Fanghua Ye

OpenViking. Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Bella. Bella is best

xiaozhi-esp32-server. 本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

HunyuanVideo-Avatar. Python

Awesome-Efficient-Reasoning. Paper list for Efficient Reasoning.

ACE-Step. ACE-Step: A Step Towards Music Generation Foundation Model

nanoVLM. The simplest, fastest repository for training/finetuning small-sized VLMs.

SurveyX. Academic Survey Paper Generation.

AI-Scientist-v2. The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

DeepEnlighten. Pure RL to post-train base models for social reasoning capabilities. Lightweight replication of DeepSeek-R1-Zero with Social IQa dataset.

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

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.

2D-Coordinate-System-for-ICL. [EMNLP 2024 Main] Official implementation of the paper "Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism".

open-box. Towards Generalized and Efficient Blackbox Optimization System/Package (KDD 2021 & JMLR 2024)

awesome-fm-fl. ✨✨A curated list of latest advances on Large Foundation Models with Federated Learning

AnLLM. Python

llm.c. LLM training in simple, raw C/CUDA

OpenHands. 🙌 OpenHands: AI-Driven Development

OOTDiffusion. [AAAI 2025] Official implementation of "OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on"

gemma_pytorch. The official PyTorch implementation of Google's Gemma models

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

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

Awesome-LLM-for-RecSys. Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

QAnything. Question and Answer based on Anything.

MAPIE. A scikit-learn-compatible library for estimating prediction intervals and controlling risks, based on conformal predictions.

alignment-handbook. Robust recipes to align language models with human and AI preferences

FactCHD. [IJCAI 2024] FactCHD: Benchmarking Fact-Conflicting Hallucination Detection

ACL2023-Retrieval-LM.github.io. https://acl2023-retrieval-lm.github.io/

haystack. Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.

XAgent. An Autonomous LLM Agent for Complex Task Solving

generative-ai-for-beginners. 21 Lessons, Get Started Building with Generative AI

Awesome-LLM-Uncertainty-Reliability-Robustness. Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

awesome-hallucination-detection. List of papers on hallucination detection in LLMs.

LLMDataHub. A quick guide (especially) for trending instruction finetuning datasets

pml2-book. Probabilistic Machine Learning: Advanced Topics

DeepExplain. A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)

CORE. CORE is a plug-and-play conversational agent for any recommender system.

CoLLiE. Collaborative Training of Large Language Models in an Efficient Way

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

deep-learning-containers. One stop shop for running AI/ML on AWS.

awesome-rl. Reinforcement learning resources curated

deep-rl-class. This repo contains the Hugging Face Deep Reinforcement Learning Course.

qdrant. Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

langchain. The agent engineering platform.

babyagi. Python

sharegpt. Easily share permanent links to ChatGPT conversations with your friends

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

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

StableLM. StableLM: Stability AI Language Models

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

llama. Inference code for Llama 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.

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.

pyserini. Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

typst. A markup-based typesetting system that is powerful and easy to learn.

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.

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

Topical-Chat. A dataset containing human-human knowledge-grounded open-domain conversations.

trlx. A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

maud. Python

ColossalAI. Making large AI models cheaper, faster and more accessible

dialogbot. dialogbot, provide search-based dialogue, task-based dialogue and generative dialogue model. 对话机器人，基于问答型对话、任务型对话、聊天型对话等模型实现，支持网络检索问答，领域知识问答，任务引导问答，闲聊问答，开箱即用。

shap. A game theoretic approach to explain the output of any machine learning model.

unified-focal-loss. Python

dice_loss_for_NLP. The repo contains the code of the ACL2020 paper `Dice Loss for Data-imbalanced NLP Tasks`

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

torchopt. TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

uvadlc_notebooks. Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2023

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

higher. higher is a pytorch library allowing users to obtain higher order gradients over losses spanning training loops rather than individual training steps.

topiocqa. Code and data for reproducing baselines for TopiOCQA, an open-domain conversational question-answering dataset

pml-book. "Probabilistic Machine Learning" - a book series by Kevin Murphy

cqe. Python

dnmf-python. Unofficial Python implementation of the DNMF overlapping community detection algorithm

conversationalIR. Overview of venues, research themes and datasets relevant for conversational search.

neural-structured-learning. Training neural models with structured signals.

DST-STAR. Slot Self-Attentive Dialogue State Tracking

Jekyll-Theme-Dumbarton. Dumbarton is a Jekyll Theme developed by Tyler Butler. The theme is designed for academics and features a simple home page with an about me section, a blog, and an interactive highlights section to describe publications, coursework, courses taught, and projects. UI design with Bootstrap and Animate CSS. Dumbarton is not compatible with Github Pages at this time.

RiSAWOZ. Datasets and codes for the paper "RiSAWOZ: A Large-Scale Multi-Domain Wizard-of-Oz Dataset with Rich Semantic Annotations for Task-Oriented Dialogue Modeling". (EMNLP 2020)

FSL-Mate. FSL-Mate: A collection of resources for few-shot learning (FSL).

fuzzywuzzy. Fuzzy String Matching in Python

Lihang. Statistical learning methods, 统计学习方法(第2版)[李航] [笔记, 代码, notebook, 参考文献, Errata, lihang]

som-dst. SOM-DST: Efficient Dialogue State Tracking by Selectively Overwriting Memory (ACL 2020)

first-order-model. This repository contains the source code for the paper First Order Motion Model for Image Animation

trade-dst. Source code for transferable dialogue state generator (TRADE, Wu et al., 2019). https://arxiv.org/abs/1905.08743

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

mit-deep-learning. Tutorials, assignments, and competitions for MIT Deep Learning related courses.

SUMBT. SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking (ACL 2019)

RNN-for-Joint-NLU. Pytorch implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling" (https://arxiv.org/abs/1609.01454)

sequicity. Source code for the ACL 2018 paper entitled "Sequicity: Simplifying Task-oriented Dialogue Systems with Single Sequence-to-Sequence Architectures" by Wenqiang Lei et al.

Mem2Seq. Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems

DialoguePaper.

multiwoz. Source code for end-to-end dialogue model from the MultiWOZ paper (Budzianowski et al. 2018, EMNLP)

Dialogue. Python

personal_website. HTML

umap. Uniform Manifold Approximation and Projection

UnsupervisedDeepLearning-Pytorch. This repository tries to provide unsupervised deep learning models with Pytorch

VaDE-pytorch. the reproduce of Variational Deep Embedding : A Generative Approach to Clustering Requirements by pytorch

GCN. Graph Convolutional Neural Network Hashing

SemanticHashingWeakSupervision. The pyTorch implementation of two models described in Deep Semantic Text Hashing with Weak Supervision (SIGIR'18)

VariationalDeepSemanticHashing. The original implementation of the models and experiments of Variational Deep Semantic Hashing paper (SIGIR 2017)

SPTAG. A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario.

pytorch-handbook. pytorch handbook是一本开源的书籍，目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门，其中包含的Pytorch教程全部通过测试保证可以成功运行

DNMF. Discrete Overlapping Community Detection with Pseudo Supervision

singa. a distributed deep learning platform

NRLPapers. Must-read papers on network representation learning (NRL) / network embedding (NE)

FedMF. Python

GNNPapers. Must-read papers on graph neural networks (GNN)

TOEFL-10000-0. 曲根一万托福单词视频

awesome-resume. Resume，Resume Templates，程序员简历例句，简历模版，

DANMF. Deep Autoencoder-like NMF

AANMF. Adaptive Affinity Learning for Accurate Community Detection

DANMF. A sparsity aware implementation of "Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection" (CIKM 2018).

the-gan-zoo. A list of all named GANs!

Generative-Adversarial-Network-Tutorial. Tutorial on creating your own GAN in Tensorflow

resume. A minimalist resume template for Jekyll and Hexo

kamranahmedse.github.io. Blog created using github-pages-blog-action

jmcglone.github.io. Data for jmcglone.com. Site generated by Jekyll. Hosted on GitHub.

one-page-wonder-jekyll. Jekyll port of One Page Wonder

raganwald.github.com. raganwald.com jekyll source

researcher. A jekyll based resume template

sustain. 🎹 Personal blog powered by Jekyll

dbyll. Stylish, minimalistic theme for jekyll.

daisyHawen.github.io. https://daisyhawen.github.io/

aktech.github.io. My Homepage/Blog at Github. :pencil:

valryon.github.io. My portfolio.

Srijancse.github.io. Jekyll based personal website + blog.