This repository serves as a comprehensive reading list and syllabus for an Advanced Machine Learning course at KAIST. It targets graduate students and researchers interested in cutting-edge deep learning topics, providing a structured curriculum and extensive references for self-study or course implementation.

How It Works

The repository outlines a hybrid on/offline course structure with a tentative schedule covering key areas of advanced ML. Topics include Vision Transformers, Self-Supervised Learning, Bayesian Deep Learning, Deep Generative Models (GANs, Diffusion Models), Deep Reinforcement Learning, Meta-Learning, Continual Learning, Interpretable DL, Reliable DL, Robust DL, Graph Neural Networks, Federated Learning, Neural Architecture Search, Large Language Models, and Multimodal Generative Models. Each topic is accompanied by a curated list of seminal and recent research papers.

Quick Start & Requirements

This repository is a collection of academic papers and a course syllabus. There are no direct installation or execution commands. The primary requirement is access to academic literature and a foundational understanding of machine learning concepts.

Highlighted Details

• Extensive reading lists for 18 distinct advanced ML topics, featuring seminal and recent papers.
• A detailed, week-by-week course schedule with topics and presentation assignments.
• Grading policy breakdown: Paper Presentation (20%), Attendance/Participation (20%), Project (60%).
• Covers a broad spectrum of modern deep learning research, from foundational concepts to state-of-the-art models.

Maintenance & Community

The repository is maintained by Sung Ju Hwang (sjhwang82@kaist.ac.kr) with TAs Seul Lee and Jaehyeong Jo. Information on community interaction channels (e.g., Discord, Slack) or a public roadmap is not provided in the README.

Licensing & Compatibility

The repository itself does not appear to have an explicit license mentioned in the README. It is a collection of links to academic papers, which are subject to their respective publisher licenses.

Limitations & Caveats

This repository is purely an informational resource and syllabus; it does not contain code implementations or executable examples. The content is academic and assumes a strong prerequisite knowledge of machine learning.