2 papers
cs.CV2026
PaCX-MAE: Physiology-Augmented Chest X-Ray Masked Autoencoder
Yancheng Liu, Kenichi Maeda, Manan Pancholy
Clinical diagnosis often requires combining imaging with physiological measurements, yet deployed models typically operate on unimodal data. We present PaCX-MAE, a cross-modal dist…
cs.CV2025
Evaluating Graphical Perception with Multimodal LLMs
Rami Huu Nguyen, Kenichi Maeda, Mahsa Geshvadi +1
Multimodal Large Language Models (MLLMs) have remarkably progressed in analyzing and understanding images. Despite these advancements, accurately regressing values in charts remain…