Starred repositories
A community-maintained Python framework for creating mathematical animations.
Official repository for the NeurIPS 2024 paper "SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition".
code and data for Paper: BIPro: Zero-shot Chinese Poem Generation via Block Inverse Prompting Constrained Generation Framework(ACL 2025 main)
Run native PE or .NET executables entirely in-memory. Build the loader as an .exe or .dll—DllMain is Cobalt Strike UDRL-compatible
《李宏毅深度学习教程》（李宏毅老师推荐👍，苹果书🍎），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
Framework for running AI locally on mobile devices and wearables. Hardware-aware C/C++ backend with wrappers for Flutter & React Native. Kotlin & Swift coming soon.
Efficient Part-level 3D Object Generation via Dual Volume Packing
Video-based AI memory library. Store millions of text chunks in MP4 files with lightning-fast semantic search. No database needed.
[Official Code] Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction
A flexible PE loader, loading module in memory. Most of the functions can be inline, compatible for shellcode.
ESP32-Powered eInk Panel for Cryptocurrency Updates and News
Global user-mode hooking framework, based on AppInit_DLLs. The goal is to allow you to rapidly develop hooks to inject in an arbitrary process.
PraisonAI is a production-ready Multi AI Agents framework, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. It provides a low-code soluti…
BillionMail gives you open-source MailServer, NewsLetter, Email Marketing — fully self-hosted, dev-friendly, and free from monthly fees. Join the discord: https://discord.gg/asfXzBUhZr
Fast mesh to 3D gaussian splat conversion
SU2: An Open-Source Suite for Multiphysics Simulation and Design
ICRA2025: OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding
SGTD: A Semantic-Guided Triangular Descriptor for One-Shot LiDAR-Based Global Localization
AI wearables. Put it on, speak, transcribe, automatically