Nim is a free and open-source personal website template built with Next.js 15, React 19, Tailwind CSS v4, and Motion-Primitives.

Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence

ALICE: An Interpretable Neural Architecture for Generalization in Substitution Ciphers

Preparing for ML Interviews.

Implementation of Hippoformer, Integrating Hippocampus-inspired Spatial Memory with Transformers

Official release of code for the paper RL is a hammer and LLMs are nails A simple RL approach to stronger prompt injection attacks

Graph Neural Network Library for PyTorch

Code for "DynaGuard: A Dynamic Guardrail Model With User-Defined Policies."

Our library for RL environments + evals

Official repository for Beyond Binary Rewards: Training LMs to Reason about Their Uncertainty

A benchmark for LLMs on complicated tasks in the terminal

[NeurIPS 2025 Spotlight] Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning

Renderer for the harmony response format to be used with gpt-oss

Pytorch implementation of MeanFlow on ImageNet and CIFAR10

A pre-commit hook for Ruff.

This is the official repo for "Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models"

Open-source framework for the research and development of foundation models.

PyTorch Implementation of Zero-Shot Vision Encoder Grafting via LLM Surrogates [ICCV'25]

Modeling, training, eval, and inference code for OLMo

An open-source AI agent that brings the power of Gemini directly into your terminal.

Official implementation of TBA for async LLM post-training.

Official Python SDK for the Agent2Agent (A2A) Protocol

A snappy + easy + pretty TUI debugger for Python.

SkyRL: A Modular Full-stack RL Library for LLMs

Simplifying reinforcement learning for complex game environments

Lighteval is your all-in-one toolkit for evaluating LLMs across multiple backends

Minimalistic 4D-parallelism distributed training framework for education purpose