From Reward Signal to Visual Utility: A Controlled Audit of Medical VLM Post-Training
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…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
