Directional Neural Collapse Explains Few-Shot Transfer in Self-Supervised Learning
Preprint, arXiv, 2026
Publications
Preprints
Tool Building as a Path to "Superintelligence"
Preprint, arXiv, 2026
Scalable Principal–Agent Contract Design via Gradient-Based Optimization
Preprint, arXiv, 2025
LLM Priors for ERM over Programs
Preprint, arXiv, 2025
The Fair Language Model Paradox
Preprint, arXiv, 2024
Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent
Preprint, arXiv, 2023
Generalization Bounds for Transfer Learning with Pretrained Classifiers
Preprint, arXiv, 2022
Publications at top-tier venues
On the Alignment Between Supervised and Self-Supervised Contrastive Learning
ICLR, 2026
Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning
NeurIPS, 2025
DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
NeurIPS, 2025
Formation of Representations in Neural Networks
ICLR, 2025 Spotlight
Distributed Speculative Inference (DSI)
ICLR, 2025
SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network
CPAL, 2025 · NeurIPS M3L Workshop, 2024
On the Power of Decision Trees in Auto-Regressive Language Modeling
NeurIPS, 2024
Norm-Based Generalization Bounds for Sparse Neural Networks
NeurIPS, 2023
Reverse Engineering Self-Supervised Learning
NeurIPS, 2023
Comparative Generalization Bounds for Deep Neural Networks
TMLR, 2023
Feature Learning in Deep Classifiers Through Intermediate Neural Collapse
ICML, 2023
Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functions
TMLR, 2023
Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models
ECCV, 2022
On the Role of Neural Collapse in Transfer Learning
ICLR, 2022
Meta Internal Learning
NeurIPS, 2021
On Random Kernels of Residual Architectures
UAI, 2021
Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs
JMLR, 2021
Evaluation Metrics for Conditional Image Generation
IJCV, 2021
On the Modularity of Hypernetworks
NeurIPS, 2020 Oral
On Infinite-Width Hypernetworks
NeurIPS, 2020
Domain Intersection and Domain Difference
ICCV, 2019
Unsupervised Learning of the Set of Local Maxima
ICLR, 2019
Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer
ICLR, 2019
Estimating the Success of Unsupervised Image to Image Translation
ECCV, 2018
The Role of Minimal Complexity in Unsupervised Learning of Semantic Mappings
ICLR, 2018
Other peer-reviewed publications
Gradient-Based Bilevel Optimization for Principal–Agent Contract Design
NeurIPS Workshop: Generative AI in Finance, 2025
Distributed Speculative Inference of Large Language Models is Provably Faster
NeurIPS ENLSP Workshop, 2024 (PMLR)
Dynamics of Deep Classifiers Trained with the Square Loss
Research (A Science Partner Journal), 2023
Improved Generalization Bounds for Transfer Learning via Neural Collapse
ICML Workshop on Pretraining, 2022
On the Implicit Bias Towards Depth Minimization in Deep Neural Networks
DEEPMATH, 2022 · TOPML, 2022
Weakly Supervised Discovery of Semantic Attributes
CLeaR, 2022
A Formal Approach to Explainability
AIES, 2019
Generalization Bounds for Cross-Domain Mapping with WGANs
NeurIPS Workshop on Integration of Deep Learning Theories, 2018
A Theoretical Framework for Deep Transfer Learning
Information and Inference: A Journal of the IMA, 2016