🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱

No fortress, purely open ground. OpenManus is Coming.

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

FlashMLA: Efficient Multi-head Latent Attention Kernels

A unified inference and post-training framework for accelerated video generation.

A collection of awesome video generation studies.

SkyReels-V2: Infinite-length Film Generative model

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Wan: Open and Advanced Large-Scale Video Generative Models

Fast and memory-efficient exact attention

[ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention

Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

LongLive: Real-time Interactive Long Video Generation

Attention is all you need implementation

[IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

Wan: Open and Advanced Large-Scale Video Generative Models

GigaWorld-0: World Models as Data Engine to Empower Embodied AI

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

OpenVLA: An open-source vision-language-action model for robotic manipulation.

NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.

A flexible, high-performance 3D simulator for Embodied AI research.

[Lumina Embodied AI] 具身智能技术指南 Embodied-AI-Guide

Unified framework for robot learning built on NVIDIA Isaac Sim

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

刷算法全靠套路，认准 labuladong 就够了！English version supported! Crack LeetCode, not only how, but also why.

Official PyTorch implementation of One-Minute Video Generation with Test-Time Training

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

MemGen: Weaving Generative Latent Memory for Self-Evolving Agents