Posts

Transfomer Explainer: Interactive Learning of Text-Generative Models

A Definition of AGI

Scaling LLMs for next-generation single-cell analysis

DeepSeek-OCR: Contexts Optical Compression

Surprises in High-Dimensional Ridgeless Least Squares Interpolation - Part III

Deep Double Descent - Bigger Models and More Data Hurt - Part II

Rethinking Generalization in Deep Learning - Part I

Less is More: Recursive Reasoning with Tiny Networks