zhoudaquan

HOI-DETR. Improving and Evaluating Hand-Object Interaction Detection

box3d. Box3D is a 3D physics engine for games

Fast-dLLM. Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"

HumanNet. HumanNet: Scaling Human-centric Video Learning to One Million Hours

VideoRAG. [KDD'2026] "VideoRAG: Chat with Your Videos"

ReVidgen. [ICML 2026🔥]Rethinking Video Generation Model for the Embodied World

MHLA. [ICLR 2026🔥] MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

Agent-Memory-Paper-List. The paper list of "Memory in the Age of AI Agents: A Survey"

awesome-humanoid-manipulation. A curated list of awesome papers and resources on humanoid manipulation, dexterous manipulation, bimanual dexterous manipulation, in-hand manipulation, and humanlike manipulation.

VeOmni. VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

BitNet. Official inference framework for 1-bit LLMs

Agent-S. Agent S: an open agentic framework that uses computers like a human

TradingAgents. TradingAgents: Multi-Agents LLM Financial Trading Framework

developer-portfolios. A list of developer portfolios for your inspiration

Awesome-GitHub-Repo. 收集整理 GitHub 上高质量、有趣的开源项目。

Matrix-Game. Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

1xgpt. world modeling challenge for humanoid robots

DeepSeek-R1.

openai-agents-python. A lightweight, powerful framework for multi-agent workflows

tabby. Self-hosted AI coding assistant

ChronoEdit. [ICLR 2026] ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation

Qwen-Image. Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

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

MeanFlow. Pytorch implementation of MeanFlow on ImageNet and CIFAR10

debugpy. An implementation of the Debug Adapter Protocol for Python

EasyOCR. Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

IMO25. An AI agent system for solving International Mathematical Olympiad (IMO) problems using Google's Gemini, OpenAI, and XAI APIs.

motionshop-2. Project page of Motionshop-2: An advanced version of the Motionshop; We add a new fancy feature: 3D Animation Engine; AI for computer graphics

coze-studio. An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.

Bagel. Open-source unified multimodal model

HunyuanCustom. HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation

Second-Me. Train your AI self, amplify you, bridge the world

ME-rPPG. ME-rPPG is a memory-efficient realtime rPPG network

OpenManus. No fortress, purely open ground. OpenManus is Coming.

VisualThinker-R1-Zero. Explore the Multimodal “Aha Moment” on 2B Model

Magma. [CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents

R1-Onevision. R1-onevision, a visual language model capable of deep CoT reasoning.

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

Step-Video-T2V. Python

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Janus. Janus-Series: Unified Multimodal Understanding and Generation Models

DeepSeek-V3. Python

open-r1. Fully open reproduction of DeepSeek-R1

TinyZero. Minimal reproduction of DeepSeek R1-Zero

OpenHands. 🙌 OpenHands: AI-Driven Development

MiniMax-01. The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention

GenesisEnvs. Genesis Reinforcement Learning Environments

droid. Distributed Robot Interaction Dataset.

VITA. ✨✨[NeurIPS 2025] VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

transfusion-pytorch. Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

trendFinder. Stay on top of trending topics on social media and the web with AI

Diffusion-LM. Diffusion-LM

AgiBot-World. [IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

NarratoAI. 利用 AI 大模型，一键解说并剪辑视频

unsloth. Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek, GLM and other models.

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

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

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

Slow_Thinking_with_LLMs. A series of technical report on Slow Thinking with LLM

DiffSensei. Implementation of [CVPR 2025] "DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"

MovieGen. Unofficial implementation of Meta's MovieGen models

superclass. [NeurIPS 2024] Classification Done Right for Vision-Language Pre-Training

VideoSys. VideoSys: An easy and efficient system for video generation

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

LLaMA-Mesh. Unifying 3D Mesh Generation with Language Models

nunchaku. [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

dask. Parallel computing with task scheduling

Protenix. Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

Grounded-Video-LLM. [EMNLP 2025 Findings] Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models

bypy. Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端

MinerU. Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

resource-stream. GPU programming related news and material links

Cosmos-Tokenizer. A suite of image and video neural tokenizers

Video-XL. 🔥🔥First-ever hour scale video understanding models

kotaemon. An open-source RAG-based tool for chatting with your documents.

swarm. Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

MaskDiffusion. Python

infinigen. Infinite Photorealistic Worlds using Procedural Generation

GR-1. Code for "Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation"

HPT. Heterogeneous Pre-trained Transformer (HPT) as Scalable Policy Learner.

Emu3. Next-Token Prediction is All You Need

Web. 千古前端图文教程，超详细的前端入门到进阶知识库。从零开始学前端，做一名精致优雅的前端工程师。

audio-diffusion-pytorch. Audio generation using diffusion models, in PyTorch.

ml-ferret. Python

vllm-kvcompress. KV cache compression for high-throughput LLM inference

movie-gen. An open source community implementation of the model from the paper: "Movie Gen: A Cast of Media Foundation Models". Join our community to help implement this model!

exo. Run frontier AI locally.

crawl4ai. 🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

xDiT. xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

localsend. An open-source cross-platform alternative to AirDrop

LVD-2M. [NeurIPS 2024 D&B Track] Official Repo for "LVD-2M: A Long-take Video Dataset with Temporally Dense Captions"

ai-toolkit. The ultimate training toolkit for finetuning diffusion models

claude-cookbooks. A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

x-flux. Python

LongWriter. [ICLR 2025] LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

MS-Diffusion. [ICLR 2025] Official implementation of MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance

Megatron-LM. Ongoing research training transformer models at scale

ComfyUI_StoryDiffusion. You can using StoryDiffusion in ComfyUI

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

mem0. Universal memory layer for AI Agents

Paints-UNDO. Understand Human Behavior to Align True Needs

Kolors. Kolors Team

torchtitan. A PyTorch native platform for training generative AI models

lloco. The official repo for "LLoCo: Learning Long Contexts Offline"

ChronoMagic-Bench. [NeurIPS 2024 D&B Spotlight🔥] ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation

cambrian. Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

hallo. Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation

LLM101n. LLM101n: Let's build a Storyteller

Awesome-LLM-Compression. Awesome LLM compression research papers and tools.

gpt4all. GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

champ. [ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

S-LoRA. S-LoRA: Serving Thousands of Concurrent LoRA Adapters

MoRF. Receptive field as experts

Unique3D. [NeurIPS 2024] Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image

llama3-from-scratch. llama3 implementation one matrix multiplication at a time

RectifiedFlow. Official Implementation of Rectified Flow (ICLR2023 Spotlight)

efficient-kan. An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

q-diffusion. [ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.

SpeeD. SpeeD: A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training

StoryDiffusion. Accepted as [NeurIPS 2024] Spotlight Presentation Paper

PLLaVA. Official repository for the paper PLLaVA

corenet. CoreNet: A library for training deep neural networks

VAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

MLLM_Factory. A Dead Simple and Modularized Multi-Modal Training and Finetune Framework. Compatible to any LLaVA/Flamingo/QwenVL/MiniGemini etc series models.

motion-diffusion-model. The official PyTorch implementation of the paper "Human Motion Diffusion Model"

co-tracker. CoTracker is a model for tracking any point (pixel) on a video.

chug. Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.

MediaCrawler. 小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫、快手视频 | 评论爬虫、B 站视频 ｜ 评论爬虫、微博帖子 ｜ 评论爬虫、百度贴吧帖子 ｜ 百度贴吧评论回复爬虫 | 知乎问答文章｜评论爬虫

grok-1. Grok open release

LLM-Viewer. Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.

RankSortLoss. Official PyTorch Implementation of Rank & Sort Loss for Object Detection and Instance Segmentation [ICCV2021]

evolutionary-model-merge. Official repository of Evolutionary Optimization of Model Merging Recipes

scaling_on_scales. When do we not need larger vision models?

autofd. Automatic Functional Differentiation in JAX

bias.

grok. Python

moviepy. Video editing with Python

Medusa. Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

mamba. Mamba SSM architecture

Sora-Generates-Videos-with-Stunning-Geometrical-Consistency. Sora Generates Videos with Stunning Geometrical Consistency

Moore-AnimateAnyone. Character Animation (AnimateAnyone, Face Reenactment)

Open-AnimateAnyone. Unofficial Implementation of Animate Anyone

EMO. Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

VILA. VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

Neural-Network-Diffusion. We introduce a novel approach for parameter generation, named neural network parameter diffusion (p-diff), which employs a standard latent diffusion model to synthesize a new set of parameters

minbpe. Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

OpenSORA. A public repository for reproducing a open source sora comparable video generation model

Magic-Me. Codes for ID-Specific Video Customized Diffusion

StableCascade. Official Code for Stable Cascade

TinyLlama. The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

LVM. Python

WeChatMsg.

big_vision. Official codebase used to develop Vision Transformer, SigLIP, MLP-Mixer, LiT and more.

Video-LLaVA. 【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

GPT-4V_Social_Media. GPT-4V(ision) as A Social Media Analysis Engine

MAgIC. Python

PixArt-alpha. PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

ChatAnything. Official Repo for the Paper: CHATANYTHING: FACETIME CHAT WITH LLM-ENHANCED PERSONAS

fiftyone. Refine high-quality datasets and visual AI models

Fooocus. Focus on prompting and generating

DiT-3D. 🔥🔥🔥Official Codebase of "DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation"

OpenMoE. A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

CoDeF. [CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

text-to-motion. Official implementation for "Generating Diverse and Natural 3D Human Motions from Texts (CVPR2022)."

gigagan-pytorch. Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

Dataset_Quantization. [ICCV2023] Dataset Quantization

MovieChat. [CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

DragDiffusion. [CVPR2024, Highlight] Official code for DragDiffusion

pytorch_geometric. Graph Neural Network Library for PyTorch

LISA. Project Page for "LISA: Reasoning Segmentation via Large Language Model"

starcoder. Home of StarCoder: fine-tuning & inference!

AdaFace-dev. A Versatile Face Encoder for Zero-Shot Diffusion Model Personalization

RealChar. 🎙️🤖Create, Customize and Talk to your AI Character/Companion in Realtime (All in One Codebase!). Have a natural seamless conversation with AI everywhere (mobile, web and terminal) using LLM OpenAI GPT3.5/4, Anthropic Claude2, Chroma Vector DB, Whisper Speech2Text, ElevenLabs Text2Speech🎙️🤖

bubogpt. BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs

HumanML3D. HumanML3D: A large and diverse 3d human motion-language dataset.

quivr. Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

milvus. Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

generative-models. Generative Models by Stability AI

ai-getting-started. A Javascript AI getting started stack for weekend projects, including image/text models, vector stores, auth, and deployment configs

ChatPaper. Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

chain-of-thought-hub. Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

DragGAN. Official Code for DragGAN (SIGGRAPH 2023)

VisualGLM-6B. Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

AudioGPT. AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

missing_aware_prompts. Multimodal Prompting with Missing Modalities for Visual Recognition, CVPR'23

consistency_models. Official repo for consistency models.

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

ImageReward. [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

eai-vc. The repository for the largest and most comprehensive empirical study of visual foundation models for Embodied AI (EAI).

GLM-130B. GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

alpaca-lora. Instruct-tune LLaMA on consumer hardware

LLM-As-Chatbot. LLM as a Chatbot Service

TaskMatrix. Python

Video-P2P. Video-P2P: Video Editing with Cross-attention Control

make-a-video-pytorch. Implementation of Make-A-Video, new SOTA text to video generator from Meta AI, in Pytorch

Prompt-Engineering-Guide. 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

evals. Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.