arXiv:2511.07801v1 Announce Type: new 
Abstract: We study multilabel classification of chest X-rays and present a simple, strong pipeline built on SE-ResNeXt101 $(32 \times 4d)$. The backbone is finetuned for 14 thoracic findings with a sigmoid head, trained using Multilabel Iterative Stratification (MIS) for robust cross-validation splits that preserve label co-occurrence. To address extreme class imbalance and asymmetric error costs, we optimize with Asymmetric Loss, employ mixed-precision (AMP), cosine learning-rate decay with warm-up, gradient clipping, and an exponential moving average (EMA) of weights. We propose a lightweight Label-Graph Refinement module placed after the classifier: given per-label probabilities, it learns a sparse, trainable inter-label coupling matrix that refines logits via a single message-passing step while adding only an L1-regularized parameter head. At inference, we apply horizontal flip test-time augmentation (TTA) and average predictions across MIS folds (a compact deep ensemble). Evaluation uses macro AUC averaging classwise ROC-AUC and skipping single-class labels in a fold to reflect balanced performance across conditions. On our dataset, a strong SE-ResNeXt101 baseline attains competitive macro AUC (e.g., 92.64% in our runs). Adding the Label-Graph Refinement consistently improves validation macro AUC across folds with negligible compute. The resulting method is reproducible, hardware-friendly, and requires no extra annotations, offering a practical route to stronger multilabel CXR classifiers.

تقدم دراسة جديدة طريقة متقدمة لتصنيف الأشعة السينية للصدر متعددة التسميات باستخدام نموذج SE-ResNeXt101. حقق هذا النهج، الذي يتضمن وحدة تحسين رسم بياني للتسميات، AUC ماكرو بنسبة 92.64% عبر 14 نتيجة صدرية. يعد هذا التطور مهمًا لأنه يعالج اختلال التوازن في الفئات ويعزز دقة التشخيص دون الحاجة إلى تعليقات إضافية، مما يجعله أداة واعدة في التصوير الطبي.

Un nuevo estudio presenta un método avanzado para la clasificación multilabel de radiografías de tórax utilizando el modelo SE-ResNeXt101. El enfoque, que incluye un módulo de Refinamiento de Grafo de Etiquetas, logró un AUC macro del 92.64% en 14 hallazgos torácicos. Este desarrollo es significativo ya que aborda el desequilibrio de clases y mejora la precisión diagnóstica sin requerir anotaciones adicionales, convirtiéndolo en una herramienta prometedora para la imagenología médica.

Une nouvelle étude présente une méthode avancée pour la classification multilabel des radiographies thoraciques utilisant le modèle SE-ResNeXt101. L'approche, qui inclut un module de raffinement de graphe de labels, a atteint un AUC macro de 92,64 % sur 14 constatations thoraciques. Ce développement est significatif car il aborde le déséquilibre des classes et améliore la précision diagnostique sans nécessiter d'annotations supplémentaires, en faisant un outil prometteur pour l'imagerie médicale.

A new study presents an advanced method for multilabel classification of chest X-rays using the SE-ResNeXt101 model. The approach, which includes a Label-Graph Refinement module, achieved a macro AUC of 92.64% across 14 thoracic findings. This development is significant as it addresses class imbalance and enhances diagnostic accuracy without requiring additional annotations, making it a promising tool for medical imaging.

Learning Sparse Label Couplings for Multilabel Chest X-Ray Diagnosis

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:2511.11093v1 Announce Type: new 
Abstract: Coronary artery calcification (CAC) is a strong predictor of cardiovascular events, with CT-based Agatston scoring widely regarded as the clinical gold standard. However, CT is costly and impractical for large-scale screening, while chest X-rays (CXRs) are inexpensive but lack reliable ground truth labels, constraining deep learning development. Digitally reconstructed radiographs (DRRs) offer a scalable alternative by projecting CT volumes into CXR-like images while inheriting precise labels. In this work, we provide the first systematic evaluation of DRRs as a surrogate training domain for CAC detection. Using 667 CT scans from the COCA dataset, we generate synthetic DRRs and assess model capacity, super-resolution fidelity enhancement, preprocessing, and training strategies. Lightweight CNNs trained from scratch outperform large pretrained networks; pairing super-resolution with contrast enhancement yields significant gains; and curriculum learning stabilises training under weak supervision. Our best configuration achieves a mean AUC of 0.754, comparable to or exceeding prior CXR-based studies. These results establish DRRs as a scalable, label-rich foundation for CAC detection, while laying the foundation for future transfer learning and domain adaptation to real CXRs.

تستكشف دراسة حديثة نُشرت على arXiv استخدام الأشعة السينية الصدرية الاصطناعية للكشف عن ترسبات الكالسيوم في الشرايين التاجية (CAC)، وهو مؤشر قوي للأحداث القلبية الوعائية. تبرز الدراسة قيود نظام تسجيل Agatston القائم على التصوير المقطعي بسبب تكلفته العالية وعدم ملاءمته للفحص على نطاق واسع. من خلال استخدام الأشعة السينية المعاد بناؤها رقميًا (DRRs) المولدة من مسحات التصوير المقطعي، تُظهر الدراسة أن الشبكات العصبية التلافيفية الخفيفة (CNNs) يمكن أن تحدد CAC بفعالية، محققة AUC متوسطًا قدره 0.754.

Un estudio reciente publicado en arXiv investiga el uso de radiografías torácicas sintéticas para la detección de la calcificación de las arterias coronarias (CAC), un predictor significativo de eventos cardiovasculares. La investigación destaca las limitaciones del puntaje Agatston basado en tomografía computarizada debido a su alto costo e impracticidad para el cribado a gran escala. Al utilizar radiografías reconstruidas digitalmente (DRRs) generadas a partir de escaneos CT, el estudio demuestra que las redes neuronales convolucionales ligeras (CNN) pueden identificar eficazmente la CAC, lo…

Une étude récente publiée sur arXiv examine l'utilisation de radiographies thoraciques synthétiques pour la détection de la calcification des artères coronaires (CAC), un indicateur significatif des événements cardiovasculaires. La recherche met en évidence les limites du scoring Agatston basé sur la tomodensitométrie en raison de son coût élevé et de son impraticabilité pour le dépistage à grande échelle. En utilisant des radiographies reconstruites numériquement (DRRs) générées à partir de scans CT, l'étude démontre que des réseaux de neurones convolutifs légers (CNN) peuvent identifier effi…

A recent study published on arXiv explores the use of synthetic chest X-rays for the detection of coronary artery calcification (CAC), a significant predictor of cardiovascular events. The research highlights the limitations of traditional CT-based Agatston scoring due to its high cost and impracticality for large-scale screening. By utilizing digitally reconstructed radiographs (DRRs) generated from CT scans, the study demonstrates that lightweight convolutional neural networks (CNNs) can effectively identify CAC, achieving a mean AUC of 0.754.

Learning Sparse Label Couplings for Multilabel Chest X-Ray Diagnosis

Was this article worth reading? Share it