Related papers: Scale-Invariance Drives Convergence in AI and Brai…

The goal of this study is to investigate whether latent space representations of visual stimuli and fMRI data share common information. Decoding and reconstructing stimuli from fMRI data remains a challenge in AI and neuroscience, with…

Foundation models have reshaped AI by unifying fragmented architectures into scalable backbones with multimodal reasoning and contextual adaptation. In parallel, the long-standing notion of AI agents, defined by the sensing-decision-action…

Large language models (LLMs) are increasingly used in human-AI interaction research and practice, yet existing capability and safety benchmarks reveal little about the value priorities these systems express or how those priorities…

Correlation matrices are fundamental summaries of functional brain networks, yet standard analyses often treat entries independently, ignoring the curved geometry of correlation space. Existing geometric methods frequently lack closed-form…

The extent to which different neural or artificial neural networks (models) rely on equivalent representations to support similar tasks remains a central question in neuroscience and machine learning. Prior work has typically compared…

Schizophrenia is a chronic neuropsychiatric disorder that causes distinct structural alterations within the brain. We hypothesize that deep learning applied to a structural neuroimaging dataset could detect disease-related alteration and…

Magnetic Resonance Imaging (MRI) provides detailed structural information, while functional MRI (fMRI) captures temporal brain activity. In this work, we present a multimodal deep learning framework that integrates MRI and fMRI for…

Multivariate analysis of fMRI data has benefited substantially from advances in machine learning. Most recently, a range of probabilistic latent variable models applied to fMRI data have been successful in a variety of tasks, including…

Machine learning models of vastly different modalities and architectures are being trained to predict the behavior of molecules, materials, and proteins. However, it remains unclear whether they learn similar internal representations of…

Representations from transformer-based unidirectional language models are known to be effective at predicting brain responses to natural language. However, most studies comparing language models to brains have used GPT-2 or similarly sized…

Functional magnetic resonance imaging (fMRI) is used to extract {\em functional networks} connecting correlated human brain sites. Analysis of the resulting networks in different tasks shows that: (a) the distribution of functional…

The geometry of the human cortex is complex and highly variable, with interactions between brain size, cortical folding, and age well-documented in the literature. However, few studies have explored how global brain size influences…

Functional magnetic resonance imaging (fMRI) is a notoriously noisy measurement of brain activity because of the large variations between individuals, signals marred by environmental differences during collection, and spatiotemporal…

Convolutional Neural Networks have dramatically improved in recent years, surpassing human accuracy on certain problems and performance exceeding that of traditional computer vision algorithms. While the compute pattern in itself is…

The magnetorotational instability (MRI) plays a crucial role in the evolution of many types of accretion disks. It is often studied using ideal-MHD numerical simulations. In principle, such simulations should be numerically converged, i.e.…

The dynamics of learning in modern large AI systems is hierarchical, often characterized by abrupt, qualitative shifts akin to phase transitions observed in physical systems. While these phenomena hold promise for uncovering the mechanisms…

Humans can effortlessly describe what they see, yet establishing a shared representational format between vision and language remains a significant challenge. Emerging evidence suggests that human brain representations in both vision and…

In certain situations, neural networks are trained upon data that obey underlying symmetries. However, the predictions do not respect the symmetries exactly unless embedded in the network structure. In this work, we introduce architectures…

In this viewpoint article, we discuss the electric properties of the medium around neurons, which are important to correctly interpret extracellular potentials or electric field effects in neural tissue. We focus on how these electric…

Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. A wealth of effective new methods based on instance matching rely on data-augmentation to drive learning, and these have reached a rough…