Windows Agent Arena (WAA) 🪟 is a scalable OS platform for testing and benchmarking of multi-modal AI agents.

UFO³: Weaving the Digital Agent Galaxy

The universal proxy platform

Train the smallest LM you can that fits in 16MB. Best model wins!

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

Copy Fail (CVE-2026-31431): 9-year-old Linux kernel LPE found by Theori's Xint Code

A curated list for Efficient Large Language Models

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

LLM KV cache compression made easy

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

🎬 火宝短剧 - 基于AI的一站式短剧生成平台 《一句话生成完整短剧，从剧本到成片全自动化》 Huobao Drama - An AI-Powered End-to-End Short Drama Generator "One Sentence to Complete Drama: Fully Automated from Script to Final Video"

搜索、推荐、广告、用增等工业界实践文章收集（来源：知乎、Datafuntalk、技术公众号）

Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

从零构建大模型：从预训练到RLHF的完整实践

A collection of token reduction (token pruning, merging, clustering, etc.) techniques for ML/AI

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

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

LLM training in simple, raw C/CUDA

🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Retrieval with Learned Similarities (http://arxiv.org/abs/2407.15462, WWW'25 Oral)

Tile primitives for speedy kernels

Causal Inference for the Brave and True的中文翻译版。全部代码基于Python，适用于计量经济学、量化社会学、策略评估等领域。英文版原作者：Matheus Facure

Transformers w/o Attention, based fully on MLPs

[TMLR2026] Video Prediction Transformers without Recurrence or Convolution