This repository serves as a comprehensive, curated collection of resources for researchers and practitioners in Machine Learning for Software Engineering (ML4SE). It aggregates papers, theses, datasets, and tools, organized by sub-fields like type inference, code completion, and vulnerability detection, aiming to provide a centralized hub for state-of-the-art knowledge and tools in this rapidly evolving domain.

How It Works

The repository functions as a living bibliography, meticulously listing academic publications, research projects, and relevant software tools. It categorizes these resources by specific ML4SE tasks, allowing users to quickly navigate and discover relevant work. The curation process emphasizes recent advancements and widely recognized contributions, facilitating efficient exploration of the ML4SE landscape.

Quick Start & Requirements

This repository is a curated list and does not require installation or execution. It serves as a reference guide.

Highlighted Details

• Extensive coverage of ML applications across numerous software engineering tasks, including type inference, code completion, generation, summarization, vulnerability detection, and program repair.
• Detailed listings include paper titles, venues, publication years, and direct links to PDFs and associated code repositories where available.
• Includes a dedicated section for PhD theses, talks, datasets, and tools, offering a holistic view of the ML4SE ecosystem.
• Resources are regularly updated, reflecting the latest research trends and tools in the field.

Maintenance & Community

The repository is maintained by the Software Engineering Research Group at Delft University of Technology, with contributions encouraged via pull requests. It links to relevant research groups and academic venues.

Licensing & Compatibility

The repository itself is licensed under a permissive license (likely MIT or similar, though not explicitly stated for the repo itself), allowing broad use and contribution. Individual resources (papers, code) are subject to their respective licenses.

Limitations & Caveats

As a curated list, the repository's depth and breadth are dependent on community contributions and maintainer efforts. While comprehensive, it may not capture every single relevant publication or tool.