WRF-LBM coupling toolkit for extremely-high resolution urban wind simulation with buildings.

An efficient goal-conditioned reinforcement learning environment for fixed-wing UAV velocity vector control based on Gymnasium (ICLR2025).

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

RLGF is a general training framework suitable for UAV deep reinforcement learning tasks. And integrates multiple mainstream deep reinforcement learning algorithms(SAC, DQN, DDQN, PPO, Dueling DQN, …

This respository contains the codes for routing for UAV

3D Trajectory Planner in Unknown Environments

Multi/Single UAV(unmanned aerial vehicle) path planning based on deep reinforcement learning

强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

Master programming by recreating your favorite technologies from scratch.

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

Code for: "Long-Context Autoregressive Video Modeling with Next-Frame Prediction"

A cascade machine learning forecasting system for 15-day global weather forecast

A Library for Advanced Deep Time Series Models for General Time Series Analysis.

Nano vLLM

股票行情实时数据接口-A股,完全免费的沪深证券股票数据-中国股市,python最简封装的API接口,包含日线,历史K线,分时线,分钟线,全部实时采集，系统包括新浪腾讯双数据核心采集获取，自动故障切换，STOCK数据格式成DataFrame格式,可用来查询研究量化分析，股票程序自动化交易系统.为量化研究者在数据获取方面极大地减轻工作量，更加专注于策略和模型的研究与实现。

TradingAgents: Multi-Agents LLM Financial Trading Framework

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024)

A Python toolkit/library for reality-centric machine/deep learning and data mining on partially-observed time series, including SOTA neural network models for scientific analysis tasks of imputatio…

Hackable and optimized Transformers building blocks, supporting a composable construction.

Fast and memory-efficient exact attention

Pixel-Space Generative Models

Code for our NeurIPS 2019 paper "Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models"

Official Code for a KDD 2025 paper "Physics-Guided Learning of Meteorological Dynamics for Weather Downscaling and Forecasting"

An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730

MTS-Mixers: Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing

Weather Generator from Cornell

Open-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods

An open source weather APP for Android. 天气普拉斯Android版，自带天气数据的开源天气APP。

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.