arXiv:2607. 22615v1 Announce Type: cross Abstract: Clinical neuroprosthetics face a data bottleneck: labeled perception trials are scarce while hours of spontaneous neural activity are largely underutilized.
arXiv:2609.13507v1 Announce Type: new Abstract: Brain-computer interfaces (BCIs) decode neural activity to restore lost function. Typically, training a high-performance neural decoder requires a larg...
Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments. Recent work has shown that tokenizing neural data at the spike level facilitates multi-session pretraining and delivers state-of-the-art decoding performance.
NeuroLens is a self‑supervised model that learns denoised, semantically informative latent embeddings from chronic neural recordings using a Joint‑Embedding Predictive Architecture. It maps changing neural populations into a common latent space and predicts future latent states, thereby reducing sensitivity to transient recording variability. Across chronic intracortical data in mice and humans, NeuroLens improves decoding of decision‑making and semantic task variables, supports multi‑day pretraining, rapid few‑shot adaptation, and yields more stable decoding over time than existing baselines.
arXiv:2607. 14086v1 Announce Type: new Abstract: Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments.
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.
arXiv:2602. 15159v2 Announce Type: replace Abstract: Electronic health records (EHR) arrive masked.
arXiv:2607. 17782v1 Announce Type: cross Abstract: Foundation models pretrained using self-supervised learning have transformed computer vision by learning transferable representations from large-scale unlabeled data.
arXiv:2606. 15278v1 Announce Type: cross Abstract: Affective and cognitive disorders manifest as distributed, time-varying brain network dynamics across regions, channels, and time, challenging robust representation learning from EEG/sEEG for clinical diagnosis.
arXiv:2607. 23554v1 Announce Type: cross Abstract: In this paper, we propose the MAEConformer, a novel self-supervised learning framework that combines the Conformer architecture with the Masked Autoencoder (MAE) paradigm for large-scale representation learning from unlabelled electroencephalography (EEG) and heart rate variability (HRV) signals.
Neural State Prediction (NSP) is a latent‑predictive framework designed to curb shortcut learning in EEG foundation models. By using a target encoder updated with an exponential moving average, identity residualization, and topology‑separated context, NSP constrains both the prediction target and the available context. Trained on 2.2 million EEG segments, NSP outperforms baselines on 14 datasets in the EEG‑FM‑Bench, achieving 63.94 % macro balanced accuracy.
EEGDM introduces a self‑supervised framework that uses latent diffusion models to generate EEG signals, moving beyond traditional masked reconstruction. The method employs an EEG encoder to produce a compact representation that conditions the diffusion denoising process, allowing joint optimization of encoder and generator. Experiments demonstrate that EEGDM can reconstruct high‑quality EEG, learn robust representations, and perform competitively on various downstream tasks.
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....