Evolve your language agent with Agentic Context Engineering (ACE)

GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent [ICML 2026]

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

The best ChatGPT that $100 can buy.

Storing long contexts in tiny caches with self-study

Official PyTorch implementation for "Large Language Diffusion Models"

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

Esoteric Language Models

A high-throughput and memory-efficient inference and serving engine for LLMs

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models

Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

accompanying material for sleep-time compute paper

FEMR (Framework for Electronic Medical Records) provides tooling for large-scale, self-supervised learning using electronic health records

ACL 2024 | LooGLE: Long Context Evaluation for Long-Context Language Models

Repo for paper "Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents"

PyTorch package for the discrete VAE used for DALL·E.

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Protocol Buffers - Google's data interchange format