MnemoDyn: Learning Resting State Dynamics from 40K FMRI sequences
cs.LG
Submitted: 2026-08-25
Updated: 2026-08-25
Comments: ICLR 2026
Code: https://github.com/vsingh-group/mnemodyn
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: We present a dynamical-systems based model for resting-state functional magnetic resonance imaging (rs-fMRI), trained on a dataset of roughly 40K rs-fMRI sequences covering a wide variety of public
Terminology
Abstract
We present a dynamical-systems based model for resting-state functional magnetic resonance imaging (rs-fMRI), trained on a dataset of roughly 40K rs-fMRI sequences covering a wide variety of public and available-by-permission datasets. While most existing proposals use transformer backbones, we utilize multi-resolution temporal modeling of the dynamics across parcellated brain regions. We show that MnemoDyn is compute efficient and generalizes very well across diverse populations and scanning protocols. When benchmarked against current state-of-the-art transformer-based approaches, MnemoDyn consistently delivers superior reconstruction quality. Overall, we find that with such large-scale pre-training on (non-proprietary) rs-fMRI datasets, we get a highly performant model for various downstream tasks. Our results also provide evidence of the efficacy of the model on small sample size studies which has implications for neuroimaging studies at large where resting state fMRI is a commonly acquired imaging modality.
Sources
- Revisiting Feature Prediction for Learning Visual Representations from Video
- On the Opportunities and Risks of Foundation Models
- RT-1: Robotics Transformer for Real-World Control at Scale
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Large Language Models are Few-Shot Health Learners
- Transformer-based Spatial-Temporal Feature Learning for EEG Decoding
- Operator Learning: A Statistical Perspective
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks