Workshops

Detection and Steering in LLMs using Feature Learning

Visit talk page
Workshops

Adam and friends via duality

Visit talk page
Workshops

Theory of Scaling: A General Framework for Scale-aware Training

Visit talk page
Workshops

A Statistical Theory of Contrastive Pre-training and Multimodal Generative AI

Visit talk page
Workshops

Generalization and overfitting in two-layer neural networks

Visit talk page
Workshops

Emergence and scaling laws for SGD learning and Learning Compositional Functions with Transformers

Visit talk page
Workshops

Local minima of the empirical risk in high dimension

Visit talk page
Workshops

Weak-to-Strong Generalization Even in Random Feature Networks, Provably

Visit talk page
Workshops

Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression

Visit talk page
Workshops

Pencil: Long Thoughts with Short Memory

Visit talk page