CortexMAE adapts Vision Transformers to fMRI via cortical flat maps, shows power-law scaling on 2.1K hours of data, and outperforms priors on cognitive state decoding while failing to beat a simple functional connectivity baseline on subject-level trait prediction.
Flexivit: One model for all patch sizes
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
Invaria trains point cloud encoders with next-resolution prediction to learn scale and density invariant features, yielding higher mIoU on ScanNet under lower resolution and scaled objects while using a smaller model.
citing papers explorer
-
Scaling Vision Transformers for Functional MRI with Flat Maps
CortexMAE adapts Vision Transformers to fMRI via cortical flat maps, shows power-law scaling on 2.1K hours of data, and outperforms priors on cognitive state decoding while failing to beat a simple functional connectivity baseline on subject-level trait prediction.
-
Invaria: Learning Scale and Density Invariance in Point Clouds via Next-Resolution Prediction
Invaria trains point cloud encoders with next-resolution prediction to learn scale and density invariant features, yielding higher mIoU on ScanNet under lower resolution and scaled objects while using a smaller model.