# SLIM-Brain: A Data- and Training-Efficient Foundation Model for fMRI Data Analysis

arXiv: https://arxiv.org/abs/2512.21881 · HTML: https://mlsanity.com/paper/2512.21881/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 26 Dec 2025.

## Builds on (most cited first, 17 of 17)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://mlsanity.com/paper/2306.00989/) (2023)
- [Generic decoding of seen and imagined objects using hierarchical visual features](https://mlsanity.com/paper/1510.06479/) (2015)
- [Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking](https://mlsanity.com/paper/2409.19407/) (2024)
- [SwiFT: Swin 4D fMRI Transformer](https://mlsanity.com/paper/2307.05916/) (2023)
- [BrainMass: Advancing Brain Network Analysis for Diagnosis with Large-scale Self-Supervised Learning](https://mlsanity.com/paper/2403.01433/) (2024)
- [Attend and Decode: 4D fMRI Task State Decoding Using Attention Models](https://mlsanity.com/paper/2004.05234/) (2020)
- [Towards a general-purpose foundation model for fMRI analysis](https://mlsanity.com/paper/2506.11167/) (2025)
- [Explainable fMRI-based Brain Decoding via Spatial Temporal-pyramid Graph Convolutional Network](https://mlsanity.com/paper/2210.05713/) (2022)
- [DSAM: A Deep Learning Framework for Analyzing Temporal and Spatial Dynamics in Brain Networks](https://mlsanity.com/paper/2405.15805/) (2024)
- [Voxel-Level Brain States Prediction Using Swin Transformer](https://mlsanity.com/paper/2506.11455/) (2025)
- [DCA: Graph-Guided Deep Embedding Clustering for Brain Atlases](https://mlsanity.com/paper/2509.01426/) (2025)
- [Whole-brain Transferable Representations from Large-Scale fMRI Data Improve Task-Evoked Brain Activity Decoding](https://mlsanity.com/paper/2507.22378/) (2025)

## Built on by (most cited first, 9 of 9)

- [Brain-DiT: A Universal Multi-state fMRI Foundation Model with Metadata-Conditioned Pretraining](https://mlsanity.com/paper/2604.12683/) (2026)
- [FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRI](https://mlsanity.com/paper/2606.11500/) (2026)
- [BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics](https://mlsanity.com/paper/2606.17742/) (2026)
- [Beyond Single-Source Cognitive Taskonomy:Multi-Source Task Relations through fMRI Transfer Learning](https://mlsanity.com/paper/2606.26279/) (2026)
- [BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction](https://mlsanity.com/paper/2602.04512/) (2026)
- [PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift](https://mlsanity.com/paper/2605.16351/) (2026)
- [Omni-Sleep: A Sleep Foundation Model via Hierarchical Contrastive Learning of CNS-ANS Dynamics](https://mlsanity.com/paper/2607.07720/) (2026)
- [A Scaling Study for fMRI Foundation Models](https://mlsanity.com/paper/2609.27232/) (2026)
- [FlatClip: Reusing Image Foundation Models for fMRI Representation Learning via Cortical Flatmaps](https://mlsanity.com/paper/2609.31204/) (2026)

## Abstract (arXiv)

Foundation models are emerging as a powerful paradigm for fMRI analysis, but current approaches face a dual bottleneck of data- and training-efficiency. Atlas-based methods aggregate voxel signals into fixed regions of interest, reducing data dimensionality but discarding fine-grained spatial details, and requiring extremely large cohorts to train effectively as general-purpose foundation models. Atlas-free methods, on the other hand, operate directly on voxel-level information - preserving spatial fidelity but are prohibitively memory- and compute-intensive, making large-scale pre-training infeasible. We introduce SLIM-Brain (Sample-efficient, Low-memory fMRI Foundation Model for Human Brain), a new atlas-free foundation model that simultaneously improves both data- and training-efficiency. SLIM-Brain adopts a two-stage adaptive design: (i) a lightweight temporal extractor captures global context across full sequences and ranks data windows by saliency, and (ii) a 4D hierarchical encoder (Hiera-JEPA) learns fine-grained voxel-level representations only from the top-k selected windows, while deleting about 70% masked patches. Extensive experiments across seven public benchmarks show that SLIM-Brain establishes new state-of-the-art performance on diverse tasks, while requiring only 4 thousand pre-training sessions and approximately 30% of GPU memory comparing to traditional voxel-level methods.