Starred repositories
"Vibe-Trading: Your Personal Trading Agent"
A comprehensive list of awesome document image rectification papers.
The official code for “Deep Unrestricted Document Image Rectification”, TMM, 2023.
The official code for “DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction”, ACM MM, Oral Paper, 2021.
18 Lessons to Get Started Building AI Agents
Central Difference Convolutional Networks (CVPR'20)
mobilenetv3 with pytorch，provide pre-train model
RetinaFace: Deep Face Detection Library for Python
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
SeetaFace 2: open source, full stack face recognization toolkit.
[CVPR2026] Detect Anything via Next Point Prediction
[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero
Generic automation framework for acceptance testing and RPA
Deep neural network to extract intelligent information from invoice documents.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without …
FinGLM: 致力于构建一个开放的、公益的、持久的金融大模型项目，利用开源开放来促进「AI+金融」。
FinQwen: 致力于构建一个开放、稳定、高质量的金融大模型项目，基于大模型搭建金融场景智能问答系统，利用开源开放来促进「AI+金融」。
Integrate cutting-edge LLM technology quickly and easily into your apps
Cambrian-1 is a family of multimodal LLMs with a vision-centric design.