Randall Balestriero
33 papers · 2018–2025 · 6 venues · across top CS/AI venues
This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 8 separate collaboration groups - the largest holds only 42% of them. Pick the group below that matches the researcher you mean. How a shared name is split.
Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.
Which Randall Balestriero?
3 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.
with Yann LeCun, Mark Ibrahim, Diane Bouchacourt
14 papers
· 2022–2025
· NeurIPS, ICLR, ICML
Hide ▲
X-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
ICLR 2025
How Learning by Reconstruction Produces Uninformative Features For Perception
ICML 2024
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
NeurIPS 2024
Active Self-Supervised Learning: A Few Low-Cost Relationships Are All You Need
ICCV 2023
An Information Theory Perspective on Variance-Invariance-Covariance Regularization
NeurIPS 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
The SSL Interplay: Augmentations, Inductive Bias, and Generalization
ICML 2023
The hidden uniform cluster prior in self-supervised learning
ICLR 2023
Understanding the detrimental class-level effects of data augmentation
NeurIPS 2023
A Data-Augmentation Is Worth A Thousand Samples: Analytical Moments And Sampling-Free Training
NeurIPS 2022
Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methods
NeurIPS 2022
The Effects of Regularization and Data Augmentation are Class Dependent
NeurIPS 2022
projUNN: efficient method for training deep networks with unitary matrices
NeurIPS 2022
5 papers whose co-authors appear nowhere else under this name
Beyond [cls]: Exploring the True Potential of Masked Image Modeling Representations
ICCV 2025
From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations
ICCV 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
A Spline Theory of Deep Learning
ICML 2018