A toolkit enhances PyTorch with specialized functions for low-bit quantized neural networks.

Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Diffusion Transformer Networks

A curated list of resources on graph-based retrieval-augmented generation (GraphRAG) for customized large language models.

A curated list of papers, code and resources pertaining to image composition/compositing or object insertion/addition/compositing, which aims to generate realistic composite image.

A React-based virtual avatar component for real-time gameplay analysis and emotional support. Integrate with screen capture to provide insights and companionship through advanced LLM integration.

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

Open-sourced, Fast and Context-aware Action Grounding from GUI Instructions for GUI/Computer-use Agents

Manuscript is a revolutionary blockchain data streaming framework. With Manuscript, you can seamlessly integrate on-chain and off-chain data into target data storage for unrestricted querying and a…

🔥 Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Align Anything: Training All-modality Model with Feedback

高颜值AI数字人克隆、声音克隆、短视频生成、直播（待发布）、AI配音、AI字幕，包括Windows安装版，Web版，H5版，小程序版，副业必备，开源数字人克隆平台后端API

Kun-peng: an ultra-fast, low-memory footprint and accurate taxonomy classifier for all

A python package that integrate algorithms and various machine learning approaches to extract features (genes) effective for classification and attribute them accordingly.

Unlimited Updates, Boundless Upgrades.

The code for "VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM"

渗透测试C2、支持Lua插件扩展、域前置/CDN上线、自定义profile、前置sRDI、文件管理、进程管理、内存加载、截图、反向代理、分组管理

Official code base for paper EZIGen: Enhancing zero-shot personalized image generation with precise subject encoding and decoupled guidance

modContact是一款专门为嵌入式平台开发的通用串口交互平台框架，它广泛的支持任何形如(request<->response)的主从机交互协议，且内置优雅的主从机切换机制和稳定可靠的多帧识别，沾帧切割，沾帧解析机制。

Official Implementation of "Phishpedia: A Hybrid Deep Learning Based Approach to Visually Identify Phishing Webpages" USENIX'21

Kafka Dog is a lightweight desktop application for visualizing and managing Apache Kafka. It provides a user-friendly graphical interface for managing and monitoring Kafka clusters. | Kafka Dog 是一款…

Highly encapsulated for effortless usage, this state machine kernel is realized with just a single function call!

"GraphAgent: Agentic Graph Language Assistant"

We present StableAnimator, the first end-to-end ID-preserving video diffusion framework, which synthesizes high-quality videos without any post-processing, conditioned on a reference image and a se…

A highly optimized LLM inference acceleration engine for Llama and its variants.

该Agent是一个基于eBPF技术的容器异常检测框架，旨在通过收集容器的行为特征和指标特征，利用人工智能算法自动识别具有异常行为的容器。

Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition