Brain-DiT applies metadata-conditioned diffusion pretraining on a Diffusion Transformer to learn multi-scale fMRI representations across diverse brain states, outperforming reconstruction-based approaches on downstream tasks.
IScience23(1) (2020)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Brain-DiT: A Universal Multi-state fMRI Foundation Model with Metadata-Conditioned Pretraining
Brain-DiT applies metadata-conditioned diffusion pretraining on a Diffusion Transformer to learn multi-scale fMRI representations across diverse brain states, outperforming reconstruction-based approaches on downstream tasks.