Alexander M Rush

How much can language models memorize?

Contextual Document Embeddings

Commit0: Library Generation from Scratch

Approximating Language Model Training Data from Weights

Multi-Turn Code Generation Through Single-Step Rewards

A Controlled Study on Long Context Extension and Generalization in LLMs

Compute-Constrained Data Selection

Overfill: Two-Stage Models for Efficient Language Model Decoding

A Controlled Study on Long Context Extension and Generalization in LLMs

Simple Guidance Mechanisms for Discrete Diffusion Models

A Codespace Autoencoder for Language Tasks