Construction 相关的热门 GitHub AI项目仓库

《ICLR 2023 Spotlight & IJCV 2024》MapTR：面向在线矢量化高清地图构建的结构化建模与学习

关于使用大型语言模型 (LLM) 进行生成式信息提取 (IE) 的优秀论文

This repository contains the implementation of AutoSchemaKG, a novel framework for automatic knowledge graph construction that combines schema generation via conceptualization.

大型语言模型在知识图谱构建和推理中的应用：最新进展与未来机遇（WWWJ 2024）

利用YOLO目标检测技术提升建筑工地安全，识别工人未戴安全帽或安全背心、以及靠近机械或车辆等危险情况。HDBSCAN算法对安全锥坐标进行聚类，创建监控区域。后期处理算法进一步提高检测精度。

C2S Agent is an lightweight AI Agent construction platform that provides configurable online Agents and MCP services, You can configure any HTTP request interface as an MCP tool. C2S Agent 是一个轻量级的AI Agent构建平台，提供在线可配置的Agent，MCP，您可以一个HTTP请求的接口配置成为一个MCP工具，Agent之间可以进行自交流。并提供了单端口多A2A服务，MCP服务的解决方案

基于YOLOv8的建筑工地工人PPE（个人防护装备）检测的自定义目标检测。此仓库包含使用YOLOv8进行PPE检测的笔记本（代码示例）。

qKnow is an open-source knowledge platform built around Knowledge Graphs, offering capabilities for knowledge extraction, knowledge fusion, graph construction, and visualization. It helps enterprises and organizations build structured, queryable, and inferable knowledge systems.

这是[ECCV 2024]论文 HRMapNet 的官方实现，该方法维护并利用低成本的全局栅格地图来增强在线矢量地图的感知能力。

这个GitHub项目旨在识别建筑工地工人不安全的动作。

基于BAML和Kuzu的知识图谱构建和图关系增强学习(Graph RAG)演示

Open-source toolkit to extract structured knowledge graphs from documents and tables — power analytics, digital twins, and AI-driven assistants.

EMNLP 2023论文《Dynosaur：一种用于指令微调数据整理的动态增长范式》的代码和数据

A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical guides on defining and collecting rewards to build more intelligent and aligned AI agents.

This repository provides the companion Jupyter Notebooks for the book Context-Engineering for Multi-Agent Systems. It technically details the progressive construction of a Context Engine moving from simple prompts to foundational concepts to a production-ready system semantic blueprint. The code is a guide to building Multi-Agent Systems (MAS)

A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical guides on defining and collecting rewards to build more intelligent and aligned AI agents.

libLLVM brings the full power of LLVM's compilation infrastructure directly to Delphi, providing native bindings for code generation, optimization, and linking with clean, Pascal-style integration.

一个基于Python的框架，用于从非结构化文本中自动化构建领域无关和领域相关的知识图谱。它整合了自然语言处理 (NLP) 和 Neo4j，用于实体提取、关系映射和语义增强。非常适合文本挖掘和分析，并支持时间和事件标注。

[EMNLP'25 main] This is the official repo for the paper, Can LLMs be Good Graph Judge for Knowledge Graph Construction?

图表示学习中基准测试的分类