Research Code for MOMENT

Large Language & Foundation Models for Time Series.

A fast MoE impl for PyTorch

GraphAlign: Pretraining One Graph Neural Network on Multiple Graphs via Feature Alignment

欢迎来到 LLM-Dojo，这里是一个开源大模型学习场所，使用简洁且易阅读的代码构建模型训练框架(支持各种主流模型如Qwen、Llama、GLM等等)、RLHF框架(DPO/CPO/KTO/PPO)等各种功能。👩‍🎓👨‍🎓

Public repo for HF blog posts

Practical guidance for time series analysis in Python

A curated list of foundation models for vision and language tasks

Unified Training of Universal Time Series Forecasting Transformers

The collection of resources about LLM for Time series tasks

[WWW'22] Towards Unsupervised Deep Graph Structure Learning

A comprehensive benchmark of Graph Structure Learning (NeurIPS 2023 Datasets and Benchmarks Track)

A curated list of papers on graph structure learning (GSL).

Pytorch Lightning入门中文教程，转载请注明来源。（当初是写着玩的，建议看完MNIST这个例子再上手）

MOMENT: A Family of Open Time-series Foundation Models

This repository contains the code for our proposed method "Multi-source Feature Alignment and Label Rectification" (MFA-LR), which has been published in the paper "Learning a Robust Unified Domain …

PyTorch implementation of DANN (Domain-Adversarial Training of Neural Networks)

This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learna…

A Fair and Scalable Time Series Forecasting Benchmark and Toolkit.

Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.

[ICML 2024] A novel, efficient approach combining convolutional operations with adaptive spectral analysis as a foundation model for different time series tasks

GraphMAE: Self-Supervised Masked Graph Autoencoders in KDD'22

Official implementation of Evidential Uncertainty Quantification: A Variance-Based Perspective [WACV 2024]

[TPAMI 2024] The official implementation of "Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training"

tracking papers, datasets, and models of "large language model (LLM) for time series"