This project implements 30+ variants of ANN algorithms to find the K nearest neighbors in high-dimensional vector spaces. It is meant as a convenient sandbox: drop in your own ANN code, run a one-l…

毛泽东选集

The AI-native database built for LLM applications, providing incredibly fast hybrid search of dense vector, sparse vector, tensor (multi-vector), and full-text.

Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.

[SIGMOD'26] Dynamically Detect and Fix Hardness for Efficient Approximate Nearest Neighbor Search

A lightweight library for the RaBitQ algorithm and its applications in vector search.

Header-only C++/python library for fast approximate nearest neighbors

Math & CS awesome List, distinguished by proof and logic technique

个人构建MoE大模型：从预训练到DPO的完整实践

Official repository for 2025 TKDE survey paper "Deep Graph Anomaly Detection: A Survey and New Perspectives", including diverse types of resources for graph anomaly detection

A very simple GRPO implement for reproducing r1-like LLM thinking.

Boosting Accuracy and Efficiency for Vector Retrieval with Local Scaling Graph

Official implementation for "SimpleTM: A Simple Baseline For Multivariate Time Series Forcasting" (ICLR 2025)

[NeurIPS 2024 Spotlight] Official repository of the CycleNet paper: "CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns". This work is developed by the Lab of Professor …

Official repository for "TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data" (AAAI 2025).

[KDD 2025] DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting

[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"

A Fair and Scalable Time Series Forecasting Benchmark and Toolkit.

A Library for Advanced Deep Time Series Models.

Official implementation for the IJCAI'24 paper: SDformer

Source code for "Scalable Transformer for High Dimensional Multivariate Time Series Forecasting" (Accepted by CIKM-24)

[NeurIPS 2024 Spotlight] Official Code of the paper "Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting"

Official implement for "SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion"(NeurIPS'24) in PyTorch.

Differentiable convex optimization layers

Awesome Domain Adaptation Python Toolbox

Out-of-distribution detection, robustness, and generalization resources. The repository contains a curated list of papers, tutorials, books, videos, articles and open-source libraries etc

Python toolbox for optimization on Riemannian manifolds with support for automatic differentiation