-
University of Hong Kong
- Hong Kong
Stars
让 AI 住在你 MacBook 的刘海里 · 零依赖开箱即用 · 多引擎并行的桌面 AI 伴侣(Swift 6 / SwiftUI / macOS 14+)
Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics
The agent that grows with you
A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.
科研写作助手 (Research Writing Assistant)
A flexible and efficient codebase for training visually-conditioned language models (VLMs)
MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
AI Research Writing Skill (AI论文写作技能) is an agent skill for ML / AI / CV / NLP researchers. Point your coding agent at code, experiment logs, notes, and a venue template; it helps you produce an aud…
📷 [CVPR'26] Camera-controlled text-to-video generation, now with intrinsics, distortion and orientation control!
GPT-Image-2 API and Prompts
GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing
Skill package for ML/CV/NLP paper writing, curated and adapted from Prof. Peng Sida's open notes for Codex, Claude Code, and Gemini.
轻应用npm版本,降低接入难度,适配自定义UI,适配主流框架
[ICCV 2025] Implementation for Describe Anything: Detailed Localized Image and Video Captioning
torchange - A Unified Change Representation Learning Benchmark Library
[CVPR 2025] UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection
A lightweight, powerful framework for multi-agent workflows
Lightweight coding agent that runs in your terminal
Fast, small, and fully autonomous AI personal assistant infrastructure, any OS, any platform — deploy anywhere, swap anything 🦀
Official repo for "Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge" ICLR2025
Curated tutorials and resources for Large Language Models, Text2SQL, Text2DSL、Text2API、Text2Vis and more.
Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷