A GUI client for Windows, Linux and macOS, support Xray and sing-box and others

MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold

Computer Vision Calibration

Define and run multi-container applications with Docker

This is a Chinese translation of the CUDA programming guide

对常见IMU芯片的原理、驱动和数据融合算法整理，以区分某度、某坛上面碎片化严重到影响入坑的乱象。也欢迎PR补充内容。

Reference_Book_for_VSALM

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

World Model with Physical Information for Robotic Planning Task

仅需Python基础，从0构建自己的具身智能机器人；从0逐步构建VLA/OpenVLA/SmolVLA/Pi0， 深入理解具身智能

多模态具身智能大模型 OpenVLA 的复现以及在 LIBERO 数据集上的微调改进

手把手复现OpenVLA的中文说明

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

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

TartanAir dataset tools and samples

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

Ext4 file system driver for Windows

求职/升学/程序员找工作简历模板大全，全网最全的简历模板收集 | Free collection of resume templates for job/education |中文简历|英文简历|程序员简历模板|简历大全|简历模板|工作简历|简历封面

Unfied World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets

FangjieYu's hugo website

News: the 10k dataset is ready for download.

Unified Codebase for Advanced World Models.

Project Lyra: Open Generative 3D World Models

[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

[CVPR 2026] GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation

WorldGrow: Generating Infinite 3D World [AAAI 2026 Oral]

Codebase for "Beyond Pixel Histories: World Models with Persistent 3D State" (ICML 26)

Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.