I$^2$-Med: Interpretable Medical Inference through Visual-Guided Dynamic Logits Calibration
arXiv:2610.23858v1 Announce Type: new Abstract: Medical vision language models have demonstrated strong potential for medical image understanding and reasoning. However, their interpretability and reliability remain limited because medical vision language tasks require precise visual grounding and…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-20 04:00 · arXiv cs.CV
I$^2$-Med: Interpretable Medical Inference through Visual-Guided Dynamic Logits Calibration