Naiyuan Liu

valuecell. ValueCell is a community-driven, multi-agent platform for financial applications.

SEED-GRPO. The official repository of SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization

OmniNWM. [ECCV 2026] OmniNWM: Omniscient Navigation World Models for Autonomous Driving

MapTR. [ICLR'23 Spotlight & ECCV'24 & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

BEVDet. Code base of the BEVDet series .

lift-splat-shoot. Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D (ECCV 2020)

occupancy_networks. This repository contains the code for the paper "Occupancy Networks - Learning 3D Reconstruction in Function Space"

BEVFormer. [ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segmentation.

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

torchtune. PyTorch native post-training library

Grounded-SAM-2. Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

recognize-anything. Open-source and strong foundation image recognition models.

speech-to-speech. Build local voice agents with open-source models

graphrag. A modular graph-based Retrieval-Augmented Generation (RAG) system

echomimic. [AAAI 2025] EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

T2I-Adapter. T2I-Adapter

DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

LLM101n. LLM101n: Let's build a Storyteller

TextGenerator. OCR dataset Text-Detection dataset Font-Classification dataset generator

nlp_chinese_corpus. 大规模中文自然语言处理语料 Large Scale Chinese Corpus for NLP

ocr_synth_text_chinese. 生成训练文本检测数据集

BaiduImageSpider. 一个超级轻量的百度图片爬虫

llama3. The official Meta Llama 3 GitHub site

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

clip_dinoiser. Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.

COMM. Pytorch code for paper From CLIP to DINO: Visual Encoders Shout in Multi-modal Large Language Models

Vary. [ECCV 2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

Vary-toy. Official code implementation of Vary-toy (Small Language Model Meets with Reinforced Vision Vocabulary)

DINO. [ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

YOLO-World. [CVPR 2024] Real-Time Open-Vocabulary Object Detection

GPT-SoVITS. 1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Person_reID_baseline_pytorch. :bouncing_ball_person: Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

IP-Adapter. The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

DWPose. "Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)

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

PicImageSearch. 整合图片识别 API，用于以图搜源 / Aggregator for Reverse Image Search API

CLRerNet. The official implementation of "CLRerNet: Improving Confidence of Lane Detection with LaneIoU"

IP_LAP. CVPR2023 talking face implementation for Identity-Preserving Talking Face Generation With Landmark and Appearance Priors

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

CTCDecoder. Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.

video-retalking. [SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild

ultimatevocalremovergui. GUI for a Vocal Remover that uses Deep Neural Networks.

faster-whisper. Faster Whisper transcription with CTranslate2

PySceneDetect. :movie_camera: Python and OpenCV-based scene cut/transition detection program & library.

MyHeyGen.

AnimateDiff. Official implementation of AnimateDiff.

OutfitAnyone. Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person

generative-models. Generative Models by Stability AI

llms_paper. 该仓库主要记录 LLMs 算法工程师相关的顶会论文研读笔记（多模态、PEFT、小样本QA问答、RAG、LMMs可解释性、Agents、CoT）

Douyin_TikTok_Download_API. 🚀「Douyin_TikTok_Download_API」是一个开箱即用的高性能异步抖音、快手、TikTok、Bilibili数据爬取工具，支持API调用，在线批量解析及下载。

TikTokDownloader. TikTok 发布/喜欢/合辑/直播/视频/图集/音乐；抖音发布/喜欢/收藏/收藏夹/视频/图集/实况/直播/音乐/合集/评论/账号/搜索/热榜数据采集工具/下载工具

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

BaiduPCS-Go. iikira/BaiduPCS-Go原版基础上集成了分享链接/秒传链接转存功能

cowtransfer-uploader. Simple Cowtransfer Uploader/Downloader in Golang

MetaCLIP. NeurIPS 2025 Spotlight; ICLR2024 Spotlight; CVPR 2024; EMNLP 2024

CTranslate2. Fast inference engine for Transformer models

whisperX. WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

whisper-diarization. Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

GeneFace. GeneFace: Generalized and High-Fidelity 3D Talking Face Synthesis; ICLR 2023; Official code

Rope. GUI-focused roop

llama-cookbook. Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

Qwen-VL. The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

Fooocus. Focus on prompting and generating

MTN. Progressive Text-to-3D Generation for Automatic 3D Prototyping (ACM TOMM)

MiniGPT-5. Official implementation of paper "MiniGPT-5: Interleaved Vision-and-Language Generation via Generative Vokens"

ChuanhuChatGPT. GUI for ChatGPT API and many LLMs. Supports agents, file-based QA, GPT finetuning and query with web search. All with a neat UI.

AutoGPTQ. An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Qwen. The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

TransHuman. Official code for ICCV 2023 paper: "TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering".

Awesome-Avatars. List of recent advances for human avatars, including generation, reconstruction, and editing, etc.

encryptpy. A tool to encrypt your Python project

facechain. FaceChain is a deep-learning toolchain for generating your Digital-Twin.

spear-tts-pytorch. Implementation of Spear-TTS - multi-speaker text-to-speech attention network, in Pytorch

visualblocks. Visual Blocks for ML is a Google visual programming framework that lets you create ML pipelines in a no-code graph editor. You – and your users – can quickly prototype workflows by connecting drag-and-drop ML components, including models, user inputs, processors, and visualizations.

wandb. The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

nncf. Neural Network Compression Framework for enhanced OpenVINO™ inference

VITS-fast-fine-tuning. This repo is a pipeline of VITS finetuning for fast speaker adaptation TTS, and many-to-many voice conversion

jupyter-ai. An open source extension that connects AI agents to computational notebooks in JupyterLab.

MQBench. Model Quantization Benchmark

so-vits-svc-fork. so-vits-svc fork with realtime support, improved interface and more features.

soft-vc. Soft speech units for voice conversion

glow. Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"

FastSpeech2. An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"

Awesome-CV-Foundational-Models.

albumentations. Fast and flexible image augmentation library. Paper about the library: https://www.mdpi.com/2078-2489/11/2/125

muzic. Muzic: Music Understanding and Generation with Artificial Intelligence

awesome. 😎 Awesome lists about all kinds of interesting topics

vits. VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

book-text-to-speech. A book about Text-to-Speech (TTS) in Chinese.

TTS. 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

llama2.c. Inference Llama 2 in one file of pure C

VQGAN-CLIP. Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

SadTalker. [CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

metaseq. Repo for external large-scale work

CM3Leon. An open source implementation of "Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning", an all-new multi modal AI that uses just a decoder to generate both text and images

mmyolo. OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

Co-DETR. [ICCV 2023] DETRs with Collaborative Hybrid Assignments Training

MOSS-RLHF. Secrets of RLHF in Large Language Models Part I: PPO

Awesome-Face-Forgery-Generation-and-Detection. A curated list of articles and codes related to face forgery generation and detection.

unicom. Large-Scale Visual Representation Model

ChatLaw. ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型

mmrazor. OpenMMLab Model Compression Toolbox and Benchmark.

Awesome-Video-Diffusion. A curated list of recent diffusion models for video generation, editing, and various other applications.

Open-R1. The open source implementation of DeepSeek-R1. 开源复现 DeepSeek-R1

MNN. MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

audiocraft. Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

musiclm-pytorch. Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

FinGPT. FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

gpt-engineer. CLI platform to experiment with codegen. Precursor to: https://lovable.dev

LLaMA-Adapter. [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

mmengine. OpenMMLab Foundational Library for Training Deep Learning Models

learning_research. 本人的科研经验

DragGAN. Implementation of DragGAN: Interactive Point-based Manipulation on the Generative Image Manifold

DragGAN. Unofficial Implementation of DragGAN - "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold" （DragGAN 全功能实现，在线Demo，本地部署试用，代码、模型已全部开源，支持Windows, macOS, Linux）

DragGAN. Official Code for DragGAN (SIGGRAPH 2023)

DDSP-SVC. Real-time end-to-end singing voice conversion system based on DDSP (Differentiable Digital Signal Processing)

contentvec. speech self-supervised representations

DiffSinger. An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism

ImageBind. ImageBind One Embedding Space to Bind Them All

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

pycatfd. Cat facial detection and landmark recognition in Python

Pets-Face-Recognition. Animal identification using face recognition based methods

VideoMAEv2. [CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

LLMsNineStoryDemonTower. 【LLMs九层妖塔】分享 LLMs在自然语言处理（ChatGLM、Chinese-LLaMA-Alpaca、小羊驼 Vicuna、LLaMA、GPT4ALL等）、信息检索（langchain）、语言合成、语言识别、多模态等领域（Stable Diffusion、MiniGPT-4、VisualGLM-6B、Ziya-Visual等）等 实战与经验。

Ask-Anything. [CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

recurrent-memory-transformer. [NeurIPS 22] [AAAI 24] Recurrent Transformer-based long-context architecture.

recurrent-memory-transformer-pytorch. Implementation of Recurrent Memory Transformer, Neurips 2022 paper, in Pytorch

MiniGPT-4. Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

pdfGPT. PDF GPT allows you to chat with the contents of your PDF file by using GPT capabilities. The most effective open source solution to turn your pdf files in a chatbot!

CodeGen. CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

MOSS. An open-source tool-augmented conversational language model from Fudan University

label-studio. Label Studio is a multi-type data labeling and annotation tool with standardized output format

lmdb. Read-only mirror of official repo on openldap.org. Issues and pull requests here are ignored. Use OpenLDAP ITS for issues.

label-studio-ml-backend. Configs and boilerplates for Label Studio's Machine Learning backend

StableLM. StableLM: Stability AI Language Models

danbooru. A taggable image board written in Rails.

Segment-Everything-Everywhere-All-At-Once. [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

dinov2. PyTorch code and models for the DINOv2 self-supervised learning method.

Segment-and-Track-Anything. An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

EditAnything. Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)

DreamPose. Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"

sd-webui-segment-anything. Segment Anything for Stable Diffusion WebUI

playground. A central hub for gathering and showcasing amazing projects that extend OpenMMLab with SAM and other exciting features.

once-for-all. [ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

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.

Caption-Anything. Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with diverse controls for user preferences. https://huggingface.co/spaces/TencentARC/Caption-Anything https://huggingface.co/spaces/VIPLab/Caption-Anything

GLM. GLM (General Language Model)

langchain. The agent engineering platform.

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

ChatGLM-6B. ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

ShowAnything. Jupyter Notebook

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

FindTheChatGPTer. ChatGPT爆火，开启了通往AGI的关键一步，本项目旨在汇总那些ChatGPT的开源平替们，包括文本大模型、多模态大模型等，为大家提供一些便利

WechatExporter. Wechat Chat History Exporter 微信聊天记录导出备份程序

pytorch-quantization-demo. A simple network quantization demo using pytorch from scratch.

InternImage. [CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions

LLMSurvey. The official GitHub page for the survey paper "A Survey of Large Language Models".

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

GLIP. Grounded Language-Image Pre-training

GroundingDINO. [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

BLIP. PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Semantic-Segment-Anything. Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

MM-Diffusion. [CVPR'23] MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

GLoT. Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation

opencv-mobile. The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, HarmonyOS, WebAssembly, watchOS, tvOS, visionOS

text_renderer. Generate text line images for training deep learning OCR models

awesome-DeepLearning. 深度学习入门课、资深课、特色课、学术案例、产业实践案例、深度学习知识百科及面试题库The course, case and knowledge of Deep Learning and AI

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

ChatGenTitle. 🌟 ChatGenTitle：使用百万arXiv论文信息在LLaMA模型上进行微调的论文题目生成模型

JARVIS. JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

dolly. Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

sd-webui-additional-networks. Python

TencentPretrain. Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo

llama. Inference code for Llama models

LMFlow. An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

pypdf. A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

alpaca-lora. Instruct-tune LLaMA on consumer hardware

PyTorchTricks. Some tricks of pytorch... :star:

bpemb. Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

gumbel-softmax. categorical variational autoencoder using the Gumbel-Softmax estimator

DALL-E. PyTorch package for the discrete VAE used for DALL·E.

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

Uni-Perceiver. Python

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

awesome-chatgpt-project. 1.chatGPT注册 2.chatGPT成品项目整理 3.高效使用chatGPT的小技巧 ↓演示网站

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。

Chinese-Text-Classification-Pytorch. 中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

UniHCP. Official PyTorch implementation of UniHCP

HumanBench. This repo is official implementation of HumanBench (CVPR2023)

Bert-Chinese-Text-Classification-Pytorch. 使用Bert，ERNIE，进行中文文本分类

Chinese-Word-Vectors. 100+ Chinese Word Vectors 上百种预训练中文词向量

text_classification. all kinds of text classification models and more with deep learning

BELLE. BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

sd-webui-controlnet. WebUI extension for ControlNet

lora-scripts. SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

HFGI3D. Jupyter Notebook

SPI. [CVPR 2023] SPI: 3D GAN Inversion with Facial Symmetry Prior