Multimodal LLMs trained on medical images decomposed into modality, anatomy, and task can generalize to unseen combinations of those elements, and this compositional generalization partially explains multi-task training gains.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Exploring Compositional Generalization of Multimodal LLMs for Medical Imaging
Multimodal LLMs trained on medical images decomposed into modality, anatomy, and task can generalize to unseen combinations of those elements, and this compositional generalization partially explains multi-task training gains.