Search papers, labs, and topics across Lattice.
Technical University of Munich, Helmholtz Munich, King's College London, Center for Machine Learning
4
0
4
Predicting breast cancer treatment response just got a major upgrade, with a new framework that outperforms traditional models by effectively modeling temporal imaging data.
Prediction bias in medical imaging models can be effectively mitigated with a new objective that prevents model collapse during test-time adaptation.
Frozen vision-language models can dramatically improve abnormality grounding in rare disease imaging by iteratively refining decisions through optimized instructions and visual perturbations.
Forget simple averaging: this entropy-adaptive model merging strategy unlocks robust performance in medical imaging by intelligently combining models trained on diverse, private clinical datasets.
