FGVCLib is an open-source and well documented library for Fine-grained Visual Classification.

UniTable: Towards a Unified Table Foundation Model

The official GitHub page for the survey paper "A Survey of Large Language Models".

Ultralytics YOLO11 🚀

A collection of original, innovative ideas and algorithms towards Advanced Literate Machinery. This project is maintained by the OCR Team in the Language Technology Lab, Tongyi Lab, Alibaba Group.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

OCR, layout analysis, reading order, table recognition in 90+ languages

Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.

Retrieval and Retrieval-augmented LLMs

MTL-TabNet: Multi-task Learning based Model for Image-based Table Recognition

企业微信/微信 安全使用的 ChatGPT 个人助手应用

🧩 Lobe Chat Plugin SDK - The LobeChat Plugin SDK assists you in creating exceptional chat plugins for Lobe Chat.

AI模型接口管理与分发系统，支持将多种大模型转为OpenAI格式调用、支持Midjourney Proxy、Suno、Rerank，兼容易支付协议，可供个人或者企业内部管理与分发渠道使用，本项目基于One API二次开发。🍥 The next-generation LLM gateway and AI asset management system supports multiple lan…

Implementation of Nougat Neural Optical Understanding for Academic Documents

🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Qwen / DeepSeek), Knowledge Base (file upload / knowledge managemen…

OpenAI 接口管理 & 分发系统，支持 Azure、Anthropic Claude、Google PaLM 2 & Gemini、智谱 ChatGLM、百度文心一言、讯飞星火认知、阿里通义千问、360 智脑以及腾讯混元，可用于二次分发管理 key，仅单可执行文件，已打包好 Docker 镜像，一键部署，开箱即用. OpenAI key management & redistributi…

A Sequence Generation Model for Reaction Diagram Parsing

Efficient vision foundation models for high-resolution generation and perception.

Robust Molecular Structure Recognition with Image-to-Graph Generation

Project : K-MolOCR, detection code for recognizing the Molecular structure in the text PDF

✨ Local and Fast AI Assistant. Support: Web | iOS | MacOS | Android | Linux | Windows

🎒 Feishu-EX-ChatGPT 并通过注册机制来激活飞书机器人的插件生态，现已支持联网，生图，公式计算

🎒 飞书 ×（GPT-4 + GPT-4V + DALL·E-3 + Whisper）= 飞一般的工作体验 🚀 语音对话、角色扮演、多话题讨论、图片创作、表格分析、文档导出 🚀

NumPy aware dynamic Python compiler using LLVM

Oscillators synchroniztion model with fortran

专注于解决推荐领域与搜索领域的两个核心问题:排序预测(Ranking)和评分预测(Rating). 为相关领域的研发人员提供完整的通用设计与参考实现. 涵盖了70多种排序预测与评分预测算法,是最快最全的Java推荐与搜索引擎.

目标是提供一个通用的Java核心编程框架,作为搭建其它框架或者项目的基础. 让相关领域的研发人员能够专注高层设计而不用关注底层实现. 涵盖了缓存,编解码,通讯,事件,输入/输出,监控,存储,配置,脚本和事务10个方面.

Spark 学习之路，包含 Spark Core，Spark SQL，Spark Streaming，Spark mllib 学习笔记