This repository is a curated collection of resources on multimodal learning applications in medical imaging, focusing on papers related to Large Language Models (LLMs). It serves researchers and practitioners in medical AI, providing a structured overview of recent advancements, datasets, and methodologies in areas like medical report generation and visual question answering.

How It Works

The repository organizes research papers by application area (e.g., Medical Report Generation, Visual Question Answering, Medical Vision-Language Models) and includes links to PDFs and code where available. It highlights papers involving LLMs and provides a structured list of relevant datasets with their domains and sizes. Recent updates showcase new papers and accepted contributions to conferences.

Quick Start & Requirements

This is a curated list of research papers and datasets, not a software package. No installation or execution is required.

Highlighted Details

• Comprehensive lists of papers covering Medical Report Generation, Visual Question Answering, and Medical Vision-Language Models.
• Detailed tables of datasets for image-captioning and VQA tasks, including domain, size, and source.
• Recent news section highlights new paper releases and acceptances at major conferences (ICLR, NeurIPS, EMNLP).
• Includes citation information for key papers.

Maintenance & Community

The repository is actively maintained by richard-peng-xia, with recent updates in late 2024 and early 2025. Contributions are welcomed via pull requests or email.

Licensing & Compatibility

The repository itself does not have a specific license mentioned, but it links to external research papers which have their own publication licenses. Compatibility for commercial use would depend on the licenses of the linked papers and datasets.

Limitations & Caveats

This is a passive resource; it does not provide code for direct implementation or experimentation. The focus is on listing and categorizing existing research.