This repository serves as a curated, up-to-date bibliography of research papers focused on time series analysis within AI venues. It targets researchers and practitioners in machine learning, data science, and related fields who need to stay abreast of the latest advancements in time series forecasting, anomaly detection, classification, and representation learning. The primary benefit is a centralized, easily searchable collection of relevant academic work.

How It Works

The repository functions as a manually curated list of papers, categorized by the AI conferences where they were published. It tracks major conferences such as NeurIPS, ICML, ICLR, KDD, AAAI, IJCAI, WSDM, CIKM, AISTATS, SDM, and ICASSP, spanning from 2021 to the present. The README includes a comprehensive list of paper titles, offering a snapshot of current research trends and methodologies.

Quick Start & Requirements

• Access: Browse the README file directly on GitHub.
• Requirements: No software installation is required. Access to academic papers may require institutional subscriptions or open-access availability.

Highlighted Details

• Comprehensive coverage of major AI conferences in time series research.
• Regularly updated with new publications.
• Provides a broad overview of emerging techniques and applications.
• Includes a substantial number of papers from 2023 and 2024, reflecting recent trends.

Maintenance & Community

• Maintained by xiyuanzh.
• Community interaction is primarily through GitHub issues and pull requests for suggestions or corrections.

Licensing & Compatibility

• License: Not explicitly stated in the README. Typically, such curated lists on GitHub are under permissive licenses like MIT or Apache 2.0, but this should be verified.
• Compatibility: Fully compatible with any system for browsing or referencing.

Limitations & Caveats

The repository is a bibliography and does not provide code, datasets, or direct access to the papers themselves. Users must independently locate and access the full research papers. The list is curated, so coverage might be subjective or incomplete for niche sub-fields.