Stars
Personal Website with Obsidian-like knowledge graph
EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.
GigaDatasets: A Unified and Lightweight Framework for Data Processing, Curation, and Visualization
HunyuanVideo-1.5: A leading lightweight video generation model
GigaTrain: An Efficient and Scalable Training Framework for AI Models
A powerful browser extension that saves, cleans, searches, and analyzes web pages with AI-powered archiving to PostgreSQL.
DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
正方教务系统自动抢课脚本：并发抢课、时间/教师筛选、换课、定时执行，内置图形界面。 | Auto course grabber with concurrent enrollment, filtering & scheduling.
Fat-Cat: A document-centric context management Agent. Making context as simple as reading chat history.
Synthetic Data Generation Platform By DataArcTech
High-Performance Perpetual Futures Exchange Matching Engine
Modular multi-agent orchestration framework powered by LangGraph and FastAPI.
Official code of Motus: A Unified Latent Action World Model
基于 AI 的个人成长轨迹分析系统，通过记录生活、回顾历史、分析模式帮助用户更好地理解自己，实现持续成长。包含智能路由、RAG 检索、自主任务智能体等功能。
MCPCAN is a centralized management platform for MCP services. It deploys each MCP service using a container deployment method. The platform supports container monitoring and MCP service token verif…
AI is changing the way how to launch cyberattack.
This project is the official implementation of "UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation"
Population-Based Training (PBT) for Reinforcement Learning using Message Passing Interface (MPI)
The Cross-Platform Deterministic Engine for Real-time Multiplayer Interactions.
Implementation of "YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception".
This is the official implementation for the paper "SNR-aware low-light image enhancement" in CVPR2022
Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured mem…
Code for Memory Consistency Guided Divide-and-Conquer Learning for Generalized Category Discovery
NEO Series: Native Vision-Language Models from First Principles