Repo đang lênCập nhật hằng ngày từ GitHub

Human Pose estimation with TensorFlow framework

ChirpStack open-source LoRaWAN Network Server

Neural question generation using transformers

Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA

Percona Monitoring and Management: an open source database monitoring, observability and management tool

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

Web-based interface for Claude CLI with streaming chat responses

NativeMind: Your fully private, open-source, on-device AI assistant

Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage computer.

A Unreal Engine 5 (UE5) based plugin aiming to provide real-time visulization, management, editing, and scalable hybrid rendering of Guassian Splatting model.

从 NLP 到 LLM 的算法全栈教程，在线阅读地址：https://datawhalechina.github.io/base-llm/

:computer: Learn to make machines learn so that you don't have to struggle to program them; The ultimate list

An application tool of edge-connect, which can do anime inpainting and drawing. 动漫人物图片自动修复，去马赛克，填补，去瑕疵

[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning

[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation

Video classification tools using 3D ResNet

A List of Data Science/Machine Learning Resources (Mostly Free)

Audio processing by using pytorch 1D convolution network

A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence. Built on HealthBench.

A desktop multi-agent harness built with Rust, Tauri, and React, powered by langgraph-rust.

Super Fast and Accurate 3D Object Detection based on 3D LiDAR Point Clouds (The PyTorch implementation)

Gemini Nexus 是一款面向浏览器场景的 AI 助手扩展，集成 Gemini Web、Gemini API 与 OpenAI 兼容接口，支持网页上下文、图像处理、工具调用和 MCP 浏览器控制。

🦓<->🦒 🌃<->🌆 A collection of image to image papers with code (constantly updating)

A lightweight header-only library for using Keras (TensorFlow) models in C++.

Change Python code while it's running without losing state

Schema-Guided Reasoning (SGR) has agentic system design created by neuraldeep community

Model Zoo For OpenCV DNN and Benchmarks.

Interact with OpenAI's ChatGPT via Telegram and Voice.

Android Camera that uses Enhanced image processing

Implementation of triplet loss in TensorFlow

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

Samples and Tools for Windows ML.

Math OCR model that outputs LaTeX and markdown

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model. 一个高质量多功能的图像修补模型，可以同时支持插入物体、移除物体、图像扩展、形状可控的物体生成，只需要一个模型

A 4-hour coding workshop to understand how LLMs are implemented and used

Give your coding agent the power to write and run agent evals.

Observe FastAPI app with three pillars of observability: Traces (Tempo), Metrics (Prometheus), Logs (Loki) on Grafana through OpenTelemetry.

Evaluate your LLM's response with Prometheus and GPT4 💯

UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery, ISPRS. Also, including other vision transformers and CNNs for satellite, aerial image and UAV image segmentation.

Multi-camera live traffic and object counting with YOLO v4, Deep SORT, and Flask.

The TypeScript framework for AI development

Notes for Fastai Deep Learning Course

PyCIL: A Python Toolbox for Class-Incremental Learning

SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.

Seamlessly extend any image in any direction with AI. Open-source web app powered by Gemini via OpenRouter, with Poisson-blended seams and best-of-3 variant picker.

Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros

My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.

EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

A PyTorch toolkit for 2D Human Pose Estimation.