Introduction to the Workshop

In recent years, the intersection of computer vision (CV) and natural language processing (NLP) has led to significant advancements in the biomedical domain, particularly through the development of Vision-Language Models (VLMs). These models integrate visual and textual data, essential for interpreting complex multimodal information such as clinical reports with diagnostic imaging or textual descriptions with biological experiments. VLMs enhance various biomedical applications by enabling medical image analysis, clinical note interpretation, and the extraction of information from scientific literature, thus facilitating decision-making in diagnosis, treatment, and drug discovery. The capabilities of VLMs extend to generating textual information, facilitating text-to-image generation, and synthetic data creation, which opens new avenues for knowledge discovery and personalized medicine. Recent advances in self-supervised learning and large vision language models (LVLMs) further underscore the potential of semantic alignment between imaging and text. However, despite these advancements, most research has still focused on unimodal text. 

The First International Workshop on Vision-Language Models for Biomedical Applications (VLM4Bio 2024), part of the ACM Multimedia (ACM MM) conference 2024, aims to address these gaps by fostering interdisciplinary dialogue among NLP, machine learning, CV, and biomedical experts, thus accelerating multimodal biomedical AI research and developing innovative healthcare solutions.

 WORKSHOP CHAIRS

Call for Papers

⦿ VLM4Bio: Biomedical image understanding and captioning using VLMs.

⦿ VLM4Bio: Visual Question Answering (VQA) in biomedical applications.

⦿ VLM4Bio: Integration of multimodal biomedical data for enhanced decision support systems.

⦿  VLM4Bio: Applications of VLMs in medical imaging, pathology, radiology, and histology.

⦿ VLM4Bio: Approaches based on VLM for drug discovery, pharmacogenomics, and personalized medicine.

⦿ VLM4Bio: VLM-based approaches for biological imaging including cells and transcriptomics.

⦿ VLM4Bio: Clinical applications of VLMs in disease diagnosis, prognosis, and treatment planning.

⦿ VLM4Bio: Benchmark datasets, evaluation metrics, and reproducibility challenges in VLM research for biomedicine.

⦿ VLM4Bio: Development, scalability, and optimization of VLM architectures for biomedical data analysis.

⦿ VLM4Bio: Case studies, real-world applications, and considerations for the deployment of VLMs in healthcare settings.

⦿ VLM4Bio: Ethical considerations, bias mitigation, and interpretability in VLMs for biomedical applications.

Submission Guidelines

The proceedings of the workshops will be published in the ACM digital library linked with ACM Multimedia and workshop. Workshop papers should not have been previously published, should not be considered for publication, and should not be under review for another workshop, conference, or journal. 

The manuscript’s length is limited to one of the two options: a) 4 pages plus 1-page reference; or b) 8 pages plus up to 2-page reference.

Papers must be submitted in PDF according to the ACM format published in the ACM guidelines, selecting the generic “sigconf” sample. The PDF files must have all non-standard fonts embedded. Workshop papers must be self-contained and in English. 

Overleaf format: https://www.overleaf.com/latex/templates/association-for-computing-machinery-acm-sig-proceedings-template/bmvfhcdnxfty (sigconf should be used).

Note: Submissions are double-blind.

IMPORTANT: All authors need to have openreview profile. We would like to make authors aware of OpenReview's moderation policy for newly created profiles:

• New profiles created without an institutional email will go through a moderation process that can take up to two weeks.

• New profiles created with an institutional email will be activated automatically.

• Submissions are double blind.