Multi-source fMRI transfer learning on 23 HCP tasks reveals motor clusters with limited cross-paradigm transfer and uses BIP to prioritize working-memory states for direct supervision under budget constraints.
arXiv preprint arXiv:2601.23090 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Pretraining induces stable leading singular vectors that form a reusable spectral basis inherited by downstream tasks, enabling competitive performance with 0.2% trainable parameters on GLUE.
PIMSM is a Mamba-based architecture that maps knee frequencies from spectra to multi-scale discretization parameters to reduce representation drift under distribution shifts in fMRI and weather forecasting.
BrainWorld is a structural-prior-conditioned generative model that produces stable whole-brain 4D fMRI trajectories up to 400 frames, augments downstream tasks, and learns transferable multimodal representations across 22 datasets.
FlexiBrain is a resolution-agnostic voxel-level encoding framework using Mamba-JEPA that ingests native fMRI data directly and outperforms prior methods by up to 12 points on five neuroscience tasks.
citing papers explorer
-
Beyond Single-Source Cognitive Taskonomy:Multi-Source Task Relations through fMRI Transfer Learning
Multi-source fMRI transfer learning on 23 HCP tasks reveals motor clusters with limited cross-paradigm transfer and uses BIP to prioritize working-memory states for direct supervision under budget constraints.
-
Pretraining Induces a Reusable Spectral Basis for Downstream Task Adaptation
Pretraining induces stable leading singular vectors that form a reusable spectral basis inherited by downstream tasks, enabling competitive performance with 0.2% trainable parameters on GLUE.
-
PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift
PIMSM is a Mamba-based architecture that maps knee frequencies from spectra to multi-scale discretization parameters to reduce representation drift under distribution shifts in fMRI and weather forecasting.
-
BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics
BrainWorld is a structural-prior-conditioned generative model that produces stable whole-brain 4D fMRI trajectories up to 400 frames, augments downstream tasks, and learns transferable multimodal representations across 22 datasets.
-
FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI
FlexiBrain is a resolution-agnostic voxel-level encoding framework using Mamba-JEPA that ingests native fMRI data directly and outperforms prior methods by up to 12 points on five neuroscience tasks.