← Authors

Randall Balestriero

33 papers · 2018–2025 · 6 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (7) 🐝 Cross-Pollinator (11) 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer πŸ—ΊοΈ Taxonomy Completionist (49) 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (7) 🀝 Dynamic Duo (10) πŸ‘‘ Triple Crown 🧬 Topic Evolution πŸ“ˆ Trend Setter ⚑ Prolific Year (8) πŸ’Ž Century Club (33) πŸ—ƒοΈ Keyword Collector (95) πŸ”₯ Unstoppable (8)

Conferences

ICLR (9) ICML (9) NIPS (9) ICCV (3) CVPR (2) MICCAI (1)

Top co-authors

Richard Baraniuk (10) Yann LeCun (10) Ahmed Imtiaz Humayun (5) Mark Ibrahim (4) Diane Bouchacourt (4) Vivien Cabannes (3) Romain Cosentino (3) Patrik Reizinger (2) Ishan Misra (2) Wieland Brendel (2)

Keywords

representation learning (6) self-supervised learning (6) data augmentation (4) deep network (3) network geometry (2) decision boundary (2) max-affine spline operator (2) contrastive learning (2) feature learning (1) unified benchmark (1) image classification (1) model evaluation (1) multimodal learning (1) multi-modal learning (1) class imbalance (1) manifold learning (1) time-frequency analysis (1) network visualization (1) probabilistic modeling (1) visual representation (1)

Papers

$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs ICLR 2025
Beyond [cls]: Exploring the True Potential of Masked Image Modeling Representations ICCV 2025
Position: An Empirically Grounded Identifiability Theory Will Accelerate Self Supervised Learning Research ICML 2025
MITIGATING OVER-EXPLORATION IN LATENT SPACE OPTIMIZATION USING LES ICML 2025
Cross-Entropy Is All You Need To Invert the Data Generating Process ICLR 2025
General Methods Make Great Domain-specific Foundation Models: A Case-study on Fetal Ultrasound MICCAI 2025
No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data ICLR 2025
From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations ICCV 2025
Deep Networks Always Grok and Here is Why ICML 2024
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling NIPS 2024
How Learning by Reconstruction Produces Uninformative Features For Perception ICML 2024
Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation ICML 2024
The SSL Interplay: Augmentations, Inductive Bias, and Generalization ICML 2023
Understanding the detrimental class-level effects of data augmentation NIPS 2023
An Information Theory Perspective on Variance-Invariance-Covariance Regularization NIPS 2023
SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries CVPR 2023
Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need ICCV 2023
The hidden uniform cluster prior in self-supervised learning ICLR 2023
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations ICLR 2023
RankMe: Assessing the Downstream Performance of Pretrained Self-Supervised Representations by Their Rank ICML 2023
Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values CVPR 2022
The Effects of Regularization and Data Augmentation are Class Dependent NIPS 2022
Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods NIPS 2022
MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining ICLR 2022
A Data-Augmentation Is Worth A Thousand Samples: Analytical Moments And Sampling-Free Training NIPS 2022
projUNN: efficient method for training deep networks with unitary matrices NIPS 2022
The Recurrent Neural Tangent Kernel ICLR 2021
Analytical Probability Distributions and Exact Expectation-Maximization for Deep Generative Networks NIPS 2020
The Geometry of Deep Networks: Power Diagram Subdivision NIPS 2019
From Hard to Soft: Understanding Deep Network Nonlinearities via Vector Quantization and Statistical Inference ICLR 2019
A Max-Affine Spline Perspective of Recurrent Neural Networks ICLR 2019
A Spline Theory of Deep Learning ICML 2018
Spline Filters For End-to-End Deep Learning ICML 2018