gastrointestinal endoscopy 1model grounding 1multitask learning 1vision-language models 1visual question answering 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CV2026
Towards Grounded GI Endoscopy VQA via Multi-Task Learning on Small VLMs
Itbaan Safwan, Ramail Khan, Muhammad Annas Shaikh +1
The paper introduces a multi‑task fine‑tuning approach for small vision‑language models to improve visual question answering on GI endoscopy images, adding grounding and descriptio…
cs.CV2025
Multi-Task Learning for Visually Grounded Reasoning in Gastrointestinal VQA
Itbaan Safwan, Muhammad Annas Shaikh, Muhammad Haaris +2
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 ge…