2 papers
cs.CV2026
Conditional Evidence Reconstruction and Decomposition for Interpretable Multimodal Diagnosis
Shaowen Wan, Yanjun Lv, Lu Zhang +5
Neurobiological and neurodegenerative diseases are inherently multifactorial, arising from coupled influences spanning genetic susceptibility, brain alterations, and environmental…
cs.CV2026
Thinking with Gaze: Sequential Eye-Tracking as Visual Reasoning Supervision for Medical VLMs
Yiwei Li, Zihao Wu, Yifan Zhou +10
Vision--language models (VLMs) process images as visual tokens, yet their intermediate reasoning is often carried out in text, which can be suboptimal for visually grounded radiolo…