arXiv:2511.08085v1 Announce Type: new 
Abstract: This research presents a comprehensive investigation into Bangla authorship attribution, introducing a new balanced benchmark corpus BARD10 (Bangla Authorship Recognition Dataset of 10 authors) and systematically analyzing the impact of stop-word removal across classical and deep learning models to uncover the stylistic significance of Bangla stop-words. BARD10 is a curated corpus of Bangla blog and opinion prose from ten contemporary authors, alongside the methodical assessment of four representative classifiers: SVM (Support Vector Machine), Bangla BERT (Bidirectional Encoder Representations from Transformers), XGBoost, and a MLP (Multilayer Perception), utilizing uniform preprocessing on both BARD10 and the benchmark corpora BAAD16 (Bangla Authorship Attribution Dataset of 16 authors). In all datasets, the classical TF-IDF + SVM baseline outperformed, attaining a macro-F1 score of 0.997 on BAAD16 and 0.921 on BARD10, while Bangla BERT lagged by as much as five points. This study reveals that BARD10 authors are highly sensitive to stop-word pruning, while BAAD16 authors remain comparatively robust highlighting genre-dependent reliance on stop-word signatures. Error analysis revealed that high frequency components transmit authorial signatures that are diminished or reduced by transformer models. Three insights are identified: Bangla stop-words serve as essential stylistic indicators; finely calibrated ML models prove effective within short-text limitations; and BARD10 connects formal literature with contemporary web dialogue, offering a reproducible benchmark for future long-context or domain-adapted transformers.

تقديم BARD10، مجموعة بيانات مرجعية جديدة لتحديد مؤلفي النصوص باللغة البنغالية، يبرز أهمية الكلمات التوقفية في تحليل أنماط الكتابة. تكشف هذه الدراسة أنه بينما تفوقت النماذج التقليدية مثل TF-IDF + SVM في الأداء، فإن Bangla BERT أظهر فعالية أقل، خاصة في سياق إزالة الكلمات التوقفية. فهم دور الكلمات التوقفية أمر حاسم لتحسين تقنيات تحديد المؤلفين في الأدب البنغالي.

La introducción de BARD10, un nuevo corpus de referencia para la atribución de autoría en bangla, resalta la importancia de las palabras vacías en el análisis de estilos de escritura. Este estudio revela que, aunque los modelos clásicos como TF-IDF + SVM sobresalieron en rendimiento, Bangla BERT mostró una efectividad inferior, especialmente en el contexto de la eliminación de palabras vacías. Comprender el papel de las palabras vacías es crucial para mejorar las técnicas de atribución de autoría en la literatura bangla.

L'introduction de BARD10, un nouveau corpus de référence pour l'attribution d'auteur en bangla, met en lumière l'importance des mots vides dans l'analyse des styles d'écriture. Cette étude révèle que, bien que les modèles classiques comme TF-IDF + SVM aient excellé en performance, Bangla BERT a montré une efficacité inférieure, en particulier dans le contexte de la suppression des mots vides. Comprendre le rôle des mots vides est crucial pour améliorer les techniques d'attribution d'auteur dans la littérature bangla.

The introduction of BARD10, a new benchmark corpus for Bangla authorship attribution, highlights the importance of stop-words in analyzing writing styles. This study reveals that while classical models like TF-IDF + SVM excelled in performance, Bangla BERT showed lower effectiveness, particularly in the context of stop-word removal. Understanding the role of stop-words is crucial for improving authorship attribution techniques in Bangla literature.

BARD10: A New Benchmark Reveals Significance of Bangla Stop-Words in Authorship Attribution

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:2511.10964v1 Announce Type: new 
Abstract: Machine Learning (ML) models are being increasingly employed for credit risk evaluation, with their effectiveness largely hinging on the quality of the input data. In this paper we investigate the impact of several data quality issues, including missing values, noisy attributes, outliers, and label errors, on the predictive accuracy of the machine learning model used in credit risk assessment. Utilizing an open-source dataset, we introduce controlled data corruption using the Pucktrick library to assess the robustness of 10 frequently used models like Random Forest, SVM, and Logistic Regression and so on. Our experiments show significant differences in model robustness based on the nature and severity of the data degradation. Moreover, the proposed methodology and accompanying tools offer practical support for practitioners seeking to enhance data pipeline robustness, and provide researchers with a flexible framework for further experimentation in data-centric AI contexts.

تستخدم نماذج التعلم الآلي بشكل متزايد لتقييم مخاطر الائتمان، وتعتمد فعاليتها على جودة البيانات. تبحث هذه الدراسة في تأثير مشكلات جودة البيانات مثل القيم المفقودة، والسمات المزعجة، والقيم الشاذة، وأخطاء التصنيف على دقة التنبؤ لنماذج التعلم الآلي. باستخدام مجموعة بيانات مفتوحة المصدر، تقيم الدراسة متانة عشرة نماذج مستخدمة بشكل شائع، بما في ذلك الغابة العشوائية، وSVM، والانحدار اللوجستي، كاشفة عن اختلافات كبيرة في أداء النموذج بناءً على تدهور البيانات.

Los modelos de aprendizaje automático (AA) se utilizan cada vez más para la evaluación del riesgo crediticio, siendo su efectividad dependiente de la calidad de los datos. Esta investigación investiga el impacto de problemas de calidad de datos como valores faltantes, atributos ruidosos, valores atípicos y errores de etiquetado en la precisión predictiva de los modelos de AA. Utilizando un conjunto de datos de código abierto, el estudio evalúa la robustez de diez modelos comúnmente utilizados, incluidos Random Forest, SVM y regresión logística, revelando diferencias significativas en el rendim…

Les modèles d'apprentissage automatique (AA) sont de plus en plus utilisés pour l'évaluation du risque de crédit, leur efficacité dépendant de la qualité des données. Cette recherche examine l'impact des problèmes de qualité des données tels que les valeurs manquantes, les attributs bruyants, les valeurs aberrantes et les erreurs d'étiquetage sur la précision prédictive des modèles d'AA. En utilisant un ensemble de données open-source, l'étude évalue la robustesse de dix modèles couramment utilisés, y compris Random Forest, SVM et régression logistique, révélant des différences significatives …

Machine Learning (ML) models are increasingly used for credit risk evaluation, with their effectiveness dependent on data quality. This research investigates the impact of data quality issues such as missing values, noisy attributes, outliers, and label errors on the predictive accuracy of ML models. Using an open-source dataset, the study assesses the robustness of ten commonly used models, including Random Forest, SVM, and Logistic Regression, revealing significant differences in model performance based on data degradation.

How Data Quality Affects Machine Learning Models for Credit Risk Assessment

arXiv:2510.24021v2 Announce Type: replace 
Abstract: Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies noisy, high-entropy signals and is especially harmful under large teacher-student capacity gaps. We introduce SelecTKD, a plug-and-play Selective Token-Weighted distillation framework that shifts the focus from "how to measure divergence" to "where to apply learning". At each step, the student proposes tokens that are verified by the teacher through a robust propose-and-verify procedure with two variants: greedy Top-k and non-greedy Spec-k. Accepted tokens receive full loss, while rejected tokens are masked or down-weighted. This objective-agnostic design works with on- and off-policy data, induces an implicit curriculum quantified by Token Acceptance Rate (TAR), and stabilizes optimization. Across instruction following, mathematical reasoning, code generation, and a VLM setting, SelecTKD consistently improves strong baselines and achieves state-of-the-art results for small models without architectural changes or extra reference models.

SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs

arXiv:2511.13368v1 Announce Type: new 
Abstract: Large language models (LLMs) perform strongly across tasks and languages, yet how improvements in one task or language affect other tasks and languages and their combinations remains poorly understood. We conduct a controlled PEFT/LoRA study across multiple open-weight LLM families and sizes, treating task and language as transfer axes while conditioning on model family and size; we fine-tune each model on a single task-language source and measure transfer as the percentage-point change versus its baseline score when evaluated on all other task-language target pairs. We decompose transfer into (i) Matched-Task (Cross-Language), (ii) Matched-Language (Cross-Task), and (iii) Cross-Task (Cross-Language) regimes. We uncover two consistent general patterns. First, a pronounced on-task vs. off-task asymmetry: Matched-Task (Cross-Language) transfer is reliably positive, whereas off-task transfer often incurs collateral degradation. Second, a stable donor-recipient structure across languages and tasks (hub donors vs. brittle recipients). We outline implications for risk-aware fine-tuning and model specialisation.

Donors and Recipients: On Asymmetric Transfer Across Tasks and Languages with Parameter-Efficient Fine-Tuning

arXiv:2511.11878v1 Announce Type: new 
Abstract: While large language models (LLMs) show transformative potential in healthcare, their development remains focused on high-resource languages, creating a critical barrier for others as simple translation fails to capture unique clinical and cultural nuances, such as endemic diseases. To address this, we introduce MedPT, the first large-scale, real-world corpus for Brazilian Portuguese, comprising 384,095 authentic question-answer pairs from patient-doctor interactions. The dataset underwent a meticulous multi-stage curation protocol, using a hybrid quantitative-qualitative analysis to filter noise and contextually enrich thousands of ambiguous queries. We further augmented the corpus via LLM-driven annotation, classifying questions into seven semantic types to capture user intent. Our analysis reveals its thematic breadth (3,200 topics) and unique linguistic properties, like the natural asymmetry in patient-doctor communication. To validate its utility, we benchmark a medical specialty routing task: fine-tuning a 1.7B parameter model achieves an outstanding 94\% F1-score on a 20-class setup. Furthermore, our qualitative error analysis shows misclassifications are not random but reflect genuine clinical ambiguities (e.g., between comorbid conditions), proving the dataset's deep semantic richness. We publicly release MedPT to foster the development of more equitable, accurate, and culturally-aware medical technologies for the Portuguese-speaking world.

BARD10: A New Benchmark Reveals Significance of Bangla Stop-Words in Authorship Attribution

Was this article worth reading? Share it