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
We study international mobility in academia, with a focus on the migration of published researchers to and from Russia. Using an exhaustive set of over $2.4$ million Scopus publications, we analyze all researchers who have published with a Russian affiliation address in Scopus-indexed sources in 1996-2020. The migration of researchers is observed through the changes in their affiliation addresses, which altered their mode countries of affiliation across different years. While only $5.2\%$ of these researchers were internationally mobile, they accounted for a substantial proportion of citations. Our estimates of net migration rates indicate that while Russia was a donor country in the late 1990s and early 2000s, it has experienced a relatively balanced circulation of researchers in more recent years. These findings suggest that the current trends in scholarly migration in Russia could be better framed as brain circulation, rather than as brain drain. Overall, researchers emigrating from Russia outnumbered and outperformed researchers immigrating to Russia. Our analysis on the subject categories of publication venues shows that in the past 25 years, Russia has, overall, suffered a ne
This scientometric study analyzes Avian Influenza research from 2014 to 2023 using bibliographic data from the Web of Science database. We examined publication trends, sources, authorship, collaborative networks, document types, and geographical distribution to gain insights into the global research landscape. Results reveal a steady increase in publications, with high contributions from Chinese and American institutions. Journals such as PLoS One and the Journal of Virology published the highest number of studies, indicating their influence in this field. The most prolific institutions include the Chinese Academy of Sciences and the University of Hong Kong, while the College of Veterinary Medicine at South China Agricultural University emerged as the most productive department. China and the USA lead in publication volume, though developed nations like the United Kingdom and Germany exhibit a higher rate of international collaboration. "Articles" are the most common document type, constituting 84.6% of the total, while "Reviews" account for 7.6%. This study provides a comprehensive view of global trends in Avian Influenza research, emphasizing the need for collaborative efforts ac
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
Since 2015, the Emerging Researchers in Exoplanetary Science (ERES) conference has provided a venue for early-career researchers in exoplanetary astronomy, astrophysics, and planetary science to share their research, network, and build new collaborations. ERES stands out in that it is spearheaded by early-career researchers, providing a unique attendance experience for the participants and a professional experience for the organizers. In this Bulletin, we share experiences and lessons learned from the perspective of the organizing committee for the 2023 edition of ERES. For this eighth ERES conference, we hosted over 100 participants in New Haven, CT, for a three-day program. This manuscript is aimed primarily toward groups of early-career scientists who are planning a conference for their fields of study. We anticipate that this Bulletin will continue dialogue within the academic community about best practices for equitable event organization.
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.
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
Multimodal learning enhances the perceptual capabilities of cognitive systems by integrating information from different sensory modalities. However, existing multimodal fusion research typically assumes static integration, not fully incorporating key dynamic mechanisms found in the brain. Specifically, the brain exhibits an inverse effectiveness phenomenon, wherein weaker unimodal cues yield stronger multisensory integration benefits; conversely, when individual modal cues are stronger, the effect of fusion is diminished. This mechanism enables biological systems to achieve robust cognition even with scarce or noisy perceptual cues. Inspired by this biological mechanism, we explore the relationship between multimodal output and information from individual modalities, proposing an inverse effectiveness driven multimodal fusion (IEMF) strategy. By incorporating this strategy into neural networks, we achieve more efficient integration with improved model performance and computational efficiency, demonstrating up to 50% reduction in computational cost across diverse fusion methods. We conduct experiments on audio-visual classification, continual learning, and question answering tasks t
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 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.
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 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
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
The production of knowledge has become increasingly a global endeavor. Yet, location related factors, such as local working environment and national policy designs, may continue to affect what kind of science is being pursued. Here we examine the geography of the production of creative science by country, through the lens of novelty and atypicality proposed in Uzzi et al. (2013). We quantify a country's representativeness in novel and atypical science, finding persistent differences in propensity to generate creative works, even among developed countries that are large producers in science. We further cluster countries based on how their tendency to publish novel science changes over time, identifying one group of emerging countries. Our analyses point out the recent emergence of China not only as a large producer in science but also as a leader that disproportionately produces more novel and atypical research. Discipline specific analysis indicates that China's over-production of atypical science is limited to a few disciplines, especially its most prolific ones like materials science and chemistry.
Background: Information processing in the brain requires large amounts of metabolic energy, the spatial distribution of which is highly heterogeneous reflecting complex activity patterns in the mammalian brain. Results: Here, it is found based on empirical data that, despite this heterogeneity, the volume-specific cerebral glucose metabolic rate of many different brain structures scales with brain volume with almost the same exponent around -0.15. The exception is white matter, the metabolism of which seems to scale with a standard specific exponent -1/4. The scaling exponents for the total oxygen and glucose consumptions in the brain in relation to its volume are identical and equal to $0.86\pm 0.03$, which is significantly larger than the exponents 3/4 and 2/3 suggested for whole body basal metabolism on body mass. Conclusions: These findings show explicitly that in mammals (i) volume-specific scaling exponents of the cerebral energy expenditure in different brain parts are approximately constant (except brain stem structures), and (ii) the total cerebral metabolic exponent against brain volume is greater than the much-cited Kleiber's 3/4 exponent. The neurophysiological factors
Semantic segmentation of brain tumours is a fundamental task in medical image analysis that can help clinicians in diagnosing the patient and tracking the progression of any malignant entities. Accurate segmentation of brain lesions is essential for medical diagnosis and treatment planning. However, failure to acquire specific MRI imaging modalities can prevent applications from operating in critical situations, raising concerns about their reliability and overall trustworthiness. This paper presents a novel multi-modal approach for brain lesion segmentation that leverages information from four distinct imaging modalities while being robust to real-world scenarios of missing modalities, such as T1, T1c, T2, and FLAIR MRI of brains. Our proposed method can help address the challenges posed by artifacts in medical imagery due to data acquisition errors (such as patient motion) or a reconstruction algorithm's inability to represent the anatomy while ensuring a trade-off in accuracy. Our proposed regularization module makes it robust to these scenarios and ensures the reliability of lesion segmentation.
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
A study on primates has established that gyral size is largely independent of overall brain size. Building on this, and other research suggesting that brain gyrification may mitigate the effects of head impacts, our study aims to explore potential correlations between gyral size and the risk of head impact across a diverse range of mammalian species. Our findings corroborate the idea that gyral sizes are largely independent of brain sizes, especially among species with larger brains, thus extending this observation beyond primates. Preliminary evidence also suggests a correlation between an animal's gyral size and its lifestyle, particularly in terms of head-impact risk. For instance, goats, known for their headbutting behaviors, exhibit smaller gyral sizes. In contrast, species such as manatees and dugongs, which typically face lower risks of head impact, have lissencephalic brains. Additionally, we explore mechanisms that may explain how narrower gyral sizes could offer protective advantages against head impact. Finally, we discuss a possible trade-off associated with gyrencephaly.