A 3D brain-MRI tokenizer whose frozen MAE embeddings score well on 23 clinical probes and also condition a diffusion transformer for controllable generation.
Alexander, and Daniele Ravì
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation
A 3D brain-MRI tokenizer whose frozen MAE embeddings score well on 23 clinical probes and also condition a diffusion transformer for controllable generation.