This work proposes MAPA, an otherwise vanilla masked autoencoder with two spatial encodings, an anatomical region embedding and a relative positional encoding that together enable it to learn neural representations that transfer to unseen subjects and across various tasks.
Abstract
Brain-computer interfaces (BCIs) decode neural activity to restore lost function. Typically, training a high-performance neural decoder requires a large labeled dataset to be collected from every new subject. One way to reduce the labeled data cost is self-supervised pretraining, which learns general neural representations from unlabeled recordings that accumulate across subjects. However, for intracranial electroencephalography (iEEG) recordings, self-supervised learning has been challenging due to differences in contact placement and neuroanatomy between subjects. We propose MAPA, an otherwise vanilla masked autoencoder with two spatial encodings, an anatomical region embedding and a relative positional encoding, which together enable it to learn neural representations that transfer to unseen subjects and across various tasks. MAPA sets a new state of the art across all three regimes of the Neuroprobe benchmark without fine-tuning: within-session, cross-session, and cross-subject. In the cross-subject regime, a linear probe on MAPA’s features needs only ~164 labeled trials to reach the accuracy that takes 3,500 without pretraining. Our results show that self-supervised pretraining can scale across heterogeneous iEEG recordings and reduce the labeled data needed for accurate decoding in new subjects.
This work introduced Dynamic Cognitive Prior Generation (DCPG), a new framework, which can be learned and is prototype based to adaptively generate priors instead of heuristic augmentations, and can be used to significantly increase the accuracy of inter-subject retrieval on the THINGS-EEG dataset with an accuracy impr...
Mehran Ali· Journal of Engineering and C...· 0 citations
iMINDBench is introduced, an iEEG Multi-Institution Neural Decoding Benchmark that evaluates models on a shared suite of fifteen decoding tasks across three naturalistic movie-watching datasets and finds that the evaluated pretrained systems generally outperform baselines within their respective preprocessing tracks, w...
Geeling Chau, Saba Hashemi, Yonghyeon Gwon et al.· arXiv.org· 0 citations
BrainWideBench is presented, a benchmark for evaluating across-animal transfer on multi-region neural recordings, built on the International Brain Laboratory Brainwide Map dataset of neural and behavioral recordings spanning 276 brain regions from 139 mice performing a sensory-guided decision-making task.
Alexandre Andre, S. Mahato, Vinam Arora et al.· arXiv.org· 1 citation
Decoding perceived speech from non-invasive brain recordings has garnered significant attention in recent years due to its wide range of potential applications. However, existing methods face considerable challenges in cross-subject decoding, primarily due to limited generalizability and the absence of explicit mechani...
Ao-Ke Zhang, Bo Wang, Xihong Wu et al.· 1 citation· ⚡1
This work proposes the Subject-Invariant Cross-Modal Perceived Speech Decoding (SICMD) method, which integrates functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG) and conducts comprehensive analyses of the fusion method, fusion position, encoder architecture, and model inputs.
It is suggested that the path a brain traces through anesthesia is a label-efficient correlate of latent vulnerability, motivating prospective validation of the representation across two cohorts and two acquisition systems.
J. Perdereau, Virginie Loison, Kanssaa El Ayeb et al.· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026