EasyLens introduces a plug-and-play amplifier that uses pathology-anatomy prototypes and morphology-guided residual enhancement to boost subtle-lesion cues in frozen medical VLMs.
A reasoning-enabled vision-language foundation model for chest x-ray interpretation.arXiv preprint arXiv:2604.00493, 2026
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Decoding-time per-token SAE steering improves clinical report quality for three radiology VLMs by 5.4-17% relative on composite metrics, with universal boost features and model-specific suppressors, and zero-shot transfer to IU-Xray.
citing papers explorer
-
EasyLens: A Training-Free Plug-and-Play Subtle-Lesion Representation Amplifier for Medical Vision-Language Models
EasyLens introduces a plug-and-play amplifier that uses pathology-anatomy prototypes and morphology-guided residual enhancement to boost subtle-lesion cues in frozen medical VLMs.
-
Universal Boosts, Specific Suppressors: Sparse Autoencoder Steering of Medical Vision-Language Models
Decoding-time per-token SAE steering improves clinical report quality for three radiology VLMs by 5.4-17% relative on composite metrics, with universal boost features and model-specific suppressors, and zero-shot transfer to IU-Xray.