Reproducing R1 for Code with Reliable Rewards

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

DataSciBench: An LLM Agent Benchmark for Data Science

Official PyTorch implementation for "Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data" (ICLR 2025)

[AAAI'2025] Official PyTorch implementation of the paper "Identity-Text Video Corpus Grounding".

Python3 control flow graph generator

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

深度学习经典、新论文逐段精读

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

A curated list of awesome Deep Reinforcement Learning resources.

OpenChat: Advancing Open-source Language Models with Imperfect Data

Easy-to-use and high-performance NLP and LLM framework based on MindSpore, compatible with models and datasets of 🤗Huggingface.

Community for applying LLMs to robotics and a robot simulator with ChatGPT integration

Teaching Assistants Competency 助教素养

Python Implementation of Reinforcement Learning: An Introduction

MEASURING MASSIVE MULTITASK CHINESE UNDERSTANDING

CTF framework and exploit development library

Playing Hollow Knight with reinforcement learning.

Instruction Tuning with GPT-4

Existing Literature about Machine Unlearning

Code and models for the paper "One Transformer Fits All Distributions in Multi-Modal Diffusion"

Open Instruction Generalist is an assistant trained on massive synthetic instructions to perform many millions of tasks

Monte Carlo tree search in JAX

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

A modular RL library to fine-tune language models to human preferences

LaTeX Thesis Template for Tsinghua University