SubmissionNumber#=%=#36 FinalPaperTitle#=%=#LAMAR-2 at MedGenVidQA 2026: Visual Answer Localization in Medical Videos via Multimodal LLM and Context-Augmented Prompting ShortPaperTitle#=%=# NumberOfPages#=%=# CopyrightSigned#=%=# JobTitle#==# Organization#==# Abstract#==#This paper presents an approach to localizing visual answers within continuous medical videos using a multi-step multimodal generation pipeline with the MedGenVidQA dataset. We frame visual answer localization as a multimodal fusion problem, integrating raw video, timestamped ASR transcripts, and VLM-generated scene descriptions into structured contextual blocks, enabling the model to cross-reference spoken commentary against observable physical events. We show that targeted guidance, which forces the model to treat audio transcripts as supplementary hints with observable visual movements, significantly outperforms baseline approaches. It achieves state-of-the-art performance on the test leaderboard, yielding an mIoU of 79.55, alongside IoU@0.3, IoU@0.5, and IoU@0.7 scores of 93.75, 90.00, and 77.50, respectively. Our findings highlight the effectiveness of combining multimodal context fusion with targeted guidance to overcome text bias, establishing a promising approach for achieving the micro-level precision required in the medical domain. Author{1}{Firstname}#=%=#Watcharitpol Author{1}{Lastname}#=%=#Sermsrisuwan Author{1}{Username}#=%=#watcharitpol Author{1}{Orcid}#=%=# Author{1}{Email}#=%=#watcharitpol.ser@student.mahidol.edu Author{1}{Affiliation}#=%=#Department of Biomedical Engineering, Faculty of Engineering, Mahidol University Author{2}{Firstname}#=%=#Nopporn Author{2}{Lastname}#=%=#Lekuthai Author{2}{Username}#=%=#swissnp Author{2}{Orcid}#=%=# Author{2}{Email}#=%=#swiss0404@gmail.com Author{2}{Affiliation}#=%=#Faculty of Medicine Ramathibodi Hospital Author{3}{Firstname}#=%=#Seksan Author{3}{Lastname}#=%=#Yoadsanit Author{3}{Username}#=%=#palmseksan Author{3}{Orcid}#=%=# Author{3}{Email}#=%=#seksan.yoadsanit@gmail.com Author{3}{Affiliation}#=%=#Faculty of Medicine Ramathibodi Hospital, Mahidol University Author{4}{Firstname}#=%=#Titipat Author{4}{Lastname}#=%=#Achakulvisut Author{4}{Username}#=%=#titipata Author{4}{Orcid}#=%=#0000-0002-2124-2979 Author{4}{Email}#=%=#my.titipat@gmail.com Author{4}{Affiliation}#=%=#Department of Biomedical Engineering, Mahidol University ========== èéáğö