# Multi-Task Learning for Visually Grounded Reasoning in Gastrointestinal VQA

Source: [Multi-Task Learning for Visually Grounded Reasoning in Gastrointestinal VQA](<https://www.sota2.com/research/paper/690d7cec2828b7cc6937cc32>)

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

Data updated: 2025-11-08T05:01:25.623Z

Authors: Itbaan Safwan, Muhammad Annas Shaikh, Muhammad Haaris, Ramail Khan, Muhammad Atif Tahir

Published: 2025-11-06T14:09:56.000Z

## Abstract

We present a multi-task framework for the MediaEval Medico 2025 challenge, leveraging a LoRA-tuned Florence-2 model for simultaneous visual question answering (VQA), explanation generation, and visual grounding. The proposed system integrates three curated datasets: (1) Kvasir-VQA-x1 for question-answer learning, (2) a synthetically enriched explanation dataset offering structured medical reasoning, and (3) text-to-region pairs linking visual features with segmentation masks. This multi-task setup enables the model to jointly learn visual grounding, reasoning, and interpretation, producing responses that are both accurate and interpretable. Extensive evaluation demonstrates that our approach substantially improves over single-task baselines in both answer accuracy and visual localization, highlighting the effectiveness of grounded multi-task learning for medical VQA applications.

## 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/2511.04384>)

[PDF](<https://arxiv.org/pdf/2511.04384.pdf>)
