# Multimodal AI for Gastrointestinal Diagnostics: Tackling VQA in MEDVQA-GI 2025

Source: [Multimodal AI for Gastrointestinal Diagnostics: Tackling VQA in MEDVQA-GI 2025](<https://www.sota2.com/research/paper/68fa7a141e209131cea80fea>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:57:50.406Z

Authors: Sujata Gaihre, Amir Thapa Magar, Prasuna Pokharel, Laxmi Tiwari

Published: 2025-07-19T09:04:13.000Z

## Abstract

This paper describes our approach to Subtask 1 of the ImageCLEFmed MEDVQA 2025 Challenge, which targets visual question answering (VQA) for gastrointestinal endoscopy. We adopt the Florence model-a large-scale multimodal foundation model-as the backbone of our VQA pipeline, pairing a powerful vision encoder with a text encoder to interpret endoscopic images and produce clinically relevant answers. To improve generalization, we apply domain-specific augmentations that preserve medical features while increasing training diversity. Experiments on the KASVIR dataset show that fine-tuning Florence yields accurate responses on the official challenge metrics. Our results highlight the potential of large multimodal models in medical VQA and provide a strong baseline for future work on explainability, robustness, and clinical integration. The code is publicly available at: https://github.com/TiwariLaxuu/VQA-Florence.git

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2507.14544>)

[PDF](<https://arxiv.org/pdf/2507.14544.pdf>)
