Repo đang lênCập nhật hằng ngày từ GitHub

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

整理目前开源的最优表格识别模型，完善前后处理，模型转换为ONNX | Organize the currently open-source optimal table recognition models, improve pre-processing and post-processing, and convert the models to ONNX.

AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.

Official implementation of Half-Quadratic Quantization (HQQ)

A collection of implementations of deep domain adaptation algorithms

PyTorch implementation of normalizing flow models

China's 1st enterprise multi-agent IT ops platform. LLM-powered auto-remediation for Zabbix/Prometheus. Docker deploy.

jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.

One-command installer for a self-hosted AI stack on your own server: n8n, Ollama, Open WebUI, OpenClaw, Dify, Flowise, Supabase, ComfyUI, Qdrant & 30+ tools. Docker Compose, automatic HTTPS via Caddy, built-in monitoring. Free Zapier/Make alternative.

Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI

The IM for agents. Shared Agent Context & Memory, supervised execution, and cross-agent audit across AI providers.

GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)

RAG-Fusion: multi-query generation + Reciprocal Rank Fusion for better retrieval-augmented generation. Includes evaluation harness with NFCorpus/BEIR.

Transparent Python RAG reference with FAISS + BM25 hybrid retrieval, reranking, Gradio UI, and FastAPI.

A multi-platform desktop application to evaluate and compare LLM models, written in Rust and React.

[ICLR 2026] A Training-free Iterative Framework for Long Story Visualization

go version of tiktoken

Code for 3D object detection for autonomous driving

Stable diffusion webui based on diffusers.

A Light CNN for Deep Face Representation with Noisy Labels, TIFS 2018

A general list of resources to image text localization and recognition 场景文本位置感知与识别的论文资源与实现合集 シーンテキストの位置認識と識別のための論文リソースの要約

Collection of recent methods on (deep) neural network compression and acceleration.

CatSniffer is an original multiprotocol and multiband board for sniffing, communicating, and attacking IoT (Internet of Things) devices using the latest radio IoT protocols. It is a highly portable USB stick that integrates TI CC1352, Semtech SX1262, and an RP2040 for V3 or a Microchip SAMD21E17 for V2

🚀A lightweight cloud-native multi-data source monitoring and alerting engine ｜一款轻量级云原生多数据源监控告警引擎

Self-paced bootcamp on Generative AI. Tutorials on ML fundamentals, Ollama, LLMs, RAGs, LangChain, LangGraph, Fine-tuning, DSPy & AI Agents (CrewAI), (Using ChatGPT, gpt-oss, Claude, Qwen, Gemma, Llama, Gemini)

A real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned

📚 Introduction to Modern Statistics - A college-level open-source textbook with a modern approach highlighting multivariable relationships and simulation-based inference.

A scalable inference server for models optimized with OpenVINO™

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

PyTorch implementation of Spatial Transformer Network (STN) with Thin Plate Spline (TPS)

Machine Learning Open Source University

Vector Quantized VAEs - PyTorch Implementation

Get Deinked!!

Ready to use implementations of various Deep Learning algorithms using TensorFlow.

Early POC of genetic neural architecture search

Bolt is a deep learning library with high performance and heterogeneous flexibility.

AI Agent 工程师面试资料库 - 国内大厂面经、岗位要求、高频面试题

[ICRA 2025 Best Paper] MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry

Promptr is a CLI tool that applies plain language instructions to the filesystem. Instructions can utilize a liquidjs based templating system. Use cases include refactoring, code generation, and experimentation.

PytorchAutoDrive: Segmentation models (ERFNet, ENet, DeepLab, FCN...) and Lane detection models (SCNN, RESA, LSTR, LaneATT, BézierLaneNet...) based on PyTorch with fast training, visualization, benchmarking & deployment help

This repository shares end-to-end notebooks on how to use various Weaviate features and integrations!

知更 — 本地 AI 的上下文与记忆层。Mac 上用语音输入、情境代回并调度 Codex / Claude Code；iOS 正在成为随身记忆终端和本地 Agent 遥控器。Local-first · BYOK.

精选了10K+项目，包括机器学习、深度学习、NLP、GNN、推荐系统、生物医药、机器视觉、前后端开发等内容。Selected more than 10k+ projects, including machine learning, deep learning, NLP, GNN, recommendation system, biomedicine, machine vision, etc. Let more excellent projects be discovered by people. Continue to update! Welcome to star!

TextBoxes++: A Single-Shot Oriented Scene Text Detector

List of Molecular and Material design using Generative AI and Deep Learning

official code repo for paper "CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers"

Fork of tess-two rewritten from scratch to support latest version of Tesseract OCR.

A-Paper-A-Week

Real-world AI penetration testing engineer for authorized assessments — built-in cloud module covering AWS/Azure/GCP + Aliyun/Tencent/Huawei clouds. Built on Claude Agent SDK

ONNX Model Exporter for PaddlePaddle