Lingrui Mei

🔥 Comprehensive survey on Context Engineering: from prompt engineering to production-grade AI systems. hundreds of papers, frameworks, and implementation guides for LLMs and AI agents.

Train computer-use agents end-to-end on real desktops, at scale: a high-performance runtime where 8K+ live environments on one laptop thread.

No description.

Training library for Megatron-based models with bidirectional Hugging Face conversion capability

No description.

A real-time classifier demo using Core ML and pre-trained Resnet50 model on iOS 11.

[EMNLP 2024 Main] Official repository of paper "SLANG: New Concept Comprehension of Large Language Models"

[COLING 2025] Official repo of paper: "Not Aligned" is Not "Malicious": Being Careful about Hallucinations of Large Language Models' Jailbreak

Bypass iOS PIN Passcode

Coordination for concurrent autonomous AI agents over shared mutable state: advisory write leases + a witnessed audit trail, over MCP. First proving ground: AI coding agents sharing a repo. Servant, not ruler.

Official repository of paper "HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router"

LLM hidden states extractor and injector.

No description.

No description.

DLND project: Face generation by deep convolutional generative adversarial network.

verl: Volcano Engine Reinforcement Learning for LLMs

No description.

Deep Convolutional Generative Adversarial Network for Street View House Numbers dataset.

No description.

An unfinished iOS Method Swizzling demo

Training and Building Realtime Classifier with Keras

Classify Traffic Signs.

A library that enables dynamically rebinding symbols in Mach-O binaries running on iOS.

runtime function overriding for Mac OS X

From Automated Idea Factory to Realization

A unified framework for building, running, and training general agents at scale.

Bridge Megatron-Core to Hugging Face/Reinforcement Learning

Ongoing research training transformer models at scale

Worked examples of integrating agents and datasets with Agentix

Agentix's host-side bridge from agent rollouts to RL training

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

A skill for Claude Code and Codex CLI that teaches them to talk to each other.

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

Low Level Skeleton Library for IO Communication on GNU/Linux platforms

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

No description.

The official implementation of the paper "AgentSquare: Automatic LLM Agent Search in Modular Design Space""

No description.

No description.

No description.

A simple, retro theme for Hugo

Recommend new arxiv papers of your interest daily according to your Zotero libarary.

Gödel Agent: A Self-Referential Agent Framework for Recursive Self-Improvement

Automated Design of Agentic Systems

Official page of paper "Decoding by Contrasting Knowledge: Enhancing LLMs’ Confidence on Edited Facts"

No description.

A rule-based tunnel in Go.

Backup clash premium nightly and release

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

No description.

Deploy twikoo to Netlify

No description.

No description.

Identify email addresses or domains names that belong to colleges or universities. Help automate the process of approving or rejecting academic discounts.

No description.

Reusable apps code. Written in Swift

Models and examples built with TensorFlow

Cascaded U-O Net (CVPR 2019 Submission)

No description.

No description.

Portrait mode on webcam.

Convolutional Variational Autoencoder

No description.

Udacity CarND Term 1 Project 5

These formulae provide software tailored to endeavours of computer vision and deep learning.

What would you do when you haven't use C++ for about 20 months.

No description.

Udaicty CarND Project 4

Udaicty CarND Project 4

A component for Apache Isis' Wicket Viewer that render entities (implementing CalendarEvent) within a calendar.

Udacity CarND Behavioral Cloning Project

Generative Adversarial Network for MNIST dataset.

Convolutional Autoencoder for MNIST Denoising

DO NOT CLONE OR FORK THIS

No description.

Implement the LeNet deep neural network model with TensorFlow.

Lane Finding Project for Self-Driving Car ND

https://cn.udacity.com/course/deep-learning-nanodegree-foundation--nd101/

No description.

Introduction to Parallel Programming class code

This is an LSTM stock prediction using Tensorflow with Keras on top.

Port of Single Shot MultiBox Detector to Keras

No description.

Udacity DLND sentiment_network

Udacity DLND P1

Repo for the Deep Learning Nanodegree Foundations program.

No description.

No description.

Starter project code for students taking Udacity ud120

No description.

My VIM configuration(.vimrc)

A collection of tools used for supporting TKG (TMK Keymap Generator).

A street traffic simulation example project for MPI-based parallel computing in Python.

various tweaks for witcher 3

Based on a true story

网传附莆田系医院名单，欢迎更新

Torch implementation of neural style algorithm

A bloom filters implementation in ruby

Ruby Tree Example

2015-2016学年度上期大学计算机基础大作业第一题

A port of https://github.com/panicinc/ColorArt to support running on IOS

The most popular HTML, CSS, and JavaScript framework for developing responsive, mobile first projects on the web.

Regression testing app for Apache Isis.

Apache Isis™ software is a framework for rapidly developing domain-driven apps in Java. Write your business logic in entities, domain services or view models, and the framework dynamically generates a representation of that domain model as a webapp or as a RESTful API. For prototyping or production.

A human detector based on Intel Edison

Invenio source code overlay for CERN Open Data Portal

libs and code

Real-time face detection using OpenCV, Node.js, and WebSockets

A machinical net novel writer

datasciencecoursera

The Leek group guide to data sharing

No description.

Demo for "iOS Method Swizzling Demo"

No description.

I'm taking a break, I swear

No description.

No description.

No description.