MEDSYN benchmark shows MLLMs match experts on differential diagnosis lists but have much larger gaps to final diagnosis selection than humans, due to text overreliance and cross-modal evidence gaps.
Quilt-llava: Visual instruction tuning by extracting localized narratives from open-source histopathology videos
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
PMC-VQA dataset and MedVInT model achieve better generative performance on medical VQA benchmarks by visual instruction tuning on a newly constructed large-scale dataset.
MRPO is a step-aware RL method that penalizes early reasoning errors exponentially more when the final answer is incorrect, reducing early-stage failures from 64% to 13% and outperforming baselines including larger models on medical VQA tasks.
citing papers explorer
-
MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models
MEDSYN benchmark shows MLLMs match experts on differential diagnosis lists but have much larger gaps to final diagnosis selection than humans, due to text overreliance and cross-modal evidence gaps.
-
PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering
PMC-VQA dataset and MedVInT model achieve better generative performance on medical VQA benchmarks by visual instruction tuning on a newly constructed large-scale dataset.
-
Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoning
MRPO is a step-aware RL method that penalizes early reasoning errors exponentially more when the final answer is incorrect, reducing early-stage failures from 64% to 13% and outperforming baselines including larger models on medical VQA tasks.