Interpretability methods for large language models (LLMs) typically derive directions from textual supervision, which can lack external grounding. We propose using human brain activity not as a training signal but as a coordinate system for reading and steering LLM states. Using the SMN4Lang MEG dataset, we construct a word-level brain atlas of phase-locking value (PLV) patterns and extract latent axes via ICA. We validate axes with independent lexica and NER-based labels (POS/log-frequency used as sanity checks), then train lightweight adapters that map LLM hidden states to these brain axes without fine-tuning the LLM. Steering along the resulting brain-derived directions yields a robust lexical (frequency-linked) axis in a mid TinyLlama layer, surviving perplexity-matched controls, and a brain-vs-text probe comparison shows larger log-frequency shifts (relative to the text probe) with lower perplexity for the brain axis. A function/content axis (axis 13) shows consistent steering in TinyLlama, Qwen2-0.5B, and GPT-2, with PPL-matched text-level corroboration. Layer-4 effects in TinyLlama are large but inconsistent, so we treat them as secondary (Appendix). Axis structure is stable
Universal embodied intelligence demands robust generalization across heterogeneous embodiments, such as autonomous driving, robotics, and unmanned aerial vehicles (UAVs). However, existing embodied brain in training a unified model over diverse embodiments frequently triggers long-tail data, gradient interference, and catastrophic forgetting, making it notoriously difficult to balance universal generalization with domain-specific proficiency. In this report, we introduce ACE-Brain-0, a generalist foundation brain that unifies spatial reasoning, autonomous driving, and embodied manipulation within a single multimodal large language model~(MLLM). Our key insight is that spatial intelligence serves as a universal scaffold across diverse physical embodiments: although vehicles, robots, and UAVs differ drastically in morphology, they share a common need for modeling 3D mental space, making spatial cognition a natural, domain-agnostic foundation for cross-embodiment transfer. Building on this insight, we propose the Scaffold-Specialize-Reconcile~(SSR) paradigm, which first establishes a shared spatial foundation, then cultivates domain-specialized experts, and finally harmonizes them thr
Cognitive science and neuroscience have long faced the challenge of disentangling representations of language from representations of conceptual meaning. As the same problem arises in today's language models (LMs), we investigate the relationship between LM--brain alignment and two neural metrics: (1) the level of brain activation during processing of sentences, targeting linguistic processing, and (2) a novel measure of meaning consistency across input modalities, which quantifies how consistently a brain region responds to the same concept across paradigms (sentence, word cloud, image) using an fMRI dataset (Pereira et al., 2018). Our experiments show that both language-only and language-vision models predict the signal better in more meaning-consistent areas of the brain, even when these areas are not strongly sensitive to language processing, suggesting that LMs might internally represent cross-modal conceptual meaning.
We present a multi-scale differentiable brain modeling workflow utilizing BrainPy, a unique differentiable brain simulator that combines accurate brain simulation with powerful gradient-based optimization. We leverage this capability of BrainPy across different brain scales. At the single-neuron level, we implement differentiable neuron models and employ gradient methods to optimize their fit to electrophysiological data. On the network level, we incorporate connectomic data to construct biologically constrained network models. Finally, to replicate animal behavior, we train these models on cognitive tasks using gradient-based learning rules. Experiments demonstrate that our approach achieves superior performance and speed in fitting generalized leaky integrate-and-fire and Hodgkin-Huxley single neuron models. Additionally, training a biologically-informed network of excitatory and inhibitory spiking neurons on working memory tasks successfully replicates observed neural activity and synaptic weight distributions. Overall, our differentiable multi-scale simulation approach offers a promising tool to bridge neuroscience data across electrophysiological, anatomical, and behavioral sc
Brain tumor segmentation is crucial for diagnosis and treatment planning, yet challenges such as class imbalance and limited model generalization continue to hinder progress. This work presents a reproducible evaluation of U-Net segmentation performance on brain tumor MRI using focal loss and basic data augmentation strategies. Experiments were conducted on a publicly available MRI dataset, focusing on focal loss parameter tuning and assessing the impact of three data augmentation techniques: horizontal flip, rotation, and scaling. The U-Net with focal loss achieved a precision of 90%, comparable to state-of-the-art results. By making all code and results publicly available, this study establishes a transparent, reproducible baseline to guide future research on augmentation strategies and loss function design in brain tumor segmentation.
The development of foundation models for functional magnetic resonance imaging (fMRI) time series holds significant promise for predicting phenotypes related to disease and cognition. Current models, however, are often trained using a mask-and-reconstruct objective on small brain regions. This focus on low-level information leads to representations that are sensitive to noise and temporal fluctuations, necessitating extensive fine-tuning for downstream tasks. We introduce Brain-Semantoks, a self-supervised framework designed specifically to learn abstract representations of brain dynamics. Its architecture is built on two core innovations: a semantic tokenizer that aggregates noisy regional signals into robust tokens representing functional networks, and a self-distillation objective that enforces representational stability across time. We show that this objective is stabilized through a novel training curriculum, ensuring the model robustly learns meaningful features from low signal-to-noise time series. We demonstrate that learned representations enable strong performance on a variety of downstream tasks even when only using a linear probe. Furthermore, we provide comprehensive s
We introduce LearnAD, a neuro-symbolic method for predicting Alzheimer's disease from brain magnetic resonance imaging data, learning fully interpretable rules. LearnAD applies statistical models, Decision Trees, Random Forests, or GNNs to identify relevant brain connections, and then employs FastLAS to learn global rules. Our best instance outperforms Decision Trees, matches Support Vector Machine accuracy, and performs only slightly below Random Forests and GNNs trained on all features, all while remaining fully interpretable. Ablation studies show that our neuro-symbolic approach improves interpretability with comparable performance to pure statistical models. LearnAD demonstrates how symbolic learning can deepen our understanding of GNN behaviour in clinical neuroscience.
Accurate tissue segmentation of thick-slice fetal brain magnetic resonance (MR) scans is crucial for both reconstruction of isotropic brain MR volumes and the quantification of fetal brain development. However, this task is challenging due to the use of thick-slice scans in clinically-acquired fetal brain data. To address this issue, we propose to leverage high-quality isotropic fetal brain MR volumes (and also their corresponding annotations) as guidance for segmentation of thick-slice scans. Due to existence of significant domain gap between high-quality isotropic volume (i.e., source data) and thick-slice scans (i.e., target data), we employ a domain adaptation technique to achieve the associated knowledge transfer (from high-quality <source> volumes to thick-slice <target> scans). Specifically, we first register the available high-quality isotropic fetal brain MR volumes across different gestational weeks to construct longitudinally-complete source data. To capture domain-invariant information, we then perform Fourier decomposition to extract image content and style codes. Finally, we propose a novel Cycle-Consistent Domain Adaptation Network (C2DA-Net) to efficient
The brain is immensely complex, with diverse components and dynamic interactions building upon one another to orchestrate a wide range of functions and behaviors. Understanding patterns of these complex interactions and how they are coordinated to support collective neural activity and function is critical for parsing human and animal behavior, treating mental illness, and developing artificial intelligence. Rapid experimental advances in imaging, recording, and perturbing neural systems across various species now provide opportunities and challenges to distill underlying principles of brain organization and function. Here, we take stock of recent progresses and review methods used in the statistical analysis of brain networks, drawing from fields of statistical physics, network theory and information theory. Our discussion is organized by scale, starting with models of individual neurons and extending to large-scale networks mapped across brain regions. We then examine the organizing principles and constraints that shape the biological structure and function of neural circuits. Finally, we describe current opportunities aimed at improving models in light of recent developments and
Exploring the developing brain is a major issue in understanding what enables children to acquire amazing abilities, and how early disruptions can lead to a wide range of neurodevelopmental disorders. MRI plays a key role here by providing a non-invasive way to link brain and behavioral changes. Several modalities are used in newborns and infants to characterize the properties of the developing brain, from growth, morphology to microstructure and functional specialization. Recent multi-modal studies have sought to couple complementary MRI markers to provide a more integrated view of brain development. In this chapter, we describe successively how these approaches have made it possible to assess the early maturation of brain tissues, to link different aspects of structural development, and to compare structural and functional brain development.
Accurate segmentation of brain tumors plays a key role in the diagnosis and treatment of brain tumor diseases. It serves as a critical technology for quantifying tumors and extracting their features. With the increasing application of deep learning methods, the computational burden has become progressively heavier. To achieve a lightweight model with good segmentation performance, this study proposes the MBDRes-U-Net model using the three-dimensional (3D) U-Net codec framework, which integrates multibranch residual blocks and fused attention into the model. The computational burden of the model is reduced by the branch strategy, which effectively uses the rich local features in multimodal images and enhances the segmentation performance of subtumor regions. Additionally, during encoding, an adaptive weighted expansion convolution layer is introduced into the multi-branch residual block, which enriches the feature expression and improves the segmentation accuracy of the model. Experiments on the Brain Tumor Segmentation (BraTS) Challenge 2018 and 2019 datasets show that the architecture could maintain a high precision of brain tumor segmentation while considerably reducing the calcu
We developed a tool for visualizing and analyzing large pre-trained vision models by mapping them onto the brain, thus exposing their hidden inside. Our innovation arises from a surprising usage of brain encoding: predicting brain fMRI measurements in response to images. We report two findings. First, explicit mapping between the brain and deep-network features across dimensions of space, layers, scales, and channels is crucial. This mapping method, FactorTopy, is plug-and-play for any deep-network; with it, one can paint a picture of the network onto the brain (literally!). Second, our visualization shows how different training methods matter: they lead to remarkable differences in hierarchical organization and scaling behavior, growing with more data or network capacity. It also provides insight into fine-tuning: how pre-trained models change when adapting to small datasets. We found brain-like hierarchically organized network suffer less from catastrophic forgetting after fine-tuned.
Criticality is hypothesized as a physical mechanism underlying efficient transitions between cortical states and remarkable information processing capacities in the brain. While considerable evidence generally supports this hypothesis, non-negligible controversies persist regarding the ubiquity of criticality in neural dynamics and its role in information processing. Validity issues frequently arise during identifying potential brain criticality from empirical data. Moreover, the functional benefits implied by brain criticality are frequently misconceived or unduly generalized. These problems stem from the non-triviality and immaturity of the physical theories that analytically derive brain criticality and the statistic techniques that estimate brain criticality from empirical data. To help solve these problems, we present a systematic review and reformulate the foundations of studying brain criticality, i.e., ordinary criticality (OC), quasi-criticality (qC), self-organized criticality (SOC), and self-organized quasi-criticality (SOqC), using the terminology of neuroscience. We offer accessible explanations of the physical theories and statistic techniques of brain criticality, pr
Non-invasive brain imaging techniques allow understanding the behavior and macro changes in the brain to determine the progress of a disease. However, computational pathology provides a deeper understanding of brain disorders at cellular level, able to consolidate a diagnosis and make the bridge between the medical image and the omics analysis. In traditional histopathology, histology slides are visually inspected, under the microscope, by trained pathologists. This process is time-consuming and labor-intensive; therefore, the emergence of Computational Pathology has triggered great hope to ease this tedious task and make it more robust. This chapter focuses on understanding the state-of-the-art machine learning techniques used to analyze whole slide images within the context of brain disorders. We present a selective set of remarkable machine learning algorithms providing discriminative approaches and quality results on brain disorders. These methodologies are applied to different tasks, such as monitoring mechanisms contributing to disease progression and patient survival rates, analyzing morphological phenotypes for classification and quantitative assessment of disease, improvin
The release of large datasets and developments in AI have led to dramatic improvements in decoding methods that reconstruct seen images from human brain activity. We evaluate the prospect of further improving recent decoding methods by optimizing for consistency between reconstructions and brain activity during inference. We sample seed reconstructions from a base decoding method, then iteratively refine these reconstructions using a brain-optimized encoding model that maps images to brain activity. At each iteration, we sample a small library of images from an image distribution (a diffusion model) conditioned on a seed reconstruction from the previous iteration. We select those that best approximate the measured brain activity when passed through our encoding model, and use these images for structural guidance during the generation of the small library in the next iteration. We reduce the stochasticity of the image distribution at each iteration, and stop when a criterion on the "width" of the image distribution is met. We show that when this process is applied to recent decoding methods, it outperforms the base decoding method as measured by human raters, a variety of image feat
In this paper, we develop an analytical approach for estimating brain connectivity networks that accounts for subject heterogeneity. More specifically, we consider a novel extension of a multi-subject Bayesian vector autoregressive model that estimates group-specific directed brain connectivity networks and accounts for the effects of covariates on the network edges. We adopt a flexible approach, allowing for (possibly) non-linear effects of the covariates on edge strength via a novel Bayesian nonparametric prior that employs a weighted mixture of Gaussian processes. For posterior inference, we achieve computational scalability by implementing a variational Bayes scheme. Our approach enables simultaneous estimation of group-specific networks and selection of relevant covariate effects. We show improved performance over competing two-stage approaches on simulated data. We apply our method on resting-state fMRI data from children with a history of traumatic brain injury and healthy controls to estimate the effects of age and sex on the group-level connectivities. Our results highlight differences in the distribution of parent nodes. They also suggest alteration in the relation of age
Understanding the human brain remains the Holy Grail in biomedical science, and arguably in all of the sciences. Our brains represent the most complex systems in the world (and some contend the universe) comprising nearly one hundred billion neurons with septillions of possible connections between them. The structure of these connections engenders an efficient hierarchical system capable of consciousness, as well as complex thoughts, feelings, and behaviors. Brain connectivity and network analyses have exploded over the last decade due to their potential in helping us understand both normal and abnormal brain function. Functional connectivity (FC) analysis examines functional associations between time series pairs in specified brain voxels or regions. Brain network analysis serves as a distinct subfield of connectivity analysis in which associations are quantified for all time series pairs to create an interconnected representation of the brain (a brain network), which allows studying its systemic properties. While connectivity analyses underlie network analyses, the subtle distinction between the two research areas has generally been overlooked in the literature, with them often b
We present BrainPainter, a software that automatically generates images of highlighted brain structures given a list of numbers corresponding to the output colours of each region. Compared to existing visualisation software (i.e. Freesurfer, SPM, 3D Slicer), BrainPainter has three key advantages: (1) it does not require the input data to be in a specialised format, allowing BrainPainter to be used in combination with any neuroimaging analysis tools, (2) it can visualise both cortical and subcortical structures and (3) it can be used to generate movies showing dynamic processes, e.g. propagation of pathology on the brain. We highlight three use cases where BrainPainter was used in existing neuroimaging studies: (1) visualisation of the degree of atrophy through interpolation along a user-defined gradient of colours, (2) visualisation of the progression of pathology in Alzheimer's disease as well as (3) visualisation of pathology in subcortical regions in Huntington's disease. Moreover, through the design of BrainPainter we demonstrate the possibility of using a powerful 3D computer graphics engine such as Blender to generate brain visualisations for the neuroscience community. Blend
Pairwise metrics are often employed to estimate statistical dependencies between brain regions, however they do not capture higher-order information interactions. It is critical to explore higher-order interactions that go beyond paired brain areas in order to better understand information processing in the human brain. To address this problem, we applied multivariate mutual information, specifically, Total Correlation and Dual Total Correlation to reveal higher-order information in the brain. In this paper, we estimate these metrics using matrix-based Rényi's entropy, which offers a direct and easily interpretable approach that is not limited by direct assumptions about probability distribution functions of multivariate time series. We applied these metrics to resting-state fMRI data in order to examine higher-order interactions in the brain. Our results showed that the higher-order information interactions captured increase gradually as the interaction order increases. Furthermore, we observed a gradual increase in the correlation between the Total Correlation and Dual Total Correlation as the interaction order increased. In addition, the significance of Dual Total Correlation va
The shape of the brain's white matter connections is relatively unexplored in diffusion MRI tractography analysis. While it is known that tract shape varies in populations and across the human lifespan, it is unknown if the variability in dMRI tractography-derived shape may relate to the brain's functional variability across individuals. This work explores the potential of leveraging tractography fiber cluster shape measures to predict subject-specific cognitive performance. We implement machine learning models to predict individual cognitive performance scores. We study a large-scale database from the HCP-YA study. We apply an atlas-based fiber cluster parcellation to the dMRI tractography of each individual. We compute 15 shape, microstructure, and connectivity features for each fiber cluster. Using these features as input, we train a total of 210 models to predict 7 different NIH Toolbox cognitive performance assessments. We apply an explainable AI technique, SHAP, to assess the importance of each fiber cluster for prediction. Our results demonstrate that shape measures are predictive of individual cognitive performance. The studied shape measures, such as irregularity, diameter