Christopher Re

Cartridges: Lightweight and general-purpose long context representations via self-study

An Information Theoretic Perspective on Agentic System Design

Support Your Local LMs: Redistributing LM Traffic from Cloud to Edge with TrafficBench

Cylon: Asynchronous Linear Attention

Scaling Laws for Precision

Restructuring Vector Quantization with the Rotation Trick

ThunderKittens: Simple, Fast, and $Adorable$ Kernels

Context Clues: Evaluating Long Context Models for Clinical Prediction Tasks on EHR Data

Cost-efficient Collaboration between On-device and Cloud Language Models

LoLCATs: On Low-Rank Linearizing of Large Language Models

Weaver: Shrinking the Generation-Verification Gap by Scaling Compute for Verification

Aioli: A Unified Optimization Framework for Language Model Data Mixing

Towards Learning High-Precision Least Squares Algorithms with Sequence Models

Automated Rewards via LLM-Generated Progress Functions

KernelBench: Can LLMs Write Efficient GPU Kernels?

Large Language Monkeys: Scaling Inference Compute with Repeated Sampling

Archon: An Architecture Search Framework for Inference-Time Techniques

An Architecture Search Framework for Inference-Time Techniques