Category
128 papers
NeuronSifter treats decision quality as a property of the intervention interface, not of controller placement, and selects measurements by their expected reduction in intervention loss, assimilating typed outcomes into the same posterior.
NeuronDiscover is an Agent-in-Twin framework whose shared, mechanism-grounded World Action Model (WAM) couples prediction, intervention proposals, and observation design; independently adjudicated outcomes revise a scoped Mechanism--Intervention--Observation--Outcome (MIOY) graph, whose supported relations compile into...
Personal adaptation of three frozen EEG foundation models was evaluated in 235 held-out subjects in 235 held-out subjects from three motor-imagery datasets, comparing each subject's adapter with the population model and with adapters fitted to other subjects.
FAST-Brain is proposed, a unified flow-aligned spatio-temporal surrogate brain model that addresses all three challenges of resting-state functional magnetic resonance imaging data, and achieves state-of-the-art performance in recovering functional connectivity, effective connectivity, and the implicit low-dimensional...
Reach audiences
Advertise in front of researchers, engineers, and readers.
The Temporal Simplicial Neural Network is introduced, which represents EEG recordings as sequences of evolving simplicial complexes, and jointly learns higher-order interactions and their temporal evolution by combining simplicial convolutions with recurrent updates.
A distribution-aware, information-theoretic measure of effective connectivity based on channel capacity under general residual distributions based on normalizing flows is introduced, and a principled distribution-aware framework for effective-connectivity estimation beyond Gaussian residual modeling is established.
This work introduces a symbolic distillation pipeline that converts trained neural likelihoods into explicit, interpretable expressions optimized for efficient parameter estimation, and uses a recovery-directed objective to guide symbolic regression toward expressions that preserve parameter-recovery accuracy.
Transformers perform computations through many successive attention and feedforward blocks, allowing them to learn complex correlations between a large collection of coupled variables. When does stacking successive attention-feedforward computations over many layers provide a computational advantage over a single trans...
A new model family (CortexMAE) trained using the masked autoencoder framework is introduced, and in this setting the CortexMAE family outperforms prior models by a large margin, and the first open evaluation suite (Brainmarks) for fMRI foundation models is released.
A computational-theoretical framework is established to provide an account of psychopathology applicable to LLMs and experiments suggest that network-theoretic computations of psychopathology may have emerged in LLMs.
An explainable deep learning framework based on sparse projected residual networks to predict fluid, crystallized, and total intelligence from resting-state functional magnetic resonance imaging in 5,285 participants from the Adolescent Brain Cognitive Development study suggests that intelligence emerges from the inter...
Reliable decisions depend on recognizing when an answer may be wrong. In biological cognition, metacognitive monitoring can dissociate from task performance, raising the question of how closely solving and judging are linked in language models. Here we study the confidence reports of four frontier models across 15 benc...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
