Mikhail Belkin

xRFM: Accurate, scalable, and interpretable feature learning models for tabular data

FACT: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations

Detecting Motivated Reasoning in Internal Representations of Language Models

Emergence in non-neural models: grokking modular arithmetic via average gradient outer product

Fast Training of Large Kernel Models with Delayed Projections

Seeds of Structure: Patch PCA Reveals Universal Compositional Cues in Diffusion Models

Task Generalization with Autoregressive Compositional Structure: Can Learning from $D$ Tasks Generalize to $D^T$ Tasks?

Emergence in non-neural models: grokking modular arithmetic via average gradient outer product

Context-Scaling versus Task-Scaling in In-Context Learning