Hongyin Luo

Sipp. AI inference, packed simply. A blazing-fast, zero-dependency WebGPU runtime to run GGUF models directly in the browser. Features a symmetric API for seamless local execution and cloud provider routing. Built with Rust & C++.

rewardgen. Python

tapestry. Project Tapestry aims to give every nation and participant frontier AI they can call their own — uniting a global consortium to train a shared frontier model from which partners build and own sovereign models aligned to their national, socio-cultural, and industrial needs.

Evaluator. Open-source library for scalable, reproducible evaluation of AI models and benchmarks.

Nemotron. Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

truss-examples. Examples of models deployable with Truss

llm-calculator. Interactive display to see if an LLM can fit on a device

atlas. Pure Rust Inference Engine

tokenspeed. TokenSpeed is a speed-of-light LLM inference engine.

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

CodeWhale. Open-source, community-driven agent harness

jinguyuan-dumpling-skill. 金谷园饺子馆.Skill - 北邮旁的饺子馆

pi. AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

OpenSWE. Python

twitter-cli. A CLI for Twitter/X — feed, bookmarks, and user timeline in terminal

dimos. Dimensional is the agentic operating system for physical space. Command humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seamlessly with physical input (cameras, lidar, actuators).

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

ms-swift. Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

play2prompt. Implementation for paper "PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play"

dataclaw. Agent harness to publish your agent chat history as Huggingface datasets.

tau2-bench. τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains

archipelago. Harness for running and evaluating AI agents against RL environments

subconscious-python. Subconscious Python SDK

flash-attention. Fast and memory-efficient exact attention

ai-agent-degree-planner. An AI agent powered by the Subconscious SDK that searches official university course catalogs, extracts degree requirements, and generates a complete semester by semester plan of study using an agent runtime built for reliable multi step reasoning and verification.

agent-browser. Browser automation CLI for AI agents

pixio. [CVPR 2026] Pixio: a capable vision encoder dedicated to dense prediction, simply by pixel reconstruction

NitroGen. A Foundation Model for Generalist Gaming Agents

mini-sglang. A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

marp. The entrance repository of Markdown presentation ecosystem

browserbench. The First Benchmark for Browser Infrastructure Stealth

miles. Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

AVCD. [NeurIPS 2025] AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding

Parallel-R1. The offical repo for "Parallel-R1: Towards Parallel Thinking via Reinforcement Learning"

EvaMAE. Python

unitree_sdk2. Unitree robot sdk version 2. https://support.unitree.com/home/zh/developer

CookLikeHOC. 🥢像老乡鸡🐔那样做饭。已添加2026年发布的《老乡鸡菜品溯源报告 2.0中新出现的菜品。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

unifolm-world-model-action. Python

AgentLab. AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

visualwebarena. VisualWebArena is a benchmark for multimodal agents.

LessIsMore. [ICML 2026] Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning

system_prompts_leaks. Extracted system prompts from Anthropic - Claude Fable 5, Opus 5, Claude Design, Claude Code. OpenAI - ChatGPT GPT-5.6-Sol, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly.

deep_research_bench. DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

mini-swe-agent. The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

agent-lightning. The absolute trainer to light up AI agents.

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

DeepResearch. Tongyi Deep Research, the Leading Open-source Deep Research Agent

awesome-web-agents. 🔥 A list of tools, frameworks, and resources for building AI web agents

Multiverse.

Multiverse-Engine. Customized Inference Engine for Multiverse Models

subconscious. JavaScript

learn-claude-code. Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

RL-Factory. Train your Agent model via our easy and efficient framework

codex. Lightweight coding agent that runs in your terminal

SelfCite. Code for the ICML 2025 paper "SelfCite Self-Supervised Alignment for Context Attribution in Large Language Models"

Awesome-ML-SYS-Tutorial. My learning notes for ML SYS.

MuSR. Python

GPU-Puzzles. Solve puzzles. Learn CUDA.

awesome-deepseek-integration. Integrate the DeepSeek API into popular software

AIChip_Paper_List.

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

llm_benchmarks. A collection of benchmarks and datasets for evaluating LLM.

UbiMoE. C++

transfomers-silicon-research. Research and Materials on Hardware implementation of Transformer Model

deep-research. An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.

PYNQ_tutorials. Jupyter Notebook

s1. s1: Simple test-time scaling

Vitis_Accel_Examples. Vitis_Accel_Examples

Transformer-Accelerator-Based-on-FPGA. You can run it on pynq z1. The repository contains the relevant Verilog code, Vivado configuration and C code for sdk testing. The size of the systolic array can be changed, now it is 16X16.

inference. Reference implementations of MLPerf® inference benchmarks

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

open-r1. Fully open reproduction of DeepSeek-R1

CNN-FPGA. 使用Verilog实现的CNN模块，可以方便的在FPGA项目中使用

AutoPresent. Code for the paper "AutoPresent: Designing Structured Visuals From Scratch" (CVPR 2025)

Vitis-AI. Vitis AI is Xilinx’s development stack for AI inference on Xilinx hardware platforms, including both edge devices and Alveo cards.

PYNQ_Workshop. Jupyter Notebook

neuralNetwork. Verilog

the_well. A 15TB Collection of Physics Simulation Datasets

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Vivado-Design-Tutorials. Tcl

Step-DPO. Implementation for "Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs"

Thinking-Claude. Let your Claude able to think

Awesome-Text2SQL. Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.

Vitis-AI-Tutorials.

Vitis-Tutorials. Vitis In-Depth Tutorials

docling. Get your documents ready for gen AI

Firefly. Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

flashinfer. FlashInfer: Kernel Library for LLM Serving

Atom. [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving

BitNet. Official inference framework for 1-bit LLMs

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

text-generation-inference. Large Language Model Text Generation Inference

mem0. Universal memory layer for AI Agents

ReBase. ReBase: Training Task Experts through Retrieval Based Distillation

hilbertcurve. maps between 1-D space filling hilbert curve and N-D coordinates

omniplex. Open-Source Perplexity

Halfrost-Field. ✍🏻 Source Code Deep Dives, System Design & Engineering Blogs | Halfrost-Field 冰霜之地：源码解析、系统设计与工程实践笔记

omniparse. Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

open-webui. User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Vane. Vane is an AI-powered answering engine.

searxng. SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.

thread. Python

HALC. [ICML 2024] Official implementation for "HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding"

llm_speech_emotion_challenge. Jupyter Notebook

fructose. Python

instructor. structured outputs for llms

research-career-tools. Python

interactions.py. A highly extensible, easy to use, and feature complete bot framework for Discord

onelinerizer. Shamelessly convert any Python 2 script into a terrible single line of code

MathPile. [NeurlPS D&B 2024] Generative AI for Math: MathPile

dinosr. DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning

cav-mae. Code and Pretrained Models for ICLR 2023 Paper "Contrastive Audio-Visual Masked Autoencoder".

LangCode. LangCode - Improving alignment and reasoning of large language models (LLMs) with natural language embedded program (NLEP).

pytorch. Ascend PyTorch adapter (torch_npu). Mirror of https://gitcode.com/Ascend/pytorch

GraphUnsupASR. Shell

anchoring-ai. An open-source no-code tool for teams to collaborate on building, evaluating, and hosting applications leveraging GPT and other large language models. You could easily build and share LLM-powered apps, manage your budget and run batch jobs.

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

openinterpreter. A coding agent for open models like Kimi K3

ibm-generative-ai. IBM-Generative-AI is a Python library built on IBM's large language model REST interface to seamlessly integrate and extend this service in Python programs.

codellama. Inference code for CodeLlama models

ast. Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

TextBlob. Simple, Pythonic, text processing--Sentiment analysis, part-of-speech tagging, noun phrase extraction, translation, and more.

whisper-at. Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

leaked-system-prompts. Collection of leaked system prompts

FakeNewsNet. This is a dataset for fake news detection research

Open-Instruction-Generalist. Open Instruction Generalist is an assistant trained on massive synthetic instructions to perform many millions of tasks

EAR. Code for the ACL 2023 long paper - Expand, Rerank, and Retrieve: Query Reranking for Open-Domain Question Answering

LogiCoT. the instructions and demonstrations for building a formal logical reasoning capable GLM

ltu. Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".

impact. ML has an impact on the climate. But not all models are born equal. Compute your model's emissions with our calculator and add the results to your paper with our generated latex template

Dromedary. Dromedary: towards helpful, ethical and reliable LLMs.

ssast. Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".

awesome-instruction-learning. Papers and Datasets on Instruction Tuning and Following. ✨✨✨

Awesome-Transformer-Attention. An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

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

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

GPT-4-LLM. Instruction Tuning with GPT-4

ddgs. A metasearch library that aggregates results from diverse web search services

chatgpt-retrieval-plugin. The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

Automated-Fact-Checking-Resources. Links to conference/journal publications in automated fact-checking (resources for the TACL22/EMNLP23 paper).

llama. Inference code for Llama models

FlexLLMGen. Running large language models on a single GPU for throughput-oriented scenarios.

uavm. Code for the IEEE Signal Processing Letters 2022 paper "UAVM: Towards Unifying Audio and Visual Models".

awesome-fairness-papers. Papers on fairness in NLP

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

adapters. A Unified Library for Parameter-Efficient and Modular Transfer Learning

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.

clevr-dataset-gen. A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning

Imppres. This repository houses the IMPlicature and PRESupposition diagnostic dataset (IMPPRES), consisting of >25k semiautomatically generated sentence pairs illustrating well-studied pragmatic inference types. IMPPRES is an NLI dataset following the format of SNLI (Bowman et al., 2015), MultiNLI (Williams et al., 2018) and XNLI (Conneau et al., 2018), which was created to determine how well trained NLI models do on recognizing several kinds of presuppositions and scalar implicatures.

CausalMediationAnalysis. Code for the paper "Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias"

aclpubcheck. Tools for checking ACL paper submissions

StereoSet. StereoSet: Measuring stereotypical bias in pretrained language models

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

pyprobml. Python code for "Probabilistic Machine learning" book by Kevin Murphy

HowToCook. Programmer's guide about how to cook at home.

Python-100-Days. Python - 100天从新手到大师

llm-beginner. LLM、Agent上手教程

language. Shared repository for open-sourced projects from the Google AI Language team.

search-tweets-python. Python client for the Twitter 'search Tweets' and 'count Tweets' endpoints (v2/Labs/premium/enterprise). Now supports Twitter API v2 /recent and /all search endpoints.

TAADpapers. Must-read Papers on Textual Adversarial Attack and Defense

Medical_DS. Python

jiant. jiant is an nlp toolkit

state-of-the-art-result-for-machine-learning-problems. This repository provides state of the art (SoTA) results for all machine learning problems. We do our best to keep this repository up to date. If you do find a problem's SoTA result is out of date or missing, please raise this as an issue or submit Google form (with this information: research paper name, dataset, metric, source code and year). We will fix it immediately.

graph-based-nn. Graph Convolutional Networks (GCNs)

MIT-6.824-2016. MIT 6.824 2016

ALSTM-cQA. Python

e2e-coref. End-to-end Neural Coreference Resolution

deep-coref. Python

NeuralDialogPapers. Summary of deep learning models for dialog systems (Tiancheng Zhao LTI, CMU)

guesswhat. GuessWhat?! Baselines

the-incredible-pytorch. The Incredible PyTorch: a curated list of tutorials, papers, projects, communities and more relating to PyTorch.

deeplearning-papernotes. Summaries and notes on Deep Learning research papers

ParlAI. A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

deep-reinforcement-learning-papers. A list of recent papers regarding deep reinforcement learning

awesome-public-datasets. A topic-centric list of HQ open datasets.

DeepRL-InformationExtraction. Code for the paper "Improving Information Extraction by Acquiring External Evidence with Reinforcement Learning" http://arxiv.org/abs/1603.07954

chatbot-retrieval. Dual LSTM Encoder for Dialog Response Generation

reinforcement-learning. Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

DeepQA. My tensorflow implementation of "A neural conversational model", a Deep learning based chatbot

deep-residual-networks. Deep Residual Learning for Image Recognition

kmeans. kmeans unsupervised pretraining from "Adam Coates and Andrew Y. Ng DEMYSTIFYING UNSUPERVISED FEATURE LEARNING"

TensorFlow-Examples. TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)

demos. Demos and tutorials around Torch7.

MITIE. MITIE: library and tools for information extraction