A Simple and Universal Swarm Intelligence Engine, Predicting Anything. 简洁通用的群体智能引擎，预测万物

《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码

The best ChatGPT that $100 can buy.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Wan: Open and Advanced Large-Scale Video Generative Models

ESGenius: EMNLP 2025 Main Oral benchmark for LLM ESG and sustainability knowledge, with 1,136 questions, evaluation code, interactive heatmap, and Hugging Face dataset release.

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

✨✨Latest Advances on Multimodal Large Language Models

Advancing Sustainability via Recommender Systems: A Survey

[ACL'24 Oral] Code for 'Rewriting the Code: A Simple Method for Large Language Model Augmented Code Search'

Supplementary materials and codes for the paper "Causal Structure Learning Supervised by Large Language Model"

因果强化学习（迷宫环境）

Adversarial Counterfactual Temporal Inference Network

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

llama3 implementation one matrix multiplication at a time

《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣

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

Distribute and run LLMs with a single file.

LLM training in simple, raw C/CUDA

The local UI to run and train text and diffusion models, including Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.

Code for tasks on Cainiao-LaDe (Last-mile Delivery dataset).

[EMNLP'23] Code for 'Rethinking Negative Pairs in Code Search'