From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training

Paper recorded by Signals 4 on 2026-09-25 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-25 on arXiv · recorded by Signals 4 on 2026-09-28

Category: cs.AI · 人工智能 · first seen 2026-09-28

Abstract

Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy. We examine how changes in accuracy and training objectives relate to image-conditioned decisions in a controlled Qwen2.5-VL-3B study on PMC-VQA. We compare supervised fine-tuning (SFT) with low-rank adaptation (LoRA) restricted to the language model, expanded multimodal adaptation scopes, standard answ

Read on arXiv →