Download
Meta-Learning-Papers is a curated bibliography focused specifically on meta-learning, learning-to-learn, one-shot learning, and few-shot learning, intended for researchers and practitioners interested in this rapidly evolving subfield of machine learning. It catalogs foundational “legacy” papers that introduced key concepts, as well as more recent work that extends meta-learning to new domains or architectures. The list spans topics such as gradient-based meta-learning, metric-based and relation-based methods, optimization-based approaches, and meta-reinforcement learning. By collecting these references in one place, the repository helps newcomers quickly get an overview of the intellectual history and main research directions in meta-learning. It is also useful for experienced researchers who need a convenient reference when writing surveys, proposals, or literature reviews.
Features
- Curated list of meta-learning, learning-to-learn, one-shot, and few-shot learning papers
- Includes early foundational work and more recent state-of-the-art methods
- Covers gradient-based, metric-based, optimization-based, and meta-RL approaches
- Serves as a literature map for students and researchers entering the field
- Useful as a reference when writing surveys, theses, or research proposals
- Simple text organization that is easy to browse and update
Project Samples
