Code for our paper "VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters".

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

Fork - Minimal reproduction of DeepSeek R1-Zero

A simple and well styled PPO implementation. Based on my Medium series: https://medium.com/@eyyu/coding-ppo-from-scratch-with-pytorch-part-1-4-613dfc1b14c8.

🚀🀄️ A fast and strong AI for riichi mahjong, powered by Rust and deep reinforcement learning.

🔍🀄️ Review mahjong game log with mjai-compatible mahjong AI.

Unified Training of Universal Time Series Forecasting Transformers

The fork from PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730

Chronos: Pretrained (Language) Models for Probabilistic Time Series Forecasting

The fork from the official code for "One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight)"

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

A Library for Advanced Deep Time Series Models. And official implementation of "TimesNet"

This is a fork from: About Code release for "Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting" (NeurIPS 2021), https://arxiv.org/abs/2106.13008

✔️最全面的 深度学习CV 笔记【吴恩达 深度学习】【李沐 动手学深度学习】【我是土堆 Pytorch】

This is a fork from cure-lab/LSTF-Linear, which is the official implementation for "Are Transformers Effective for Time Series Forecasting?"

Fork from: Official implementation of our ICLR 2023 paper "Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting"

Fork from PyTorch code for ETSformer: Exponential Smoothing Transformers for Time-series Forecasting