Multi-agent system for research, powered by ag2

Modular Multi-Agent System for Scientific Research Assistance

Official code for: Conformal prediction interval for dynamic time-series (conference, ICML 21 Long Presentation) AND Conformal prediction for time-series (journal, IEEE TPAMI)

KDD 2019: Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network

PyTorch implementation of MTAD-GAT (Multivariate Time-Series Anomaly Detection via Graph Attention Networks) by Zhao et. al (2020, https://arxiv.org/abs/2009.02040).

LoCoMotif is a time series motif discovery method that discovers variable-length motif sets in multivariate time series using time warping

pip install antialiased-cnns to improve stability and accuracy

Accompanying code for the paper "MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning"

Official code for the paper "PNI : Industrial Anomaly Detection using Position and Neighborhood Information"

Paper list and datasets for industrial image anomaly/defect detection (updating). 工业异常/瑕疵检测论文及数据集检索库(持续更新)。

Implementation of our paper "Optimizing PatchCore for Few/many-shot Anomaly Detection"

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

Toolbox for histopathology image analysis

Result of DigiLut Data Challenge

SPARQL graph database

Code for the paper "H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition" (NeurIPS 2025)

Minimalistic implementation for LLM-based chat assistants with Tool Use (function calling) and MCP

🚀 The fast, Pythonic way to build MCP servers and clients

Multimodal Integration with Modality-agnostic Autoencoders - Developed by LMIB @ KU Leuven

Lightweight Python implementation of SHAP

Data Engineering Zoomcamp is a free 9-week course on building production-ready data pipelines. The next cohort starts in January 2026. Join the course here 👇🏼

Code for the "Build Your Own Search Engine" workshop

Minimalistic text search engine that uses sklearn and pandas

Official implementation of the paper "FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective"

Code for AI Bootcamp from RAG to Agents

Code release for CVPR'24 submission 'OmniGlue'

A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.

Representation learning-based graph alignment based on implicit matrix factorization and structural embeddings