paper-with-me

홈 › Papers

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

2025-12-26 · Mo Wang, Junfeng Xia, Wenhao Ye, Enyu Liu, Kaining Peng, Jianfeng Feng, Quanying Liu, Hongkai Wen 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.

📄 PDF Abstract BibTeX arXiv:2512.21881

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Brain-DiT: A Universal Multi-state fMRI Foundation Model with Metadata-Conditioned Pretraining

2026-04-14 · Junfeng Xia, Wenhao Ye, Xuanye Pan, Xinke Shen 외 arxiv

Current fMRI foundation models primarily rely on a limited range of brain states and mismatched pretraining tasks, restricting their ability to learn generalized representations across diverse brain states. We present Br…

fMRI-PTE: A Large-scale fMRI Pretrained Transformer Encoder for Multi-Subject Brain Activity Decoding

2023-11-01 · Xuelin Qian, Yun Wang, Jingyang Huo, Jianfeng Feng 외

The exploration of brain activity and its decoding from fMRI data has been a longstanding pursuit, driven by its potential applications in brain-computer interfaces, medical diagnostics, and virtual reality. Previous app…

A Brain Graph Foundation Model: Pre-Training and Prompt-Tuning for Any Atlas and Disorder

2025-05-31 · Xinxu Wei, Kanhao Zhao, Yong Jiao, Lifang He 외

As large language models (LLMs) continue to revolutionize AI research, there is a growing interest in building large-scale brain foundation models to advance neuroscience. While most existing brain foundation models are …

Contrastive LearningMeta-LearningZero-Shot Learning

BrainWorld: A Structural-Prior-Conditioned Generative Model for Whole-Brain 4D fMRI Dynamics

2026-06-16 · Junfeng Xia, Wenhao Ye, Junxiang Zhang, Xuanye Pan 외 arxiv

Whole-brain 4D fMRI generation is valuable for modeling functional brain dynamics, yet existing fMRI foundation models mainly target representation learning and downstream prediction rather than conditional predictive ge…

Representation Learning

Region-Aware Reconstruction Strategy for Pre-training fMRI Foundation Model

2025-11-01 · Ruthwik Reddy Doodipala, Pankaj Pandey, Carolina Torres Rojas, Manob Jyoti Saikia 외 arxiv

The emergence of foundation models in neuroimaging is driven by the increasing availability of large-scale and heterogeneous brain imaging datasets. Recent advances in self-supervised learning, particularly reconstructio…

Self-Supervised Learning