Stars
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
Witness the aha moment of VLM with less than $3.
🐙 关于提示词工程（prompt）的指南、论文、讲座、笔记本和资源大全（自动持续更新）
综合多种调度算法得到分布式深度学习多作业在 GPU 集群上的调度次序以及资源分配方案
vHeat: Building Vision Models upon Heat Conduction
Training and Inference Characteristics Performance Prediction Model
About code release of "Interpretable Weather Forecasting for Worldwide Stations with a Unified Deep Model", Nature Machine Intelligence, 2023. https://www.nature.com/articles/s42256-023-00667-9
Time Series Contrastive Learning with Information-Aware Augmentations (Code)
Official code for "The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting", TKDE 2024
[CVPR'23 & TPAMI'25] Hard Patches Mining for Masked Image Modeling & Bootstrap Masked Visual Modeling via Hard Patch Mining
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
实现向 ChatGPT 自动提问的脚本。A script that implements automatic questions to ChatGPT.
This repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (STF). These papers are mainly categorized according to the …
A Library for Advanced Deep Time Series Models for General Time Series Analysis.
[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"
OpenMMLab Pre-training Toolbox and Benchmark
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复
关于提示工程的技术文章汇总和翻译
Prompt工程师指南，源自英文版，但增加了AIGC的prompt部分，为了降低同学们的学习门槛，翻译更新
Critical difference diagram with Wilcoxon-Holm post-hoc analysis.
Self-supervised contrastive learning for time series via time-frequency consistency
General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.