ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model

MOMENT: A Family of Open Time-series Foundation Models

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

Unified Training of Universal Time Series Forecasting Transformers

ProbTS is a benchmarking toolkit for time series forecasting.

Codes for "Retrieval-Augmented Diffusion Models for Time Series Forecasting"

[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"

The GitHub repository for the paper "Informer" accepted by AAAI 2021.

A PyTorch implementation of the Transformer model in "Attention is All You Need".

《机器学习》（西瓜书）公式详解

Translate PDF, EPub, webpage, metadata, annotations, notes to the target language. Support 20+ translate services.

李宏毅2021/2022/2023春季机器学习课程课件及作业

Deep Learning Specialization by Andrew Ng on Coursera.

Official codebase for the Paper “Retrieval-Augmented Diffusion Models”

A latent text-to-image diffusion model

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Raw data and processing scripts of Weather Captioned Dataset in TGTSF

Additional exercises and data for EE364a. No solutions; for public consumption.

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Official code, datasets and checkpoints for "Timer: Generative Pre-trained Transformers Are Large Time Series Models" (ICML 2024)

A unified multi-task time series model.

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

Chronos: Pretrained Models for Probabilistic Time Series Forecasting

Awesome Learn From Model Beyond Fine-Tuning: A Survey

A Library for Advanced Deep Time Series Models.