark Ibrahim, Randall Balestriero, Diane Bouchacourt, Ramakrishna Vedantam, Hamed Firooz, Andrew Gordon Wilson
2024	A*	`conf`	UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling. NeurIPS Haider Al-Tahan, Quentin Garrido, Randall Balestriero, Diane Bouchacourt, Caner Hazirbas, Mark Ibrahim
2024	J	`jnl`	UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling. CoRR Haider Al-Tahan, Quentin Garrido, Randall Balestriero, Diane Bouchacourt, Caner Hazirbas, Mark Ibrahim
2024	J	`jnl`	𝕏-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs. CoRR Vlad Sobal, Mark Ibrahim, Randall Balestriero, Vivien Cabannes, Diane Bouchacourt, Pietro Astolfi, Kyunghyun Cho, Yann LeCun
2023	J	`jnl`	A Cookbook of Self-Supervised Learning. CoRR Randall Balestriero, Mark Ibrahim, Vlad Sobal, Ari Morcos, Shashank Shekhar, Tom Goldstein, Florian Bordes, Adrien Bardes, Grégoire Mialon, Yuandong Tian, Avi Schwarzschild, Andrew Gordon Wilson, Jonas Geiping, Quentin Garrido, Pierre Fernandez, Amir Bar, Hamed Pirsiavash, Yann LeCun, Micah Goldblum
2023	J	`jnl`	A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation. CoRR Florian Bordes, Samuel Lavoie, Randall Balestriero, Nicolas Ballas, Pascal Vincent
2023	A*	`conf`	Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need. ICCV Vivien Cabannes, Léon Bottou, Yann LeCun, Randall Balestriero
2023	J	`jnl`	Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need. CoRR Vivien Cabannes, Léon Bottou, Yann LeCun, Randall Balestriero
2023	A*	`conf`	An Information Theory Perspective on Variance-Invariance-Covariance Regularization. NeurIPS Ravid Shwartz-Ziv, Randall Balestriero, Kenji Kawaguchi, Tim G. J. Rudner, Yann LeCun
2023	J	`jnl`	An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization. CoRR Ravid Shwartz-Ziv, Randall Balestriero, Kenji Kawaguchi, Tim G. J. Rudner, Yann LeCun
2023	J	`jnl`	Characterizing Large Language Model Geometry Solves Toxicity Detection and Generation. CoRR Randall Balestriero, Romain Cosentino, Sarath Shekkizhar
2023	J	`jnl`	FAIR-Ensemble: When Fairness Naturally Emerges From Deep Ensembling. CoRR Wei-Yin Ko, Daniel D'souza, Karina Nguyen, Randall Balestriero, Sara Hooker
2023	Misc	`conf`	Fast and Exact Enumeration of Deep Networks Partitions Regions. ICASSP Randall Balestriero, Yann LeCun
2023	J	`jnl`	Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning. Trans. Mach. Learn. Res. Florian Bordes, Randall Balestriero, Quentin Garrido, Adrien Bardes, Pascal Vincent
2023	A*	`conf`	ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations. ICLR Badr Youbi Idrissi, Diane Bouchacourt, Randall Balestriero, Ivan Evtimov, Caner Hazirbas, Nicolas Ballas, Pascal Vincent, Michal Drozdzal, David Lopez-Paz, Mark Ibrahim
2023	J	`jnl`	Martian time-series unraveled: A multi-scale nested approach with factorial variational autoencoders. CoRR Ali Siahkoohi, Rudy Morel, Randall Balestriero, Erwan Allys, Grégory Sainton, Taichi Kawamura, Maarten V. de Hoop
2023	Misc	`conf`	On Minimal Variations for Unsupervised Representation Learning. ICASSP Vivien Cabannes, Alberto Bietti, Randall Balestriero
2023	Misc	`conf`	Police: Provably Optimal Linear Constraint Enforcement For Deep Neural Networks. ICASSP Randall Balestriero, Yann LeCun
2023	A*	`conf`	RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their Rank. ICML Quentin Garrido, Randall Balestriero, Laurent Najman, Yann LeCun
2023	A*	`conf`	SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries. CVPR Ahmed Imtiaz Humayun, Randall Balestriero, Guha Balakrishnan, Richard G. Baraniuk
2023	J	`jnl`	SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries. CoRR Ahmed Imtiaz Humayun, Randall Balestriero, Guha Balakrishnan, Richard G. Baraniuk
2023	A*	`conf`	The SSL Interplay: Augmentations, Inductive Bias, and Generalization. ICML Vivien Cabannes, Bobak Toussi Kiani, Randall Balestriero, Yann LeCun, Alberto Bietti
2023	J	`jnl`	The SSL Interplay: Augmentations, Inductive Bias, and Generalization. CoRR Vivien Cabannes, Bobak Toussi Kiani, Randall Balestriero, Yann LeCun, Alberto Bietti
2023	A*	`conf`	The hidden uniform cluster prior in self-supervised learning. ICLR Mido Assran, Randall Balestriero, Quentin Duval, Florian Bordes, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael G. Rabbat, Nicolas Ballas
2023	J	`jnl`	Towards Democratizing Joint-Embedding Self-Supervised Learning. CoRR Florian Bordes, Randall Balestriero, Pascal Vincent
2023	J	`jnl`	Training Dynamics of Deep Network Linear Regions. CoRR Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk
2023	A*	`conf`	Understanding the detrimental class-level effects of data augmentation. NeurIPS Polina Kirichenko, Mark Ibrahim, Randall Balestriero, Diane Bouchacourt, Shanmukha Ramakrishna Vedantam, Hamed Firooz, Andrew Gordon Wilson
2023	J	`jnl`	Unsupervised Learning on a DIET: Datum IndEx as Target Free of Self-Supervision, Reconstruction, Projector Head. CoRR Randall Balestriero
2022	A*	`conf`	A Data-Augmentation Is Worth A Thousand Samples: Analytical Moments And Sampling-Free Training. NeurIPS Randall Balestriero, Ishan Misra, Yann LeCun
2022	J	`jnl`	A Data-Augmentation Is Worth A Thousand Samples: Exact Quantification From Analytical Augmented Sample Moments. CoRR Randall Balestriero, Ishan Misra, Yann LeCun
2022	J	`jnl`	Batch Normalization Explained. CoRR Randall Balestriero, Richard G. Baraniuk
2022	A*	`conf`	Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods. NeurIPS Randall Balestriero, Yann LeCun
2022	J	`jnl`	Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods. CoRR Randall Balestriero, Yann LeCun
2022	Misc	`conf`	DeepHull: Fast Convex Hull Approximation in High Dimensions. ICASSP Randall Balestriero, Zichao Wang, Richard G. Baraniuk
2022	J	`jnl`	DeepTensor: Low-Rank Tensor Decomposition with Deep Network Priors. CoRR Vishwanath Saragadam, Randall Balestriero, Ashok Veeraraghavan, Richard G. Baraniuk
2022	J	`jnl`	Guillotine Regularization: Improving Deep Networks Generalization by Removing their Head. CoRR Florian Bordes, Randall Balestriero, Quentin Garrido, Adrien Bardes, Pascal Vincent
2022	J	`jnl`	High Fidelity Visualization of What Your Self-Supervised Representation Knows About. Trans. Mach. Learn. Res. Florian Bordes, Randall Balestriero, Pascal Vincent
2022	J	`jnl`	ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations. CoRR Badr Youbi Idrissi, Diane Bouchacourt, Randall Balestriero, Ivan Evtimov, Caner Hazirbas, Nicolas Ballas, Pascal Vincent, Michal Drozdzal, David Lopez-Paz, Mark Ibrahim
2022	J	`jnl`	Joint Embedding Self-Supervised Learning in the Kernel Regime. CoRR Bobak Toussi Kiani, Randall Balestriero, Yubei Chen, Seth Lloyd, Yann LeCun
2022	A*	`conf`	MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining. ICLR Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk
2022	J	`jnl`	Max-Affine Spline Insights Into Deep Network Pruning. Trans. Mach. Learn. Res. Haoran You, Randall Balestriero, Zhihan Lu, Yutong Kou, Huihong Shi, Shunyao Zhang, Shang Wu, Yingyan Lin, Richard G. Baraniuk
2022	—	`conf`	NeuroView-RNN: It's About Time. FAccT C. J. Barberan, Sina Alemohammad, Naiming Liu, Randall Balestriero, Richard G. Baraniuk
2022	J	`jnl`	NeuroView-RNN: It's About Time. CoRR C. J. Barberan, Sina Alemohammad, Naiming Liu, Randall Balestriero, Richard G. Baraniuk
2022	Misc	`conf`	No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds. ICASSP Ahmed Imtiaz Humayun, Randall Balestriero, Anastasios Kyrillidis, Richard G. Baraniuk
2022	J	`jnl`	No More Than 6ft Apart: Robust K-Means via Radius Upper Bounds. CoRR Ahmed Imtiaz Humayun, Randall Balestriero, Anastasios Kyrillidis, Richard G. Baraniuk
2022	J	`jnl`	On minimal variations for unsupervised representation learning. CoRR Vivien Cabannes, Alberto Bietti, Randall Balestriero
2022	J	`jnl`	POLICE: Provably Optimal Linear Constraint Enforcement for Deep Neural Networks. CoRR Randall Balestriero, Yann LeCun
2022	A*	`conf`	Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values. CVPR Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk
2022	J	`jnl`	Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values. CoRR Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk
2022	J	`jnl`	RankMe: Assessing the downstream performance of pretrained self-supervised representations by their rank. CoRR Quentin Garrido, Randall Balestriero, Laurent Najman, Yann LeCun
2022	J	`jnl`	Recurrent Scattering Network Detects Metastable Behavior in Polyphonic Seismo-Volcanic Signals for Volcano Eruption Forecasting. IEEE Trans. Geosci. Remote. Sens. Ángel Bueno Rodríguez, Randall Balestriero, Silvio De Angelis, M. Carmen Benítez, Luciano Zuccarello, Richard G. Baraniuk, Jesús M. Ibáñez, Maarten V. de Hoop
2022	J	`jnl`	Singular Value Perturbation and Deep Network Optimization. CoRR Rudolf H. Riedi, Randall Balestriero, Richard G. Baraniuk
2022	—	`conf`	Spatial Transformer K-Means. IEEECONF Romain Cosentino, Randall Balestriero, Yanis Bahroun, Anirvan M. Sengupta, Richard G. Baraniuk, Behnaam Aazhang
2022	J	`jnl`	Spatial Transformer K-Means. CoRR Romain Cosentino, Randall Balestriero, Yanis Bahroun, Anirvan M. Sengupta, Richard G. Baraniuk, Behnaam Aazhang
2022	A*	`conf`	The Effects of Regularization and Data Augmentation are Class Dependent. NeurIPS Randall Balestriero, Léon Bottou, Yann LeCun
2022	J	`jnl`	The Effects of Regularization and Data Augmentation are Class Dependent. CoRR Randall Balestriero, Léon Bottou, Yann LeCun
2022	J	`jnl`	The Hidden Uniform Cluster Prior in Self-Supervised Learning. CoRR Mahmoud Assran, Randall Balestriero, Quentin Duval, Florian Bordes, Ishan Misra, Piotr Bojanowski, Pascal Vincent, Michael G. Rabbat, Nicolas Ballas
2022	J	`jnl`	Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations. CoRR Grégoire Mialon, Randall Balestriero, Yann LeCun
2022	J	`jnl`	What Do We Maximize in Self-Supervised Learning? CoRR Ravid Shwartz-Ziv, Randall Balestriero, Yann LeCun
2022	A*	`conf`	projUNN: efficient method for training deep networks with unitary matrices. NeurIPS Bobak Toussi Kiani, Randall Balestriero, Yann LeCun, Seth Lloyd
2022	J	`jnl`	projUNN: efficient method for training deep networks with unitary matrices. CoRR Bobak Toussi Kiani, Randall Balestriero, Yann LeCun, Seth Lloyd
2021	—	`conf`	Deep Autoencoders: From Understanding to Generalization Guarantees. MSML Romain Cosentino, Randall Balestriero, Richard G. Baraniuk, Behnaam Aazhang
2021	J	`jnl`	Fast Jacobian-Vector Product for Deep Networks. CoRR Randall Balestriero, Richard G. Baraniuk
2021	J	`jnl`	High Fidelity Visualization of What Your Self-Supervised Representation Knows About. CoRR Florian Bordes, Randall Balestriero, Pascal Vincent
2021	—	`conf`	Interpretable and Learnable Super-Resolution Time-Frequency Representation. MSML Randall Balestriero, Hervé Glotin, Richard G. Baraniuk
2021	J	`jnl`	Learning in High Dimension Always Amounts to Extrapolation. CoRR Randall Balestriero, Jerome Pesenti, Yann LeCun
2021	J	`jnl`	MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining. CoRR Ahmed Imtiaz Humayun, Randall Balestriero, Richard G. Baraniuk
2021	J	`jnl`	Mad Max: Affine Spline Insights Into Deep Learning. Proc. IEEE Randall Balestriero, Richard G. Baraniuk
2021	J	`jnl`	Max-Affine Spline Insights Into Deep Network Pruning. CoRR Randall Balestriero, Haoran You, Zhihan Lu, Yutong Kou, Yingyan Lin, Richard G. Baraniuk
2021	J	`jnl`	NeuroView: Explainable Deep Network Decision Making. CoRR C. J. Barberan, Randall Balestriero, Richard G. Baraniuk
2021	A*	`conf`	The Recurrent Neural Tangent Kernel. ICLR Sina Alemohammad, Zichao Wang, Randall Balestriero, Richard G. Baraniuk
2021	Misc	`conf`	Wearing A Mask: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels. ICASSP 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
2020	J	`jnl`	Analytical Probability Distributions and EM-Learning for Deep Generative Networks. CoRR Randall Balestriero, Sébastien Paris, Richard G. Baraniuk
2020	A*	`conf`	Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks. NeurIPS Randall Balestriero, Sébastien Paris, Richard G. Baraniuk
2020	J	`jnl`	Ensembles of Generative Adversarial Networks for Disconnected Data. CoRR Lorenzo Luzi, Randall Balestriero, Richard G. Baraniuk
2020	J	`jnl`	Interpretable Image Clustering via Diffeomorphism-Aware K-Means. CoRR Romain Cosentino, Randall Balestriero, Yanis Bahroun, Anirvan M. Sengupta, Richard G. Baraniuk, Behnaam Aazhang
2020	J	`jnl`	Interpretable Super-Resolution via a Learned Time-Series Representation. CoRR Randall Balestriero, Hervé Glotin, Richard G. Baraniuk
2020	J	`jnl`	Max-Affine Spline Insights into Deep Generative Networks. CoRR Randall Balestriero, Sébastien Paris, Richard G. Baraniuk
2020	J	`jnl`	Provable Finite Data Generalization with Group Autoencoder. CoRR Romain Cosentino, Randall Balestriero, Richard G. Baraniuk, Behnaam Aazhang
2020	J	`jnl`	Scalable Neural Tangent Kernel of Recurrent Architectures. CoRR Sina Alemohammad, Randall Balestriero, Zichao Wang, Richard G. Baraniuk
2020	J	`jnl`	Sparse Multi-Family Deep Scattering Network. CoRR Romain Cosentino, Randall Balestriero
2020	J	`jnl`	SymJAX: symbolic CPU/GPU/TPU programming. CoRR Randall Balestriero
2020	J	`jnl`	The Recurrent Neural Tangent Kernel. CoRR Sina Alemohammad, Zichao Wang, Randall Balestriero, Richard G. Baraniuk
2020	J	`jnl`	Universal Frame Thresholding. IEEE Signal Process. Lett. Romain Cosentino, Randall Balestriero, Richard G. Baraniuk, Behnaam Aazhang
2020	J	`jnl`	Wearing a MASK: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels. CoRR 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
2019	J	`jnl`	A Hessian Based Complexity Measure for Deep Networks. CoRR Hamid Javadi, Randall Balestriero, Richard G. Baraniuk
2019	—	`conf`	A Max-Affine Spline Perspective of Recurrent Neural Networks. ICLR (Poster) Zichao Wang, Randall Balestriero, Richard G. Baraniuk
2019	—	`conf`	From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference. ICLR (Poster) Randall Balestriero, Richard G. Baraniuk
2019	A*	`conf`	The Geometry of Deep Networks: Power Diagram Subdivision. NeurIPS Randall Balestriero, Romain Cosentino, Behnaam Aazhang, Richard G. Baraniuk
2019	J	`jnl`	The Geometry of Deep Networks: Power Diagram Subdivision. CoRR Randall Balestriero, Romain Cosentino, Behnaam Aazhang, Richard G. Baraniuk
2018	J	`jnl`	A Spline Theory of Deep Networks (Extended Version). CoRR Randall Balestriero, Richard G. Baraniuk
2018	A*	`conf`	A Spline Theory of Deep Networks. ICML Randall Balestriero, Richard G. Baraniuk
2018	J	`jnl`	From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference. CoRR Randall Balestriero, Richard G. Baraniuk
2018	J	`jnl`	Semi-Supervised Learning Enabled by Multiscale Deep Neural Network Inversion. CoRR Randall Balestriero, Hervé Glotin, Richard G. Baraniuk
2018	A*	`conf`	Spline Filters For End-to-End Deep Learning. ICML Randall Balestriero, Romain Cosentino, Hervé Glotin, Richard G. Baraniuk
2017	J	`jnl`	Adaptive Partitioning Spline Neural Networks: Template Matching, Memorization, Inhibitor Connections, Inversion, Semi-Sup, Topology Search. CoRR Randall Balestriero, Richard G. Baraniuk
2017	—	`conf`	Fast Chirplet Transform Injects Priors in Deep Learning of Animal Calls and Speech. ICLR (Workshop) Hervé Glotin, Julien Ricard, Randall Balestriero
2017	J	`jnl`	Linear Time Complexity Deep Fourier Scattering Network and Extension to Nonlinear Invariants. CoRR Randall Balestriero, Hervé Glotin
2017	J	`jnl`	Multiscale Residual Mixture of PCA: Dynamic Dictionaries for Optimal Basis Learning. CoRR Randall Balestriero
2017	J	`jnl`	Neural Decision Trees. CoRR Randall Balestriero
2017	J	`jnl`	Overcomplete Frame Thresholding for Acoustic Scene Analysis. CoRR Romain Cosentino, Randall Balestriero, Richard G. Baraniuk, Ankit B. Patel
2017	J	`jnl`	Semi-Supervised Learning via New Deep Network Inversion. CoRR Randall Balestriero, Vincent Roger, Hervé Glotin, Richard G. Baraniuk
2016	—	`conf`	Best basis selection using sparsity driven multi-family wavelet transform. GlobalSIP Romain Cosentino, Randall Balestriero, Behnaam Aazhang
2016	J	`jnl`	Fast Chirplet Transform feeding CNN, application to orca and bird bioacoustics. CoRR Hervé Glotin, Julien Ricard, Randall Balestriero
2015	—	`conf`	Scattering Decomposition for Massive Signal Classification: From Theory to Fast Algorithm and Implementation with Validation on International Bioacoustic Benchmark. ICDM Workshops Randall Balestriero, Hervé Glotin