arXiv:2606. 11500v1 Announce Type: cross Abstract: The success of large-scale deep learning models in neuroscience is fundamentally constrained by severe data heterogeneity.
arXiv:2609.31204v1 Announce Type: cross Abstract: Recent fMRI foundation models differ substantially in the spatial scale at which they represent brain activity. ROI- and connectivity-based models ar...
arXiv:2606. 04772v1 Announce Type: cross Abstract: Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience.
arXiv:2608.23936v1 Announce Type: new 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-fM...
Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience. While modern vision models achieve strong performance in image recognition, their correspondence with the hierarchical organization of the human visual cortex remains an open question.
arXiv:2608. 08135v1 Announce Type: cross Abstract: Cross-modality medical image translation can reduce the burden of multi-modal acquisitions, yet the field remains constrained by two coupled limitations: methods operate on 2D slices or 3D patches rather than whole volumes, and train a separate model for each translation task.
Rhamba is a region‑aware pretraining framework for resting‑state fMRI that combines anatomically guided masking with hybrid Attention‑Mamba architectures. The study pretrained models on the ABIDE dataset using three masking strategies (Any, Majority, Pure) and evaluated four architectural variants, finding that the Mamba‑Attention (MA) hybrid achieved the best average AUROC on downstream schizophrenia and ADHD classification tasks. Explainable AI via Integrated Gradients highlighted that performance depends on the interaction between masking strategy and architecture rather than a single dominant configuration.
The paper introduces a deep learning pipeline that rapidly and accurately registers 3D high‑resolution Drosophila larval brain volumes to a shared anatomical reference. Unlike traditional methods that require per‑case optimization and minutes per brain, the trained network performs a single forward pass, handling volumes with many more voxels and maintaining high accuracy even as image quality declines. The authors benchmarked their approach against eleven classical and seven learned baselines, achieving a 23‑percentage‑point improvement in landmark‑based mutual information and registering brains one to two orders of magnitude faster.
The paper introduces SIMS-MRI, a self‑supervised framework that performs single‑subject multi‑view MRI super‑resolution using implicit neural representations. It processes anisotropic multi‑view scans without pre‑ or post‑processing, employing a multi‑resolution hash‑encoded representation and learned inter‑view alignment to produce isotropic reconstructions. The method is validated on simulated brain and clinical prostate MRI datasets, and the code will be publicly released.
The study investigates how data volume, model size, and training duration affect the performance of fMRI foundation models. Using over 200 datasets and 10,000 GPU‑hours, the authors find that larger models benefit more from additional data, and that at a fixed compute budget, increasing data yields greater gains than enlarging the model. By selecting optimal combinations of data, size, and duration, they produce models that outperform existing fMRI foundation models on out‑of‑distribution tasks while requiring less pretraining compute.
arXiv:2609.34167v2 Announce Type: replace Abstract: Foundation models pre-trained on large-scale fMRI datasets have shown strong downstream performance, but at substantial data and computation cost....
arXiv:2607. 26829v1 Announce Type: cross Abstract: Many high-performing volumetric segmentation models maintain dense multi-scale feature maps, leading to high activation memory and inference cost.
arXiv:2510.14383v4 Announce Type: replace Abstract: Accurate brain tumor segmentation is significant for clinical diagnosis and treatment but remains challenging due to tumor heterogeneity. Mamba-bas...