04:00
2026-07-31
arxiv.org
artificial-intelligence
Objective-Aligned Direct Answer SFT for Robust Multi-Frame Medical VQA
A new arXiv preprint (2607.27566v1) finds that direct answer-only supervised fine-tuning (SFT) on MedGemma-1.5-4B is the most robust adaptation method for multi-frame medical visual question answering…