Papers

A new preprint introduces BLPM, an EEG-language foundation model that reframes EEG decoding as continuous semantic embedding prediction.

SpikeGadgets says its hardware, using low-latency Ethernet and the TrodesNetwork API, lets researchers detect a neural activity pattern and trigger a perturbation within milliseconds. Two UCSF studies show it in use: one continuously decoded hippocampal population activity in rats to run a neurofeedback system, training the animals to volitionally generate specific memory representations for reward; the other triggered theta-phase-specific optogenetic stimulation in real time and showed that theta rhythm and replay are mechanistically separable.

Researchers propose combining discrete wavelet transform and chirplet transform for motor imagery EEG classification, achieving 94.8% accuracy on CBCIC with 1.03-second response time.

Researchers address the challenge of unifying consent standards for implantable brain-computer interfaces.

Intracortical recordings from 3 BrainGate2 participants show preparatory motor cortex activity encodes movement direction, curvature, and distance, enabling preparatory-activity-based online cursor control.

A review analyses technical, hardware, and user-level bottlenecks facing SSVEP-BCI systems in real-world deployment, summarising solutions including EMG fusion denoising, novel sponge electrodes, and hybrid paradigms.

Researchers propose CLMT-Net, a contrastive learning network based on a multi-scale Transformer, for fine-grained within-limb MI decoding, achieving 76.13% accuracy on the MI-2 dataset.

Researchers release a steady-state visual evoked potential-based BCI dataset collected from children and adolescents.

A game theory-based adaptive human-machine joint learning method for online MI-BCI decoding improves accuracy by 9.7% and 5.6% in 14-subject online experiments (both p < 0.01).

A University of Pittsburgh team (Bose et al.) tested the crossmodal congruency effect (CCE) task in 15 able-bodied volunteers to see whether it can quantify how intuitive lower-limb sensory feedback feels. At the knee, the task distinguished more natural pneumatic stimulation from less natural electrical stimulation; at the foot, it could not tell the same stimuli apart. The study was posted to bioRxiv on August 10, 2026. Lower-limb amputees often have balance and gait problems because their prostheses give no somatosensory feedback; electrical-stimulation neuroprostheses can partly restore sensation, but there has been no way to quantify how intuitive that sensation is. The authors stress that external factors affecting the CCE must be identified before it can be used with amputees.

Brain-computer interface decoders can guess the right label using information unrelated to the target mental state. A team at the School of Psychology, Beijing Language and Culture University (BLCU), proposes a falsifiable substitution-test standard: candidate evidence must persist in disjoint data, survive capacity-matched substitutions of physical organization or listener templates, and remain testable after target events are excluded. Across six EEG datasets (41 participants), averaging four neural-speech margin metrics brought 5-second decoding to what the authors call a leading level; in two hierarchical interfaces, parent-stream error scores kept AUCs of 0.968 and 0.965 after all target-command events were excluded. The framework offers a test for attributing evidence in neuroscience and BCI.

Researchers from Southwest State University developed an integrated brain-computer interface system supporting both synchronous and asynchronous paradigms, achieving 60-65% recognition accuracy in EEG-based robotic device control tasks.

Researchers propose ReCIL, a rehearsal-based class incremental learning method for cross-subject motor imagery classification that lets a model learn new MI classes sequentially without retraining from scratch. Using Euclidean alignment to reduce cross-subject EEG distribution shift and global-local replay to preserve earlier-task knowledge, ReCIL achieved a good balance between plasticity and stability across three public MI datasets. The authors report it as the first study of cross-subject class incremental learning for MI classification.

Researchers at Air Force Medical University have published a functional near-infrared spectroscopy (fNIRS) dataset in Scientific Data: frontal hemoglobin responses from 55 young adults, each recorded across three color-word Stroop sessions spread over about two weeks, with more than 30 trials per condition. The authors offer it for work on conflict inhibition, for building decoders for neurofeedback training, and for training large-scale cross-subject fNIRS models.

The study proposes BiGSTF-Net, a multimodal architecture that exploits the complementary properties of EEG and functional near-infrared spectroscopy (fNIRS) for cognitive-state decoding: heterogeneous spatio-temporal extractors capture each modality's representations, a modal residual interaction unit provides bidirectional cross-modal guidance, and a spatio-temporal gating unit fuses intra-modal features. Under cross-session evaluation on multiple BCI datasets, BiGSTF-Net consistently outperformed representative multimodal fusion baselines; ablations validated each component and visualizations matched the known neurophysiological features of the two signals.

A preprint introduces NeuroPB, a framework that scales neural decoding by transferring pretrained behavioral representations: a motion encoder is first pretrained on large-scale motor behavior data, then limited paired neural-behavior recordings align neural activity to the behavioral representation space, and a neural encoder with a lightweight motor decoder reconstructs continuous movement. The researchers report that behavioral pretraining lifted center-out trajectory decoding R² by 11% and random-target task performance by 8%, that pretraining on robotic trajectories matched macaque-trajectory performance, and that only 10% calibration was needed to match training from scratch. The study is a preprint and has not been peer-reviewed.

A preprint introduces OSPDIM, a source-free online unsupervised domain adaptation framework for class-imbalanced label shift in online EEG brain-computer interfaces. The study argues that Riemannian alignment methods such as the Riemannian centering transform handle covariate shift but implicitly assume balanced class priors, so shifting label distributions in real online use geometrically misalign the target data; OSPDIM adds a manifold-constrained bias parameter in the Riemannian tangent-space mapping, optimized by information maximization, and estimates and corrects the geometric bias online rather than relying on global batch statistics. 2D SPD matrix simulations showed OSPDIM correcting misalignment that standard centering fails on, and across multiple motor imagery datasets it significantly outperformed standard Riemannian baselines, especially online. The study is a preprint and has not been peer-reviewed.

The study presents an EEG brain-computer interface signal-processing framework that combines hybrid MothCray channel-selection optimization — fusing moth-flame and crayfish optimization — with deep learning. After notch filtering, independent component analysis (ICA) and time-window segmentation, the MothCray algorithm identifies the most informative channels and a deep neural network adapted to EEG spatio-temporal features classifies. The model reached 93.92% accuracy on BCI Competition IV dataset IIa, ahead of existing methods.

The study presents AutoMI, a framework that uses LLM multi-agents to automatically and rapidly iterate on motor imagery EEG classification models, combining a Q-learning policy with deterministic rules and integrating planning, execution and output agents with predefined tools, plus experience tracking and rollback. Models built by AutoMI reached 77.62%, 78.08% and 83.02% accuracy on the IV2a, OpenBMI and ECUST-MI datasets — up 18.42%, 9.27% and 19.25% over automated optimization algorithms.

The study recorded hippocampal CA1 population activity in rats performing a sequential spatial decision task in a modified T-maze, dividing the decision into initiation, running and approach phases. Local theta sequences consistently over-represented the actual choice, while prospective representations driven by choice-arm place cells shifted from predicting the actual choice during running to representing potential paths more evenly at the choice point. Integrating local and prospective features improved decoding, reaching 74.4% accuracy for future choice prediction and 78.2% for upcoming trajectory decoding.

Researchers at the Institute of Biological Information Processing at Forschungszentrum Jülich posted a preprint to bioRxiv on August 4, 2026, proposing hierarchical, dendrite-inspired organic bioelectronic interfaces built to integrate with neurons. Brain-computer interfaces depend on intimate electrical communication between living neurons and artificial materials, the authors write, yet conventional electrode architectures remain structurally unlike neural tissue, limiting stable cell-electrode coupling and long-term recording. The work is a preprint and has not been peer reviewed.

A preprint presents STEAM, a hierarchical transfer framework for EEG decoding that pairs a dual-branch spatio-temporal encoder with a shared soft mixture-of-experts (SSMoE) module to reconcile general representation learning with paradigm-specific specialization in EEG foundation models, letting complementary representations exchange information through a compact set of soft slots. The researchers report that STEAM attained the best average rank at competitive inference cost across 7 downstream datasets and 14 evaluation settings, and that its hierarchical pretraining further lifted decoding accuracy without retraining from scratch. The study is a preprint and has not been peer-reviewed.

CORTIVA, a candidate-score fusion framework for EEG- and MEG-to-image retrieval, reached 73.5% Top-1 and 95.3% Top-5 accuracy across ten participants on the 200-way THINGS-EEG2 benchmark, beating the strongest reported baseline by 10.3 and 5.4 percentage points. Instead of compressing heterogeneous visual supervision into a single embedding before ranking, the authors let separate decoding routes align to different visual targets and score the same candidate pool independently, merging only the temperature-scaled score vectors, which they say preserves complementary evidence; with a modality-specific encoder the same approach reached 42.4% Top-1 on THINGS-MEG. The work is a preprint and has not been peer reviewed.

The study presents a spatial harmonization framework built on a two-layer graph convolutional network (GCN) that maps heterogeneous EEG recordings onto a unified physical electrode layout while preserving motor imagery information, addressing electrode-configuration mismatches across MI-BCI datasets. Each trial is modeled as a graph so the GCN captures spatio-temporal relations, and harmonized EEG showed lower error than spherical spline interpolation while retaining the key temporal-spectral-spatial features. Combining real and harmonized EEG lifted EEGNet accuracy from 56.57% to 66.20% and FBCNet from 61.96% to 72.54% in within-session classification on Dataset A, and supported source-only cross-dataset transfer and target-domain fine-tuning.

A preprint uses radio-frequency backscatter and near-field wireless charging to tackle the wireless-link and power constraints of implantable brain-machine interfaces, noting that while high-resolution microelectrode arrays enable precise brain readout and stimulation, the 32–128 Mbps links they need are too power-hungry for a long-lived implanted battery. The approach strips the transceiver electronics out of the implant, moving complexity to the external reader to cut implant power, and powers the neural recording and stimulation chips via magnetic coupling. Preliminary tests validate the feasibility of the design; the study has not been peer reviewed.

This preprint introduces EasyBCI, which the authors say automates BCI preprocessing across six signal types with a two-phase large language model agent. The study is a preprint and has not been peer reviewed. On EEG with a fixed linear classifier, the authors report that all five EasyBCI backbones preserve more task-relevant separability than the manual pipeline, and that the system extends to five additional modalities spanning nearly three orders of magnitude in sampling rate.