Medical MLLMs degrade on image classification due to four failure modes in visual representation quality, connector projection fidelity, LLM comprehension, and semantic mapping alignment, quantified by feature probing on 14 models across 3 datasets.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
Fundus-R1 is a fundus-reading MLLM trained exclusively on public data via RAG-generated reasoning traces and process-reward RLVR, outperforming its base model and a version trained without the traces.
citing papers explorer
-
Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification
Medical MLLMs degrade on image classification due to four failure modes in visual representation quality, connector projection fidelity, LLM comprehension, and semantic mapping alignment, quantified by feature probing on 14 models across 3 datasets.
-
Fundus-R1: Training a Fundus-Reading MLLM with Knowledge-Aware Reasoning on Public Data
Fundus-R1 is a fundus-reading MLLM trained exclusively on public data via RAG-generated reasoning traces and process-reward RLVR, outperforming its base model and a version trained without the traces.
- Beyond the Crowd: LLM-Augmented Community Notes for Governing Health Misinformation