liyaxuanliyaxuan

giga-world-1. A Roadmap to Build World Models for Robot Policy Evaluation

Pathwise_TTC.

FramePack. Lets make video diffusion practical!

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

Stable-Video-Infinity. [ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

vggt-omega. [CVPR 2026 Oral] VGGT Omega

Lance. A 3B-active-parameter native unified multimodal model for image and video understanding, generation, and editing.

RollingForcing. [ICLR 2026] Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

PointWorld. PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation

mmpose. OpenMMLab Pose Estimation Toolbox and Benchmark.

das-datakit. Python

lingbot-world. Advancing Open-source World Models

cc9s. A k9s-inspired CLI and TUI for managing Claude Code sessions — browse, search, inspect, and clean up your AI coding sessions

interactive_world_sim. [RSS 2026] Interactive World Simulator for Robot Policy Training and Evaluation

DreamDojo. Official Codebase for "DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos" (ICML 2026)

WMPO. Official Implementation of Paper: WMPO: World Model-based Policy Optimization for Vision-Language-Action Models

world-model-eval. Code for "Evaluating Robot Policies in a World Model".

Ctrl-World. ICLR 2026 Paper: Ctrl-World

InfinityStar. [NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

LLaMA-VID. LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models (ECCV 2024)

MA-LMM. (2024CVPR) MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding

ICEdit. [NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!

OpenTrajBooster. Official implementation of TrajBooster

video-prediction-policy. Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations https://video-prediction-policy.github.io

Worldeval. Python

Bagel. Open-source unified multimodal model

cosmos-predict2. Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

Awesome-World-Models. A comprehensive list of papers for the definition of World Models and using World Models for General Video Generation, Embodied AI, and Autonomous Driving, including papers, codes, and related websites.

HunyuanWorld-1.0. Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

VideoWorld. [CVPR 2025] VideoWorld is a simple generative model that learns purely from unlabeled videos—much like how babies learn by observing their environment.

OmniGen2. OmniGen2: Exploration to Advanced Multimodal Generation. https://arxiv.org/abs/2506.18871

learn-python3. Jupyter notebooks for teaching/learning Python 3

UniVLA. [RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions

Awesome-From-Video-Generation-to-World-Model. A list of works on video generation towards world model

SimpleVLA-RL. [ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

ATI. Official implementation of ATI: Any Trajectory Instruction for Controllable Video Generation. https://arxiv.org/pdf/2505.22944

EX-4D. The implementation of Extreme Viewpoint 4D Video Generation

vjepa2. PyTorch code and models for VJEPA2 self-supervised learning from video.

jepa. PyTorch code and models for V-JEPA self-supervised learning from video.

Depth-Anything-V2. [NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

EWMBench. Official code for EWMBench: Evaluating Scene, Motion, and Semantic Quality in Embodied World Models

Open-Sora-Plan. This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

EasyControl. Implementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"(ICCV2025)

OpenHelix. OpenHelix: An Open-source Dual-System VLA Model for Robotic Manipulation

MAGI-1. MAGI-1: Autoregressive Video Generation at Scale

vq_bet_official. Official code for "Behavior Generation with Latent Actions" (ICML 2024 Spotlight)

Step-Video-TI2V. Python

open-genie. Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).

1xgpt. world modeling challenge for humanoid robots

EmbodiedEval. Evaluate Multimodal LLMs as Embodied Agents

AMBER. An LLM-free Multi-dimensional Benchmark for Multi-modal Hallucination Evaluation

Mirror. Python

QueryAgent. Code and data for QueryAgent(ACL 2024)

g1. g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

lumos. Code and data for "Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs"

avatar. (NeurIPS 2024) AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning

ToRA. ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

refiner. About The corresponding code from our paper " REFINER: Reasoning Feedback on Intermediate Representations" (EACL 2024). Do not hesitate to open an issue if you run into any trouble!

openr. OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models

search-and-learn. Recipes to scale inference-time compute of open models

LLMo1Wrapper. A Python wrapper that enables large language models (LLMs) to simulate the step-by-step thinking process of OpenAI’s o1 model, providing users with detailed reasoning and comprehensive answers.

DPO-ST. [ACL 2024] Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

DoLa. Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

PromptGating4MCTG. This is the repo for our work “An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation” (ACL 2023).

alfworld. ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

clip-image-search. Search images with a text or image query, using Open AI's pretrained CLIP model.

Style-LLM. Python

sNeuron-TST. EMNLP 2024 | Style-Specific Neurons for Steering LLMs in Text Style Transfer

annotated-transformer. An annotated implementation of the Transformer paper.

Transformer. Transformer模型复现

Reproduce_the_Transformer_model. 通过阅读论文Attention is all you need来复现Transformer模型

nanoCLIP. A lightweight Text-to-Image Retrieval model [Web App]

image-retrieval. Content-Based Image Retrieval (CBIR) using Faiss (Facebook) and many different feature extraction methods ( VGG16, ResNet50, Local Binary Pattern, RGBHistogram)

image-retrieval. 图片向量检索服务，包含Numpy、Faiss、ES、Milvus多种计算引擎

TinyStyler. Code for TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings, EMNLP 2024 Findings

stylellm_models. StyleLLM文风大模型：基于大语言模型的文本风格迁移项目。Text style transfer base on Large Language Model. #文字修饰 # 润色 #风格模仿

CDR_Meets_LLMs. Python

Ask-before-Plan. [EMNLP 2024] Ask-before-Plan: Proactive Language Agents for Real-World Planning

XAgent. An Autonomous LLM Agent for Complex Task Solving

Tell_Me_More. Repo for paper "Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents"

MAGE. Machine-generated text detection in the wild (ACL 2024)

OpenScholar. This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.

ProactiveAgent. A LLM-based Agent that predict its tasks proactively.

quiet-star. Code for Quiet-STaR

Awesome-LLM-Reasoning. From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

jittor. Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

face_recognition. The world's simplest facial recognition api for Python and the command line

ecnu-PGCourseShare. 华东师范大学研究生课程攻略共享计划

Langchain-Chatchat. Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

anything-llm. Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

AI-Scientist. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

awesome-chatgpt-zh. ChatGPT 中文指南🔥，ChatGPT 中文调教指南，指令指南，应用开发指南，精选资源清单，更好的使用 chatGPT 让你的生产力 up up up! 🚀

GPT_API_free. Free ChatGPT&DeepSeek API Key，免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API，支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。

PBR-White-Paper. ⚡️基于物理的渲染（PBR）白皮书 | White Paper of Physically Based Rendering(PBR)

swiper. Most modern mobile touch slider with hardware accelerated transitions

react-device-mockups. 📱React Wrapper for html5-device-mockups

camera-controls. A camera control for three.js, similar to THREE.OrbitControls yet supports smooth transitions and more features.

model-viewer. Easily display interactive 3D models on the web and in AR!

three-dat.gui. A package which create THREE.js controls on Dat.GUI

calendar. React Calendar

daycaca. 🐣 a pure JavaScript library to handle image via canvas

web-vitals. Essential metrics for a healthy site.

loadable-components. The recommended Code Splitting library for React ✂️✨

engine. A typescript interactive engine, support 2D, 3D, animation, physics, built on WebGL and glTF.

ShadowEditor. Cross-platform 3D scene editor based on three.js, golang and mongodb for desktop and web.

webglstudio.js. A full open source 3D graphics editor in the browser, with scene editor, coding pad, graph editor, virtual file system, and many features more.

whs.js. :rocket: 🌪 Super-fast 3D framework for Web Applications 🥇 & Games 🎮. Based on Three.js

Sketchbook. 3D playground built on three.js and cannon.js.

react-three-fiber. 🇨🇭 A React renderer for Three.js

three.js. JavaScript 3D Library.

glTF-Tutorials. glTF Tutorials

Hilo3d. 🎮 A 3D WebGL Rendering Engine

vudio.js. 音频可视化展示模块

kBooks. kindle网络电子书资源

tailwindcss. A utility-first CSS framework for rapid UI development.

tonovel-go. tonovel是一个简洁，干净的小说聚合系统

go-admin. 基于go+gin+vue+element admin 后台管理系统，支持用户管理，认证，内容管理等

react-use. React Hooks — 👍

roomler. Roomler - Multi-party Video Conferencing & Team Collaboration Tool using WebRTC (Janus Gateway)

gp. General purpose multi-party video conferencing application using WebRTC and signalling over Firebase Firestore in a mesh topology.

webrtc-mesh-network. Demo for a webrtc mesh network, communicate and watch stuff with friends in real time.

meething. dWebRTC Video Meetings MESH/SFU hybrid using GunDB, MediaSoup and Beyond!

flutter-sfu-video-call-group. Group video call mobile app built with Flutter and WebRTC SFU architecture

edumeet. edumeet - multiparty web-meetings using mediasoup and WebRTC

video-conference-webrtc. 🐀Complete client/server application demonstrating how to setup a video conference with multiple peers using WebRTC.

webrtc-stream. 🍧🍭😻包括但不局限于 WebRTC 的各种栗子

WiLearning. Multiparty meeting&e-learning using mediasoup, webrtc ,angular and ionic with powerful whiteboard support

Blog. Blogs about Technology - 一些技术文章

fe-code. 🍹🍰 愉快的写代码~（文章合集）

esbuild. An extremely fast bundler for the web

antd-tools. 🔧 Cli Tools for Ant Design React

copyfiles. copy files on the command line

ant-design. An enterprise-class UI design language and React UI library

astexplorer. A web tool to explore the ASTs generated by various parsers.

TypeScript. TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

intermock. Mocking library to create mock objects with fake data for TypeScript interfaces

vscode-extension-samples. Sample code illustrating the VS Code extension API.

vscode-bookmarks. Bookmarks Extension for Visual Studio Code

htmlparser2. The fast & forgiving HTML and XML parser

vue3-mindmap. Mindmap component for Vue3

Vue.D3.tree. Vue component to display tree based on D3.js layout.

vue3-News. 🔥 Find the latest breaking Vue3、Vue CLI 3+ & Vite News. (2024/2025)

lerna. Lerna is a fast, modern build system for managing and publishing multiple JavaScript/TypeScript packages from the same repository.

react-native-video-project. 一个基于react-native的纯跨平台的影视项目，欢迎大家star

ReactNativeEveryDayRead. React Native实现的阅读器，模仿观止app

react-native-guide. React Native指南汇集了各类react-native学习资源、开源App和组件

service-workers. A collection of utilities for creating/testing/experimenting with service workers.

vist. Virtual-list component build with react and rxjs

rxviz. Rx Visualizer - Animated playground for Rx Observables

rxmarbles. Interactive diagrams of Rx Observables

zao-interview. 📖常见面试问题

dva. 🌱 React and redux based, lightweight and elm-style framework. (Inspired by elm and choo)

leetcode-javascript. :beers: 喝杯小酒，一起做题。前端攻城狮从零入门算法的宝藏题库，根据知名算法老师的经验总结了 100+ 道 LeetCode 力扣的经典题型 JavaScript 题解和思路。已按题目类型分 label，一起加油。

free-api. 收集免费的接口服务,做一个api的搬运工

SmileVue. 这是一个移动端的电商系统,前端使用了Vue，后端使用了Koa2.

JavaScript-Algorithms. 基础理论+JS框架应用+实践，从0到1构建整个前端算法体系

react-cloud-music. React 16.8打造精美音乐WebApp

fucking-algorithm. Crack LeetCode, not only how, but also why.

daily_management. 日常管理系统

VeraBlog. HTML

Koa2-blog. node+koa2+mysql

React-Whole-barrels. webapck + react + react-router +dva + es6 + less + antd 实现的脚手架 👌👌

mywebpack. JavaScript

node-react-koa. 一个简单的前端react 后端node koa 的用户增删改查小web

blog. 博客

reactjs101. 从零开始学 ReactJS（ReactJS 101）是一本希望让初学者一看就懂的 ReactJS 中文入门教学书，由浅入深学习 ReactJS 生态系 (Flux, Redux, React Router, ImmutableJS, React Native, Relay/GraphQL etc.)。该分支为转码简体中文版

programmer-book. 公众号：普通程序员

fe-interview. 前端面试每日 3+1，以面试题来驱动学习，提倡每日学习与思考，每天进步一点！每天早上5点纯手工发布面试题（死磕自己，愉悦大家），6000+道前端面试题全面覆盖，HTML/CSS/JavaScript/Vue/React/Nodejs/TypeScript/ECMAScritpt/Webpack/Jquery/小程序/软技能……

album-express. node编写，express搭建的简单相册，功能有查看相册内图片，新建相册文件夹，上传图片。看这个代码可以简单了解下前后端交互的流程

react-projects. React从入门到放弃 -- 项目实战

verify-slide. 纯前端的滑动验证

jigsaw. canvas滑动验证码

DataStructure. C