mimic-cxr-7b455981·3 events·first seen Aliases: MIMIC-CXR
Researchers introduce KANEx, a framework that leverages the symbolic transparency of Kolmogorov-Arnold Networks (KANs) to produce more faithful textual and visual explanations for chest X-ray classifiers. The system includes KAN-Map, a novel heatmap method derived directly from KAN model structure rather than gradient approximations, which feeds grounded context into downstream Vision-Language Models. Benchmarked on MIMIC-CXR, KAN-based architectures with ResNet/ViT backbones show a 10% improvement in visual localization and downstream reasoning quality over baseline approaches. The work positions mathematically interpretable architectural units as a path toward clinician-trustworthy medical AI.
Researchers introduce SHOVIR, a benchmark for detecting 'vision shortcut' behavior in Vision-Language Models applied to Radiology Report Generation (RRG), where models achieve high scores by exploiting learned priors rather than actual image evidence. The benchmark extends MIMIC-CXR and PadChest-GR with per-box CheXpert labels and uses localized occlusion experiments to isolate two failure modes: direct shortcuts (findings persist after visual evidence is removed) and contextual shortcuts (detection degrades when co-occurring pathologies are occluded). Evaluating eight state-of-the-art VLMs, the authors find that high report quality does not correlate with strong spatial grounding, revealing a systematic blind spot in current RRG evaluation protocols.
DIVE is a frozen-backbone distillation framework that addresses a fundamental limitation in token-level in-context vector distillation: uniform cross-entropy supervision treats all output tokens equally, but long-form outputs like medical reports are dominated by low-information template tokens while diagnostically critical tokens receive insufficient gradient signal. The method introduces decisive-token supervision (upweighting pathology-related tokens and EOS events) and state-conditioned dynamic steering (hidden-state-dependent adapters replacing fixed residuals) to correct supervision imbalance and autoregressive drift. Evaluated on MIMIC-CXR and CheXpert Plus with two medical VLM backbones, DIVE achieves best BLEU-4, ROUGE-L, and RadGraph F1 across all dataset-backbone combinations while remaining competitive on CheXbert F1.