arXiv:2502.05109v2 Announce Type: replace 
Abstract: With recent advancements in non-invasive techniques for measuring brain activity, such as magnetic resonance imaging (MRI), the study of structural and functional brain networks through graph signal processing (GSP) has gained notable prominence. GSP stands as a key tool in unraveling the interplay between the brain's function and structure, enabling the analysis of graphs defined by the connections between regions of interest -- referred to as connectomes in this context. Our work represents a further step in this direction by exploring supervised contrastive learning methods within the realm of graph representation learning. The main objective of this approach is to generate subject-level (i.e., graph-level) vector representations that bring together subjects sharing the same label while separating those with different labels. These connectome embeddings are derived from a graph neural network Encoder-Decoder architecture, which jointly considers structural and functional connectivity. By leveraging data augmentation techniques, the proposed framework achieves state-of-the-art performance in a gender classification task using Human Connectome Project data. More broadly, our connectome-centric methodological advances support the promising prospect of using GSP to discover more about brain function, with potential impact to understanding heterogeneity in the neurodegeneration for precision medicine and diagnosis.

تستكشف دراسة حديثة نُشرت على arXiv استخدام التعلم التبايني الرسومي لتصنيف الشبكات العصبية، مستفيدة من التقدم في تقنيات التصوير بالرنين المغناطيسي (MRI). تهدف هذه الطريقة إلى إنشاء تمثيلات متجهية للاتصال العصبي تعزز من فهم وظيفة الدماغ وبنيته، محققة نتائج رائدة في مهام تصنيف الجنس. تدعم النتائج إمكانية تحسين الطب الدقيق في تشخيص التنكس العصبي.

Un estudio reciente publicado en arXiv explora el uso del aprendizaje contrastivo en grafos para clasificar conectomas, aprovechando los avances en tecnología de resonancia magnética (IRM). Este enfoque busca crear representaciones vectoriales de la conectividad cerebral que mejoren la comprensión de la función y estructura del cerebro, logrando resultados de vanguardia en tareas de clasificación de género. Los hallazgos apoyan el potencial de una medicina de precisión mejorada en el diagnóstico de neurodegeneración.

Une étude récente publiée sur arXiv explore l'utilisation de l'apprentissage contrastif par graphes pour classifier les connectomes, en s'appuyant sur les avancées de la technologie IRM. Cette approche vise à créer des représentations vectorielles de la connectivité cérébrale qui améliorent la compréhension de la fonction et de la structure du cerveau, atteignant des résultats de pointe dans les tâches de classification par genre. Les résultats soutiennent le potentiel d'une médecine de précision améliorée dans le diagnostic de la neurodégénérescence.

A recent study published on arXiv explores the use of graph contrastive learning for classifying connectomes, leveraging advancements in MRI technology. This approach aims to create vector representations of brain connectivity that enhance the understanding of brain function and structure, achieving state-of-the-art results in gender classification tasks. The findings support the potential for improved precision medicine in neurodegeneration diagnosis.

Graph Contrastive Learning for Connectome Classification

arXiv:1906.07172v5 Announce Type: replace-cross 
Abstract: Equivariant neural networks are a class of neural networks designed to preserve symmetries inherent in the data. In this paper, we introduce a general method for modifying a neural network to enforce equivariance, a process we refer to as equivarification. We further show that group convolutional neural networks (G-CNNs) arise as a special case of our framework.

Equivariant neural networks and equivarification

arXiv:2311.13745v4 Announce Type: replace-cross 
Abstract: Diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability. From a theoretical standpoint, a number of recent works have studied the iteration complexity of sampling, assuming access to an accurate diffusion model. In this work, we focus on understanding the sample complexity of training such a model; how many samples are needed to learn an accurate diffusion model using a sufficiently expressive neural network? Prior work showed bounds polynomial in the dimension, desired Total Variation error, and Wasserstein error. We show an exponential improvement in the dependence on Wasserstein error and depth, along with improved dependencies on other relevant parameters.

Improved Sample Complexity Bounds for Diffusion Model Training

arXiv:2410.22995v2 Announce Type: replace-cross 
Abstract: A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains critically underdeveloped in current Large Multi-modal Models (LMMs). The deficiency is often masked by evaluation metrics that prioritize final-answer accuracy, creating an illusion of competence where genuine reasoning is absent. Using the domain of geometric problem-solving as a precise instrument, we probe this issue through tasks that require constructing visual aids. To this end, we introduce \textbf{VisAidMath}, a challenging benchmark, and our novel Three-Layered Funnel Evaluation Framework. This framework moves beyond simple accuracy (ACCU) to scrutinize the generation of valid visual aids (PVA) and the soundness of subsequent reasoning steps (SPRS). Our extensive experiments on state-of-the-art models, including Doubao-Seed-1.6 and o4, reveal a profound ``Reasoning Illusion''. We observe that high surface-level accuracy conceals a catastrophic failure in the models' ability to produce valid visual aids or to reason from them. Our findings expose a fundamental schism between visual perception and logical deduction in modern LMMs. We host an evaluation platform at CodaBench for testing publicly. Homepage: https://nlp2ct.github.io/VisAidMathHomepage/ Evaluation: https://www.codabench.org/competitions/7634/

VisAidMath: Benchmarking Visual-Aided Mathematical Reasoning

arXiv:2508.01249v3 Announce Type: replace-cross 
Abstract: Large Language Model (LLM) agents offer a powerful new paradigm for solving various problems by combining natural language reasoning with the execution of external tools. However, their dynamic and non-transparent behavior introduces critical security risks, particularly in the presence of prompt injection attacks. In this work, we propose a novel insight that treats the agent runtime traces as structured programs with analyzable semantics. Thus, we present AgentArmor, a program analysis framework that converts agent traces into graph intermediate representation-based structured program dependency representations (e.g., CFG, DFG, and PDG) and enforces security policies via a type system. AgentArmor consists of three key components: (1) a graph constructor that reconstructs the agent's runtime traces as graph-based intermediate representations with control and data flow described within; (2) a property registry that attaches security-relevant metadata of interacted tools \& data, and (3) a type system that performs static inference and checking over the intermediate representation. By representing agent behavior as structured programs, AgentArmor enables program analysis for sensitive data flow, trust boundaries, and policy violations. We evaluate AgentArmor on the AgentDojo benchmark, the results show that AgentArmor can reduce the ASR to 3\%, with the utility drop only 1\%.

AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection

arXiv:2511.14691v1 Announce Type: cross 
Abstract: Attention is the brain's ability to selectively focus on a few specific aspects while ignoring irrelevant ones. This biological principle inspired the attention mechanism in modern Transformers. Transformers now underpin large language models (LLMs) such as GPT, but at the cost of massive training and inference energy, leading to a large carbon footprint. While brain attention emerges from neural circuits, Transformer attention relies on dot-product similarity to weight elements in the input sequence. Neuromorphic computing, especially spiking neural networks (SNNs), offers a brain-inspired path to energy-efficient intelligence. Despite recent work on attention-based spiking Transformers, the core attention layer remains non-neuromorphic. Current spiking attention (i) relies on dot-product or element-wise similarity suited to floating-point operations, not event-driven spikes; (ii) keeps attention matrices that suffer from the von Neumann bottleneck, limiting in-memory computing; and (iii) still diverges from brain-like computation. To address these issues, we propose the Spiking STDP Transformer (S$^{2}$TDPT), a neuromorphic Transformer that implements self-attention through spike-timing-dependent plasticity (STDP), embedding query--key correlations in synaptic weights. STDP, a core mechanism of memory and learning in the brain and widely studied in neuromorphic devices, naturally enables in-memory computing and supports non-von Neumann hardware. On CIFAR-10 and CIFAR-100, our model achieves 94.35\% and 78.08\% accuracy with only four timesteps and 0.49 mJ on CIFAR-100, an 88.47\% energy reduction compared to a standard ANN Transformer. Grad-CAM shows that the model attends to semantically relevant regions, enhancing interpretability. Overall, S$^{2}$TDPT illustrates how biologically inspired attention can yield energy-efficient, hardware-friendly, and explainable neuromorphic models.

Attention via Synaptic Plasticity is All You Need: A Biologically Inspired Spiking Neuromorphic Transformer

arXiv:2511.08955v2 Announce Type: replace-cross 
Abstract: Simulating microstructure evolution (MicroEvo) is vital for materials design but demands high numerical accuracy, efficiency, and physical fidelity. Although recent studies on deep learning (DL) offer a promising alternative to traditional solvers, the field lacks standardized benchmarks. Existing studies are flawed due to a lack of comparing specialized MicroEvo DL models with state-of-the-art spatio-temporal architectures, an overemphasis on numerical accuracy over physical fidelity, and a failure to analyze error propagation over time. To address these gaps, we introduce MicroEvoEval, the first comprehensive benchmark for image-based microstructure evolution prediction. We evaluate 14 models, encompassing both domain-specific and general-purpose architectures, across four representative MicroEvo tasks with datasets specifically structured for both short- and long-term assessment. Our multi-faceted evaluation framework goes beyond numerical accuracy and computational cost, incorporating a curated set of structure-preserving metrics to assess physical fidelity. Our extensive evaluations yield several key insights. Notably, we find that modern architectures (e.g., VMamba), not only achieve superior long-term stability and physical fidelity but also operate with an order-of-magnitude greater computational efficiency. The results highlight the necessity of holistic evaluation and identify these modern architectures as a highly promising direction for developing efficient and reliable surrogate models in data-driven materials science.

MicroEvoEval: A Systematic Evaluation Framework for Image-Based Microstructure Evolution Prediction

arXiv:2511.13082v1 Announce Type: new 
Abstract: Early diagnosis of breast cancer is crucial, enabling the establishment of appropriate treatment plans and markedly enhancing patient prognosis. While direct magnetic resonance imaging-guided biopsy demonstrates promising performance in detecting cancer lesions, its practical application is limited by prolonged procedure times and high costs. To overcome these issues, an indirect MRI-guided biopsy that allows the procedure to be performed outside of the MRI room has been proposed, but it still faces challenges in creating an accurate real-time deformable breast model. In our study, we tackled this issue by developing a graph neural network (GNN)-based model capable of accurately predicting deformed breast cancer sites in real time during biopsy procedures. An individual-specific finite element (FE) model was developed by incorporating magnetic resonance (MR) image-derived structural information of the breast and tumor to simulate deformation behaviors. A GNN model was then employed, designed to process surface displacement and distance-based graph data, enabling accurate prediction of overall tissue displacement, including the deformation of the tumor region. The model was validated using phantom and real patient datasets, achieving an accuracy within 0.2 millimeters (mm) for cancer node displacement (RMSE) and a dice similarity coefficient (DSC) of 0.977 for spatial overlap with actual cancerous regions. Additionally, the model enabled real-time inference and achieved a speed-up of over 4,000 times in computational cost compared to conventional FE simulations. The proposed deformation-aware GNN model offers a promising solution for real-time tumor displacement prediction in breast biopsy, with high accuracy and real-time capability. Its integration with clinical procedures could significantly enhance the precision and efficiency of breast cancer diagnosis.

تقدم دراسة حديثة نموذجًا لشبكة عصبية رسومية واعية للتشوهات مصممة للتنبؤ بمواقع سرطان الثدي في الوقت الحقيقي أثناء إجراءات الخزعة. تتناول هذه الابتكار القيود المفروضة على الخزعات الموجهة بواسطة التصوير بالرنين المغناطيسي، والتي غالبًا ما تكون مكلفة وتستغرق وقتًا طويلاً. من خلال استخدام نماذج العناصر المحدودة الخاصة بكل فرد المستمدة من صور الرنين المغناطيسي، يهدف النهج الجديد إلى تحسين دقة الكشف عن السرطان، مما يعزز نتائج المرضى من خلال التشخيص والعلاج في الوقت المناسب.

Un estudio reciente presenta un modelo de red neuronal gráfica consciente de la deformación diseñado para predecir en tiempo real los sitios de cáncer de mama durante los procedimientos de biopsia. Esta innovación aborda las limitaciones de las biopsias guiadas por resonancia magnética (IRM), que a menudo son costosas y requieren mucho tiempo. Al utilizar modelos de elementos finitos específicos para cada individuo derivados de imágenes de IRM, el nuevo enfoque busca mejorar la precisión en la detección del cáncer, mejorando así los resultados para los pacientes mediante un diagnóstico y trata…

Une étude récente présente un modèle de réseau de neurones graphique conscient de la déformation, conçu pour prédire en temps réel les sites de cancer du sein lors des procédures de biopsie. Cette innovation répond aux limites des biopsies guidées par IRM traditionnelles, souvent longues et coûteuses. En utilisant des modèles d'éléments finis spécifiques à chaque individu dérivés d'images IRM, cette nouvelle approche vise à améliorer la précision de la détection du cancer, améliorant ainsi les résultats pour les patients grâce à un diagnostic et un traitement rapides.

A recent study presents a deformation-aware graph neural network model designed to predict breast cancer sites in real time during biopsy procedures. This innovation addresses the limitations of traditional MRI-guided biopsies, which are often time-consuming and costly. By utilizing individual-specific finite element models derived from MRI images, the new approach aims to enhance the accuracy of cancer detection, ultimately improving patient outcomes through timely diagnosis and treatment planning.

Graph Contrastive Learning for Connectome Classification

Was this article worth reading? Share it