Search papers, labs, and topics across Lattice.
Affiliation:
2
1
3
4
No single foundation model rules 3D radiology: across 2.1 million volumetric scans and 108 benchmarks, ConvNets consistently outperform transformers at dense spatial localization, while transformers decisively win on global semantic reasoning.
Overcome the surgical HSI data bottleneck: a latent diffusion model generates realistic hyperspectral images from segmentation masks, even those derived from different modalities, boosting segmentation performance by 35%.
