# Research Papers — 2025-10 · bundle page 189 of 217 > Full-text markdown of papers #9401–9450 of 10843 published in 2025-10, newest first. AI-readable mirrors of the full 10843-paper 2025-10 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-10/page/189 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/188.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/190.md) ### PrivSpike: Employing Homomorphic Encryption for Private Inference of Deep Spiking Neural Networks Authors: Nges Brian Njungle, Eric Jahns, Milan Stojkov, Michel A. Kinsy Published: 2025-10-05 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2510.03995v1 Deep learning has become a cornerstone of modern machine learning. It relies heavily on vast datasets and significant computational resources for high performance. This data often contains sensitive information, making privacy a major concern in deep learning. Spiking Neural Networks (SNNs) have emerged as an energy-efficient alternative to conventional deep learning approaches. Nevertheless, SNNs still depend on large volumes of data, inheriting all the privacy challenges of deep learning. Homomorphic encryption addresses this challenge by allowing computations to be performed on encrypted data, ensuring data confidentiality throughout the entire processing pipeline. In this paper, we introduce PRIVSPIKE, a privacy-preserving inference framework for SNNs using the CKKS homomorphic encryption scheme. PRIVSPIKE supports arbitrary depth SNNs and introduces two key algorithms for evaluating the Leaky Integrate-and-Fire activation function: (1) a polynomial approximation algorithm designed for high-performance SNN inference, and (2) a novel scheme-switching algorithm that optimizes precision at a higher computational cost. We evaluate PRIVSPIKE on MNIST, CIFAR-10, Neuromorphic MNIST, and CIFAR-10 DVS using models from LeNet-5 and ResNet-19 architectures, achieving encrypted inference accuracies of 98.10%, 79.3%, 98.1%, and 66.0%, respectively. On a consumer-grade CPU, SNN LeNet-5 models achieved inference times of 28 seconds on MNIST and 212 seconds on Neuromorphic MNIST. For SNN ResNet-19 models, inference took 784 seconds on CIFAR-10 and 1846 seconds on CIFAR-10 DVS. These results establish PRIVSPIKE as a viable and efficient solution for secure SNN inference, bridging the gap between energy-efficient deep neural networks and strong cryptographic privacy guarantees while outperforming prior encrypted SNN solutions. --- ### Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning Authors: Yaxin Hou, Bo Han, Yuheng Jia, Hui Liu, Junhui Hou Published: 2025-10-05 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.03993v6 Current long-tailed semi-supervised learning methods assume that labeled data exhibit a long-tailed distribution, and unlabeled data adhere to a typical predefined distribution (i.e., long-tailed, uniform, or inverse long-tailed). However, the distribution of the unlabeled data is generally unknown and may follow an arbitrary distribution. To tackle this challenge, we propose a Controllable Pseudo-label Generation (CPG) framework, expanding the labeled dataset with the progressively identified reliable pseudo-labels from the unlabeled dataset and training the model on the updated labeled dataset with a known distribution, making it unaffected by the unlabeled data distribution. Specifically, CPG operates through a controllable self-reinforcing optimization cycle: (i) at each training step, our dynamic controllable filtering mechanism selectively incorporates reliable pseudo-labels from the unlabeled dataset into the labeled dataset, ensuring that the updated labeled dataset follows a known distribution; (ii) we then construct a Bayes-optimal classifier using logit adjustment based on the updated labeled data distribution; (iii) this improved classifier subsequently helps identify more reliable pseudo-labels in the next training step. We further theoretically prove that this optimization cycle can significantly reduce the generalization error under some conditions. Additionally, we propose a class-aware adaptive augmentation module to further improve the representation of minority classes, and an auxiliary branch to maximize data utilization by leveraging all labeled and unlabeled samples. Comprehensive evaluations on various commonly used benchmark datasets show that CPG achieves consistent improvements, surpassing state-of-the-art methods by up to $\textbf{15.97%}$ in accuracy. The code is available at https://github.com/yaxinhou/CPG. --- ### Quantitative Certification of Agentic Tool Selection Authors: Jehyeok Yeon, Isha Chaudhary, Gagandeep Singh Published: 2025-10-05 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2510.03992v2 Large language models (LLMs) are increasingly deployed in agentic systems, where a fundamental task is mapping user intents to relevant external tools. Errors in tool selection can have severe outcomes, such as unauthorized data access, even without modifying the agent's underlying model. Existing evaluations measure performance on curated, benign benchmarks. However, a pipeline's behavior in deployment depends on the tool pool the agent actually encounters, which in open registries is shaped by third parties. We introduce LLMCert-T, the first statistical framework that returns \textbf{high-confidence upper bounds on the probability that a tool-selection pipeline satisfies a declared safety specification under a realistic tool distribution}. LLMCert-T models tool-selection evaluation as a Bernoulli estimation problem, drawing inserted-tool sequences from a distribution that the safety specification fixes. To evaluate robustness against realistic deployment conditions, we instantiate this distribution as a stochastic process that generates inserted-tool sequences round by round, conditioning each round on the agent's selection in the previous round. LLMCert-T aggregates the per-trial outcomes into a one-sided Clopper-Pearson upper bound on the probability that the specification is satisfied. By returning this bound as a certificate with statistical guarantees over the inserted-tool sequence distribution, LLMCert-T makes safety claims intuitive, actionable, and comparable across models, retrievers, mitigations, and registry policies. Across popular BFCL and OpenAPI tool pools, LLMCert-T shows that current LLM agents remain fragile under Distractor Selection and Top-N Saturation specifications: their certified correctness upper bounds drop to approximately 20\%, far below their clean-pool lower bounds. --- ### A Mathematical Explanation of Transformers Authors: Xue-Cheng Tai, Hao Liu, Lingfeng Li, Raymond H. Chan Published: 2025-10-05 Categories: cs.LG, cs.AI, math.NA arXiv: https://arxiv.org/abs/2510.03989v2 The Transformer architecture has revolutionized the field of sequence modeling and underpins the recent breakthroughs in large language models (LLMs). However, a comprehensive mathematical theory that explains its structure and operations remains elusive. In this work, we propose a novel continuous framework that rigorously interprets the Transformer as a discretization of a structured integro-differential equation. Within this formulation, the self-attention mechanism emerges naturally as a non-local integral operator, and layer normalization is characterized as a projection to a time-dependent constraint. This operator-theoretic and variational perspective offers a unified and interpretable foundation for understanding the architecture's core components, including attention, feedforward layers, and normalization. Our approach extends beyond previous theoretical analyses by embedding the entire Transformer operation in continuous domains for both token indices and feature dimensions. This leads to a principled and flexible framework that not only deepens on theoretical insight but also offers new directions for architecture design, analysis, and control-based interpretations. This new interpretation provides a step toward bridging the gap between deep learning architectures and continuous mathematical modeling, and contributes a foundational perspective to the ongoing development of interpretable and theoretically grounded neural network models. --- ### The Signal is in the Steps: Local Scoring for Reasoning Data Selection Authors: Hoang Anh Just, Myeongseob Ko, Ruoxi Jia Published: 2025-10-05 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.03988v2 Distilling long-form reasoning from teacher models into smaller students requires selecting which candidate solutions to train on. Recent work argues that one should select responses the student model assigns highest probability, i.e., favoring solutions ``natural'' to the student. However, we find that this approach works within a single teacher but fails when scaling to long reasoning traces from multiple diverse teachers. We identify a key cause: this approach scores entire solutions, but students generalize by recombining familiar reasoning steps, not by memorizing complete solutions. Full-trajectory scoring optimizes the wrong target; it rewards global fluency while the transferable signal lies in local step transitions. We propose Local Average Log Probability (LALP), which scores each reasoning step using only a small window of preceding context, measuring whether each step is justified by its immediate premises rather than whether the full response looks natural to the student. LALP enables two practical use cases: selecting the best teacher before fine-tuning and curating training data from diverse teacher pools. Across math, coding, and science reasoning tasks, LALP consistently improves accuracy when selecting the most natural solutions by a large margin. --- ### ICEPool: Enhancing Graph Pooling Networks with Inter-cluster Connectivity Authors: Michael Yang Published: 2025-10-05 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.03987v1 Hierarchical Pooling Models have demonstrated strong performance in classifying graph-structured data. While numerous innovative methods have been proposed to design cluster assignments and coarsening strategies, the relationships between clusters are often overlooked. In this paper, we introduce Inter-cluster Connectivity Enhancement Pooling (ICEPool), a novel hierarchical pooling framework designed to enhance model's understanding of inter-cluster connectivity and ability of preserving the structural integrity in the original graph. ICEPool is compatible with a wide range of pooling-based GNN models. The deployment of ICEPool as an enhancement to existing models effectively combines the strengths of the original model with ICEPool's capability to emphasize the integration of inter-cluster connectivity, resulting in a more comprehensive and robust graph-level representation. Moreover, we make theoretical analysis to ICEPool's ability of graph reconstruction to demonstrate its effectiveness in learning inter-cluster relationship that is overlooked by conventional models. Finally, the experimental results show the compatibility of ICEPool with wide varieties of models and its potential to boost the performance of existing graph neural network architectures. --- ### Beyond Static Evaluation: Rethinking the Assessment of Personalized Agent Adaptability in Information Retrieval Authors: Kirandeep Kaur, Preetam Prabhu Srikar Dammu, Hideo Joho, Chirag Shah Published: 2025-10-05 Categories: cs.IR, cs.LG arXiv: https://arxiv.org/abs/2510.03984v1 Personalized AI agents are becoming central to modern information retrieval, yet most evaluation methodologies remain static, relying on fixed benchmarks and one-off metrics that fail to reflect how users' needs evolve over time. These limitations hinder our ability to assess whether agents can meaningfully adapt to individuals across dynamic, longitudinal interactions. In this perspective paper, we propose a conceptual lens for rethinking evaluation in adaptive personalization, shifting the focus from static performance snapshots to interaction-aware, evolving assessments. We organize this lens around three core components: (1) persona-based user simulation with temporally evolving preference models; (2) structured elicitation protocols inspired by reference interviews to extract preferences in context; and (3) adaptation-aware evaluation mechanisms that measure how agent behavior improves across sessions and tasks. While recent works have embraced LLM-driven user simulation, we situate this practice within a broader paradigm for evaluating agents over time. To illustrate our ideas, we conduct a case study in e-commerce search using the PersonalWAB dataset. Beyond presenting a framework, our work lays a conceptual foundation for understanding and evaluating personalization as a continuous, user-centric endeavor. --- ### Beyond Awareness: Investigating How AI and Psychological Factors Shape Human Self-Confidence Calibration Authors: Federico Maria Cau, Lucio Davide Spano Published: 2025-10-04 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2511.17509v1 Human-AI collaboration outcomes depend strongly on human self-confidence calibration, which drives reliance or resistance toward AI's suggestions. This work presents two studies examining whether calibration of self-confidence before decision tasks, low versus high levels of Need for Cognition (NFC), and Actively Open-Minded Thinking (AOT), leads to differences in decision accuracy, self-confidence appropriateness during the tasks, and metacognitive perceptions (global and affective). The first study presents strategies to identify well-calibrated users, also comparing decision accuracy and the appropriateness of self-confidence across NFC and AOT levels. The second study investigates the effects of calibrated self-confidence in AI-assisted decision-making (no AI, two-stage AI, and personalized AI), also considering different NFC and AOT levels. Our results show the importance of human self-confidence calibration and psychological traits when designing AI-assisted decision systems. We further propose design recommendations to address the challenge of calibrating self-confidence and supporting tailored, user-centric AI that accounts for individual traits. --- ### Deep Learning-based Lightweight RGB Object Tracking for Augmented Reality Devices Authors: Alice Smith, Bob Johnson, Xiaoyu Zhu, Carol Lee Published: 2025-10-04 Categories: cs.HC, cs.CV arXiv: https://arxiv.org/abs/2511.17508v1 Augmented Reality (AR) applications often require robust real-time tracking of objects in the user's environment to correctly overlay virtual content. Recent advances in computer vision have produced highly accurate deep learning-based object trackers, but these models are typically too heavy in computation and memory for wearable AR devices. In this paper, we present a lightweight RGB object tracking algorithm designed specifically for resource-constrained AR platforms. The proposed tracker employs a compact Siamese neural network architecture and incorporates optimization techniques such as model pruning, quantization, and knowledge distillation to drastically reduce model size and inference cost while maintaining high tracking accuracy. We train the tracker offline on large video datasets using deep convolutional neural networks and then deploy it on-device for real-time tracking. Experimental results on standard tracking benchmarks show that our approach achieves comparable accuracy to state-of-the-art trackers, yet runs in real-time on a mobile AR headset at around 30 FPS -- more than an order of magnitude faster than prior high-performance trackers on the same hardware. This work enables practical, robust object tracking for AR use-cases, opening the door to more interactive and dynamic AR experiences on lightweight devices. --- ### Multimodal Learning with Augmentation Techniques for Natural Disaster Assessment Authors: Adrian-Dinu Urse, Dumitru-Clementin Cercel, Florin Pop Published: 2025-10-04 Categories: cs.CY, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2511.00004v1 Natural disaster assessment relies on accurate and rapid access to information, with social media emerging as a valuable real-time source. However, existing datasets suffer from class imbalance and limited samples, making effective model development a challenging task. This paper explores augmentation techniques to address these issues on the CrisisMMD multimodal dataset. For visual data, we apply diffusion-based methods, namely Real Guidance and DiffuseMix. For text data, we explore back-translation, paraphrasing with transformers, and image caption-based augmentation. We evaluated these across unimodal, multimodal, and multi-view learning setups. Results show that selected augmentations improve classification performance, particularly for underrepresented classes, while multi-view learning introduces potential but requires further refinement. This study highlights effective augmentation strategies for building more robust disaster assessment systems. --- ### AdaptAuth: Multi-Layered Behavioral and Credential Analysis for a Secure and Adaptive Authentication Framework for Password Security Authors: Tonmoy Ghosh Published: 2025-10-04 Categories: cs.CR, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2510.09645v1 Password security has been compelled to evolve in response to the growing computational capabilities of modern systems. However, this evolution has often resulted in increasingly complex security practices that alienate users, leading to poor compliance and heightened vulnerability. Consequently, individuals remain exposed to attackers through weak or improperly managed passwords, underscoring the urgent need for a comprehensive defense mechanism that effectively addresses password-related risks and threats. In this paper, we propose a multifaceted solution designed to revolutionize password security by integrating diverse attributes such as the Password Dissection Mechanism, Dynamic Password Policy Mechanism, human behavioral patterns, device characteristics, network parameters, geographical context, and other relevant factors. By leveraging learning-based models, our framework constructs detailed user profiles capable of recognizing individuals and preventing nearly all forms of unauthorized access or device possession. The proposed framework enhances the usability-security paradigm by offering stronger protection than existing standards while simultaneously engaging users in the policy-setting process through a novel, adaptive approach. --- ### Enhanced Urban Traffic Management Using CCTV Surveillance Videos and Multi-Source Data Current State Prediction and Frequent Episode Mining Authors: Shaharyar Alam Ansari, Mohammad Luqman, Aasim Zafar, Savir Ali Published: 2025-10-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.09644v1 Rapid urbanization has intensified traffic congestion, environmental strain, and inefficiencies in transportation systems, creating an urgent need for intelligent and adaptive traffic management solutions. Conventional systems relying on static signals and manual monitoring are inadequate for the dynamic nature of modern traffic. This research aims to develop a unified framework that integrates CCTV surveillance videos with multi-source data descriptors to enhance real-time urban traffic prediction. The proposed methodology incorporates spatio-temporal feature fusion, Frequent Episode Mining for sequential traffic pattern discovery, and a hybrid LSTM-Transformer model for robust traffic state forecasting. The framework was evaluated on the CityFlowV2 dataset comprising 313,931 annotated bounding boxes across 46 cameras. It achieved a high prediction accuracy of 98.46 percent, with a macro precision of 0.9800, macro recall of 0.9839, and macro F1-score of 0.9819. FEM analysis revealed significant sequential patterns such as moderate-congested transitions with confidence levels exceeding 55 percent. The 46 sustained congestion alerts are system-generated, which shows practical value for proactive congestion management. This emphasizes the need for the incorporation of video stream analytics with data from multiple sources for the design of real-time, responsive, adaptable multi-level intelligent transportation systems, which makes urban mobility smarter and safer. --- ### Direct Routing Gradient (DRGrad): A Personalized Information Surgery for Multi-Task Learning (MTL) Recommendations Authors: Yuguang Liu, Yiyun Miao, Luyao Xia Published: 2025-10-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.09643v1 Multi-task learning (MTL) has emerged as a successful strategy in industrial-scale recommender systems, offering significant advantages such as capturing diverse users' interests and accurately detecting different behaviors like ``click" or ``dwell time". However, negative transfer and the seesaw phenomenon pose challenges to MTL models due to the complex and often contradictory task correlations in real-world recommendations. To address the problem while making better use of personalized information, we propose a personalized Direct Routing Gradient framework (DRGrad), which consists of three key components: router, updater and personalized gate network. DRGrad judges the stakes between tasks in the training process, which can leverage all valid gradients for the respective task to reduce conflicts. We evaluate the efficiency of DRGrad on complex MTL using a real-world recommendation dataset with 15 billion samples. The results show that DRGrad's superior performance over competing state-of-the-art MTL models, especially in terms of AUC (Area Under the Curve) metrics, indicating that it effectively manages task conflicts in multi-task learning environments without increasing model complexity, while also addressing the deficiencies in noise processing. Moreover, experiments on the public Census-income dataset and Synthetic dataset, have demonstrated the capability of DRGrad in judging and routing the stakes between tasks with varying degrees of correlation and personalization. --- ### Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models Authors: Shahriar Kabir Nahin, Hadi Askari, Muhao Chen, Anshuman Chhabra Published: 2025-10-04 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.08592v3 Test-Time Scaling (TTS) improves LLM reasoning by exploring multiple candidate responses and then operating over this set to find the best output. A tacit premise behind TTS is that sufficiently diverse candidate pools enhance reliability. In this work, we show that this assumption in TTS introduces a previously unrecognized failure mode. When candidate diversity is curtailed, even by a modest amount, TTS becomes much more likely to produce unsafe outputs. We present a reference-guided diversity reduction protocol (RefDiv) that serves as a diagnostic attack to stress test TTS pipelines. Through extensive experiments across open-source models (e.g. Qwen3, Mistral, Llama3.1, Gemma3) and two widely used TTS strategies (Monte Carlo Tree Search and Best-of-N), constraining diversity consistently signifies the rate at which TTS produces unsafe results. The effect is often stronger than that produced by prompts directly with high adversarial intent scores. This observed phenomenon also transfers across TTS strategies and to closed-source models (e.g. OpenAI o3-mini and Gemini-2.5-Pro), thus indicating that this is a general and extant property of TTS rather than a model-specific artifact. Additionally, we find that numerous widely used safety guardrail classifiers (e.g. Llama-Guard), are unable to flag the adversarial input prompts generated by RefDiv, demonstrating that existing defenses offer limited protection against this diversity-driven failure mode. --- ### The Enduring Dominance of Deep Neural Networks: A Critical Analysis of the Fundamental Limitations of Quantum Machine Learning and Spiking Neural Networks Authors: Takehiro Ishikawa Published: 2025-10-04 Categories: cs.NE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.08591v1 Recent advancements in QML and SNNs have generated considerable excitement, promising exponential speedups and brain-like energy efficiency to revolutionize AI. However, this paper argues that they are unlikely to displace DNNs in the near term. QML struggles with adapting backpropagation due to unitary constraints, measurement-induced state collapse, barren plateaus, and high measurement overheads, exacerbated by the limitations of current noisy intermediate-scale quantum hardware, overfitting risks due to underdeveloped regularization techniques, and a fundamental misalignment with machine learning's generalization. SNNs face restricted representational bandwidth, struggling with long-range dependencies and semantic encoding in language tasks due to their discrete, spike-based processing. Furthermore, the goal of faithfully emulating the brain might impose inherent inefficiencies like cognitive biases, limited working memory, and slow learning speeds. Even their touted energy-efficient advantages are overstated; optimized DNNs with quantization can outperform SNNs in energy costs under realistic conditions. Finally, SNN training incurs high computational overhead from temporal unfolding. In contrast, DNNs leverage efficient backpropagation, robust regularization, and innovations in LRMs that shift scaling to inference-time compute, enabling self-improvement via RL and search algorithms like MCTS while mitigating data scarcity. This superiority is evidenced by recent models such as xAI's Grok-4 Heavy, which advances SOTA performance, and gpt-oss-120b, which surpasses or approaches the performance of leading industry models despite its modest 120-billion-parameter size deployable on a single 80GB GPU. Furthermore, specialized ASICs amplify these efficiency gains. Ultimately, QML and SNNs may serve niche hybrid roles, but DNNs remain the dominant, practical paradigm for AI advancement. --- ### Evolutionary Computation as Natural Generative AI Authors: Yaxin Shi, Abhishek Gupta, Ying Wu, Melvin Wong, Ivor Tsang, Thiago Rios, Stefan Menzel, Bernhard Sendhoff, Yaqing Hou, Yew-Soon Ong Published: 2025-10-04 Categories: cs.NE, cs.LG arXiv: https://arxiv.org/abs/2510.08590v1 Generative AI (GenAI) has achieved remarkable success across a range of domains, but its capabilities remain constrained to statistical models of finite training sets and learning based on local gradient signals. This often results in artifacts that are more derivative than genuinely generative. In contrast, Evolutionary Computation (EC) offers a search-driven pathway to greater diversity and creativity, expanding generative capabilities by exploring uncharted solution spaces beyond the limits of available data. This work establishes a fundamental connection between EC and GenAI, redefining EC as Natural Generative AI (NatGenAI) -- a generative paradigm governed by exploratory search under natural selection. We demonstrate that classical EC with parent-centric operators mirrors conventional GenAI, while disruptive operators enable structured evolutionary leaps, often within just a few generations, to generate out-of-distribution artifacts. Moreover, the methods of evolutionary multitasking provide an unparalleled means of integrating disruptive EC (with cross-domain recombination of evolved features) and moderated selection mechanisms (allowing novel solutions to survive), thereby fostering sustained innovation. By reframing EC as NatGenAI, we emphasize structured disruption and selection pressure moderation as essential drivers of creativity. This perspective extends the generative paradigm beyond conventional boundaries and positions EC as crucial to advancing exploratory design, innovation, scientific discovery, and open-ended generation in the GenAI era. --- ### Enhanced Self-Distillation Framework for Efficient Spiking Neural Network Training Authors: Xiaochen Zhao, Chengting Yu, Kairong Yu, Lei Liu, Aili Wang Published: 2025-10-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.06254v1 Spiking Neural Networks (SNNs) exhibit exceptional energy efficiency on neuromorphic hardware due to their sparse activation patterns. However, conventional training methods based on surrogate gradients and Backpropagation Through Time (BPTT) not only lag behind Artificial Neural Networks (ANNs) in performance, but also incur significant computational and memory overheads that grow linearly with the temporal dimension. To enable high-performance SNN training under limited computational resources, we propose an enhanced self-distillation framework, jointly optimized with rate-based backpropagation. Specifically, the firing rates of intermediate SNN layers are projected onto lightweight ANN branches, and high-quality knowledge generated by the model itself is used to optimize substructures through the ANN pathways. Unlike traditional self-distillation paradigms, we observe that low-quality self-generated knowledge may hinder convergence. To address this, we decouple the teacher signal into reliable and unreliable components, ensuring that only reliable knowledge is used to guide the optimization of the model. Extensive experiments on CIFAR-10, CIFAR-100, CIFAR10-DVS, and ImageNet demonstrate that our method reduces training complexity while achieving high-performance SNN training. Our code is available at https://github.com/Intelli-Chip-Lab/enhanced-self-distillation-framework-for-snn. --- ### LLM-Driven Rubric-Based Assessment of Algebraic Competence in Multi-Stage Block Coding Tasks with Design and Field Evaluation Authors: Yong Oh Lee, Byeonghun Bang, Sejun Oh Published: 2025-10-04 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2510.06253v1 As online education platforms continue to expand, there is a growing need for assessment methods that not only measure answer accuracy but also capture the depth of students' cognitive processes in alignment with curriculum objectives. This study proposes and evaluates a rubric-based assessment framework powered by a large language model (LLM) for measuring algebraic competence, real-world-context block coding tasks. The problem set, designed by mathematics education experts, aligns each problem segment with five predefined rubric dimensions, enabling the LLM to assess both correctness and quality of students' problem-solving processes. The system was implemented on an online platform that records all intermediate responses and employs the LLM for rubric-aligned achievement evaluation. To examine the practical effectiveness of the proposed framework, we conducted a field study involving 42 middle school students engaged in multi-stage quadratic equation tasks with block coding. The study integrated learner self-assessments and expert ratings to benchmark the system's outputs. The LLM-based rubric evaluation showed strong agreement with expert judgments and consistently produced rubric-aligned, process-oriented feedback. These results demonstrate both the validity and scalability of incorporating LLM-driven rubric assessment into online mathematics and STEM education platforms. --- ### Machine learning for fraud detection in digital banking: a systematic literature review REVIEW Authors: Md Zahin Hossain George, Md Khorshed Alam, Md Tarek Hasan Published: 2025-10-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.05167v1 This systematic literature review examines the role of machine learning in fraud detection within digital banking, synthesizing evidence from 118 peer-reviewed studies and institutional reports. Following the PRISMA guidelines, the review applied a structured identification, screening, eligibility, and inclusion process to ensure methodological rigor and transparency. The findings reveal that supervised learning methods, such as decision trees, logistic regression, and support vector machines, remain the dominant paradigm due to their interpretability and established performance, while unsupervised anomaly detection approaches are increasingly adopted to address novel fraud patterns in highly imbalanced datasets. Deep learning architectures, particularly recurrent and convolutional neural networks, have emerged as transformative tools capable of modeling sequential transaction data and detecting complex fraud typologies, though challenges of interpretability and real-time deployment persist. Hybrid models that combine supervised, unsupervised, and deep learning strategies demonstrate superior adaptability and detection accuracy, highlighting their potential as convergent solutions. --- ### Domain-Adapted Granger Causality for Real-Time Cross-Slice Attack Attribution in 6G Networks Authors: Minh K. Quan, Pubudu N. Pathirana Published: 2025-10-04 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2510.05165v1 Cross-slice attack attribution in 6G networks faces the fundamental challenge of distinguishing genuine causal relationships from spurious correlations in shared infrastructure environments. We propose a theoretically-grounded domain-adapted Granger causality framework that integrates statistical causal inference with network-specific resource modeling for real-time attack attribution. Our approach addresses key limitations of existing methods by incorporating resource contention dynamics and providing formal statistical guarantees. Comprehensive evaluation on a production-grade 6G testbed with 1,100 empirically-validated attack scenarios demonstrates 89.2% attribution accuracy with sub-100ms response time, representing a statistically significant 10.1 percentage point improvement over state-of-the-art baselines. The framework provides interpretable causal explanations suitable for autonomous 6G security orchestration. --- ### SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading Authors: Yuanzhe Shen, Yide Liu, Zisu Huang, Ruicheng Yin, Xiaoqing Zheng, Xuanjing Huang Published: 2025-10-04 Categories: cs.DC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.05164v1 Large language models (LLMs) demonstrate remarkable performance across diverse tasks, yet their effectiveness frequently depends on costly commercial APIs or cloud services. Model selection thus entails a critical trade-off between performance and cost: high-performing LLMs typically incur substantial expenses, whereas budget-friendly small language models (SLMs) are constrained by limited capabilities. Current research primarily proposes two routing strategies: pre-generation routing and cascade routing. Both approaches have distinct characteristics, with cascade routing typically offering superior cost-effectiveness and accuracy despite its higher latency. To further address the limitations of both approaches, we introduce SATER, a dual-mode compatible approach that fine-tunes models through shortest-response preference optimization and a confidence-aware rejection mechanism. SATER significantly reduces redundant outputs and response times, while improving both the performance of pre-generation routing and the efficiency of cascade routing. Experiments across three SLMs and six datasets, varying in type and complexity, demonstrate that SATER achieves comparable performance while consistently reducing computational costs by over 50\% and cascade latency by over 80\%. --- ### Deep Learning-Based Multi-Factor Authentication: A Survey of Biometric and Smart Card Integration Approaches Authors: Abdelilah Ganmati, Karim Afdel, Lahcen Koutti Published: 2025-10-04 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2510.05163v1 In the era of pervasive cyber threats and exponential growth in digital services, the inadequacy of single-factor authentication has become increasingly evident. Multi-Factor Authentication (MFA), which combines knowledge-based factors (passwords, PINs), possession-based factors (smart cards, tokens), and inherence-based factors (biometric traits), has emerged as a robust defense mechanism. Recent breakthroughs in deep learning have transformed the capabilities of biometric systems, enabling higher accuracy, resilience to spoofing, and seamless integration with hardware-based solutions. At the same time, smart card technologies have evolved to include on-chip biometric verification, cryptographic processing, and secure storage, thereby enabling compact and secure multi-factor devices. This survey presents a comprehensive synthesis of recent work (2019-2025) at the intersection of deep learning, biometrics, and smart card technologies for MFA. We analyze biometric modalities (face, fingerprint, iris, voice), review hardware-based approaches (smart cards, NFC, TPMs, secure enclaves), and highlight integration strategies for real-world applications such as digital banking, healthcare IoT, and critical infrastructure. Furthermore, we discuss the major challenges that remain open, including usability-security tradeoffs, adversarial attacks on deep learning models, privacy concerns surrounding biometric data, and the need for standardization in MFA deployment. By consolidating current advancements, limitations, and research opportunities, this survey provides a roadmap for designing secure, scalable, and user-friendly authentication frameworks. --- ### Artificial-Intelligence Grading Assistance for Handwritten Components of a Calculus Exam Authors: Gerd Kortemeyer, Alexander Caspar, Daria Horica Published: 2025-10-04 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2510.05162v2 We investigate whether contemporary multimodal LLMs can assist with grading open-ended calculus at scale without eroding validity. In a large first-year exam, students' handwritten work was graded by GPT-5 against the same rubric used by teaching assistants (TAs), with fractional credit permitted; TA rubric decisions served as ground truth. We calibrated a human-in-the-loop filter that combines a partial-credit threshold with an Item Response Theory (2PL) risk measure based on the deviation between the AI score and the model-expected score for each student-item. Unfiltered AI-TA agreement was moderate, adequate for low-stakes feedback but not for high-stakes use. Confidence filtering made the workload-quality trade-off explicit: under stricter settings, AI delivered human-level accuracy, but also left roughly 70% of the items to be graded by humans. Psychometric patterns were constrained by low stakes on the open-ended portion, a small set of rubric checkpoints, and occasional misalignment between designated answer regions and where work appeared. Practical adjustments such as slightly higher weight and protected time, a few rubric-visible substeps, stronger spatial anchoring should raise ceiling performance. Overall, calibrated confidence and conservative routing enable AI to reliably handle a sizable subset of routine cases while reserving expert judgment for ambiguous or pedagogically rich responses. --- ### Beyond Softmax: A New Perspective on Gradient Bandits Authors: Emerson Melo, David Müller Published: 2025-10-04 Categories: cs.LG, econ.TH arXiv: https://arxiv.org/abs/2510.03979v1 We establish a link between a class of discrete choice models and the theory of online learning and multi-armed bandits. Our contributions are: (i) sublinear regret bounds for a broad algorithmic family, encompassing Exp3 as a special case; (ii) a new class of adversarial bandit algorithms derived from generalized nested logit models \citep{wen:2001}; and (iii) \textcolor{black}{we introduce a novel class of generalized gradient bandit algorithms that extends beyond the widely used softmax formulation. By relaxing the restrictive independence assumptions inherent in softmax, our framework accommodates correlated learning dynamics across actions, thereby broadening the applicability of gradient bandit methods.} Overall, the proposed algorithms combine flexible model specification with computational efficiency via closed-form sampling probabilities. Numerical experiments in stochastic bandit settings demonstrate their practical effectiveness. --- ### No Tokens Wasted: Leveraging Long Context in Biomedical Vision-Language Models Authors: Min Woo Sun, Alejandro Lozano, Javier Gamazo Tejero, Vishwesh Nath, Xiao Xiao Sun, James Burgess, Yuhui Zhang, Kun Yuan, Robert Tibshirani, Sean Huver, Serena Yeung-Levy Published: 2025-10-04 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2510.03978v1 Embedding vision-language models (VLMs) are typically pretrained with short text windows (<77 tokens), which forces the truncation of long-format captions. Yet, the distribution of biomedical captions from large-scale open source literature reveals that a huge portion of captions far exceed 77 tokens. To this end, we investigate the impact of pretraining on long-format biomedical captions by extending the context length of text encoders in VLMs. We find that longer context (thus, enabling additional supervision provided in long-format captions) correlates with better retrieval and classification performance. Given this finding, we introduce BIOMEDICA-LongCAP, a dataset of 1M image-caption pairs enriched with context-aware descriptions from full-text articles, providing longer and additional textual supervision. Using BIOMEDICA-LongCAP, we train BMC-LongCLIP, a long-context biomedical VLM with a text encoder supporting windows of up to 512 tokens. Our model extends context capacity by 6.6x, reducing token waste from 55% to just 2.2%. On long-caption retrieval benchmarks, BMC-LongCLIP achieves up to +30% absolute gains in Recall@1 and +2% average improvements in classification, while also converging faster than short-context. Our results demonstrate that long-context modeling is a promising direction for advancing biomedical VLMs. --- ### Use of Quadcopter Wakes to Supplement Strawberry Pollination Authors: Sadie Cutler, Ben DeFay, Scott McArt, Kirstin Petersen Published: 2025-10-04 Categories: eess.SY, cs.CV arXiv: https://arxiv.org/abs/2510.03974v1 Pollinators are critical to the world's ecosystems and food supply, yet recent studies have found pollination shortfalls in several crops, including strawberry. This is troubling because wild and managed pollinators are currently experiencing declines. One possibility is to try and provide supplemental pollination solutions. These solutions should be affordable and simple for farmers to implement if their use is to be widespread; quadcopters are a great example, already used for monitoring on many farms. This paper investigates a new method for artificial pollination based on wind pollination that bears further investigation. After determining the height where the lateral flow is maximized, we performed field experiments with a quadcopter assisting natural pollinators. Although our results in the field were inconclusive, lab studies show that the idea shows promise and could be adapted for better field results. --- ### What Can You Do When You Have Zero Rewards During RL? Authors: Jatin Prakash, Anirudh Buvanesh Published: 2025-10-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.03971v1 Reinforcement learning (RL) with outcome-based rewards has proven effective for improving large language models (LLMs) on complex reasoning tasks. However, its success often depends on the base model occasionally sampling correct solutions. When no correct solutions are sampled, training encounters a zero-reward barrier where learning stalls due to zero gradients. We study this scenario through the graph search task introduced in Bachmann et al. (2024) and evaluate recent methods that incorporate desirable components such as dense rewards, diversity incentives, and improved credit assignment. Our experiments show that none of these approaches overcome the zero-reward barrier if the base model never produces a correct answer. In contrast, we find that a simple data-centric intervention of adding easier samples to the training set enables the model to eventually solve the original hard task despite starting from zero reward. Importantly, this succeeds without modifying the RL algorithm itself. Because official implementations of several baselines were unavailable, we developed our own, which allowed us to conduct a detailed analysis of their failure modes. We release these implementations to support further research at: https://github.com/rl4reasoning/rl-baselines --- ### Towards Carbon-Aware Container Orchestration: Predicting Workload Energy Consumption with Federated Learning Authors: Zainab Saad, Jialin Yang, Henry Leung, Steve Drew Published: 2025-10-04 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2510.03970v1 The growing reliance on large-scale data centers to run resource-intensive workloads has significantly increased the global carbon footprint, underscoring the need for sustainable computing solutions. While container orchestration platforms like Kubernetes help optimize workload scheduling to reduce carbon emissions, existing methods often depend on centralized machine learning models that raise privacy concerns and struggle to generalize across diverse environments. In this paper, we propose a federated learning approach for energy consumption prediction that preserves data privacy by keeping sensitive operational data within individual enterprises. By extending the Kubernetes Efficient Power Level Exporter (Kepler), our framework trains XGBoost models collaboratively across distributed clients using Flower's FedXgbBagging aggregation using a bagging strategy, eliminating the need for centralized data sharing. Experimental results on the SPECPower benchmark dataset show that our FL-based approach achieves 11.7 percent lower Mean Absolute Error compared to a centralized baseline. This work addresses the unresolved trade-off between data privacy and energy prediction efficiency in prior systems such as Kepler and CASPER and offers enterprises a viable pathway toward sustainable cloud computing without compromising operational privacy. --- ### How Catastrophic is Your LLM? Certifying Risk in Conversation Authors: Chengxiao Wang, Isha Chaudhary, Qian Hu, Weitong Ruan, Rahul Gupta, Gagandeep Singh Published: 2025-10-04 Categories: cs.AI, cs.CR, cs.LG arXiv: https://arxiv.org/abs/2510.03969v3 Large Language Models (LLMs) can produce catastrophic responses in conversational settings that pose serious risks to public safety and security. Existing evaluations often fail to fully reveal these vulnerabilities because they rely on fixed attack prompt sequences, lack statistical guarantees, and do not scale to the vast space of multi-turn conversations. In this work, we propose C$^3$LLM, a novel, principled statistical Certification framework for Catastrophic risks in multi-turn Conversation for LLMs that bounds the probability of an LLM generating catastrophic responses under multi-turn conversation distributions with statistical guarantees. We model multi-turn conversations as probability distributions over query sequences, represented by a Markov process on a query graph whose edges encode semantic similarity to capture realistic conversational flow, and quantify catastrophic risks using confidence intervals. We define several inexpensive and practical distributions--random node, graph path, and adaptive with rejection. Our results demonstrate that these distributions can reveal substantial catastrophic risks in frontier models, with certified lower bounds as high as 70% for the worst model, highlighting the urgent need for improved safety training strategies in frontier LLMs. --- ### SPEAR: Soft Prompt Enhanced Anomaly Recognition for Time Series Data Authors: Hanzhe Wei, Jiajun Wu, Jialin Yang, Henry Leung, Steve Drew Published: 2025-10-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.03962v1 Time series anomaly detection plays a crucial role in a wide range of fields, such as healthcare and internet traffic monitoring. The emergence of large language models (LLMs) offers new opportunities for detecting anomalies in the ubiquitous time series data. Traditional approaches struggle with variable-length time series sequences and context-based anomalies. We propose Soft Prompt Enhanced Anomaly Recognition (SPEAR), a novel approach to leverage LLMs for anomaly detection with soft prompts and quantization. Our methodology involves quantizing and transforming the time series data into input embeddings and combining them with learnable soft prompt embeddings. These combined embeddings are then fed into a frozen LLM. The soft prompts are updated iteratively based on a cross-entropy loss, allowing the model to adapt to time series anomaly detection. The use of soft prompts helps adapt LLMs effectively to time series tasks, while quantization ensures optimal handling of sequences, as LLMs are designed to handle discrete sequences. Our experimental results demonstrate that soft prompts effectively increase LLMs' performance in downstream tasks regarding time series anomaly detection. --- ### Operational early warning of thunderstorm-driven power outages from open data: a two-stage machine learning approach Authors: Iryna Stanishevska, Seth Guikema Published: 2025-10-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.03959v4 Thunderstorm-driven power outages are difficult to predict because most storms do not cause damage, convective processes occur rapidly and chaotically, and the available public data are noisy and incomplete. Severe convective storms now account for a large and rising share of U.S. weather losses, yet thunderstorm-induced outages remain understudied. We develop a 48-hour early-warning model for summer thunderstorm-related outages in Michigan using only open-source outage (EAGLE-I) and weather (METAR) data. Relative to prior work, we (i) rely solely on public data, (ii) preserve convective extremes from a sparse station network via parameter-specific kriging and causal spatiotemporal features, and (iii) use a multi-level LSTM-based architecture evaluated on event-centric peak metrics. The pipeline builds rolling and k-NN inverse-distance aggregates to capture moisture advection, wind shifts, and pressure drops. A two-stage design uses a logistic gate followed by a long short-term memory (LSTM) regressor to filter routine periods and limit noise exposure. Evaluation focuses on state-level peaks of at least 50,000 customers without power, using hits, misses, false alarms, and peak-conditional MASE (cMASE) within 48-hour windows, with uncertainty quantified by block bootstrapping. On the test sample, the Two-Stage model detects more peaks with only one additional false alarm and reduces cMASE near peaks, providing event-focused early warnings without the utility-specific data. --- ### Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs Authors: Sameep Vani, Shreyas Jena, Maitreya Patel, Chitta Baral, Somak Aditya, Yezhou Yang Published: 2025-10-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.03955v1 While Video Large Language Models (Video-LLMs) have demonstrated remarkable performance across general video understanding benchmarks-particularly in video captioning and descriptive tasks-they consistently underperform on tasks that require fine-grained temporal understanding. This limitation arises due to the lack of visual complexity and temporal nuance in current fine-tuning datasets, leading these models to rely heavily on language-based reasoning rather than truly understanding video dynamics. In this work, we propose TimeWarp, a systematic method to create a targeted synthetic temporal dataset to fine-tune the model's responses to encourage it to focus on the given input video. We introduce a large-scale preference dataset, created using TimeWarp, that captures intricate temporal dynamics often overlooked, grounding the model's responses to visual and temporal information. We demonstrate that when our method is applied to existing models, it significantly improves performance on temporal understanding benchmarks, highlighting the effectiveness of our proposed datasets in advancing temporal understanding in Video-LLMs, resulting in an absolute improvement in performance across seven benchmarks. Code is available at https://github.com/sameepv21/timewarp. --- ### Optimizing Resources for On-the-Fly Label Estimation with Multiple Unknown Medical Experts Authors: Tim Bary, Tiffanie Godelaine, Axel Abels, Benoît Macq Published: 2025-10-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.03954v1 Accurate ground truth estimation in medical screening programs often relies on coalitions of experts and peer second opinions. Algorithms that efficiently aggregate noisy annotations can enhance screening workflows, particularly when data arrive continuously and expert proficiency is initially unknown. However, existing algorithms do not meet the requirements for seamless integration into screening pipelines. We therefore propose an adaptive approach for real-time annotation that (I) supports on-the-fly labeling of incoming data, (II) operates without prior knowledge of medical experts or pre-labeled data, and (III) dynamically queries additional experts based on the latent difficulty of each instance. The method incrementally gathers expert opinions until a confidence threshold is met, providing accurate labels with reduced annotation overhead. We evaluate our approach on three multi-annotator classification datasets across different modalities. Results show that our adaptive querying strategy reduces the number of expert queries by up to 50% while achieving accuracy comparable to a non-adaptive baseline. Our code is available at https://github.com/tbary/MEDICS --- ### Strategy Logic, Imperfect Information, and Hyperproperties Authors: Raven Beutner, Bernd Finkbeiner Published: 2025-10-04 Categories: cs.LO, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2510.03952v1 Strategy logic (SL) is a powerful temporal logic that enables first-class reasoning over strategic behavior in multi-agent systems (MAS). In many MASs, the agents (and their strategies) cannot observe the global state of the system, leading to many extensions of SL centered around imperfect information, such as strategy logic with imperfect information (SL$_\mathit{ii}$). Along orthogonal lines, researchers have studied the combination of strategic behavior and hyperproperties. Hyperproperties are system properties that relate multiple executions in a system and commonly arise when specifying security policies. Hyper Strategy Logic (HyperSL) is a temporal logic that combines quantification over strategies with the ability to express hyperproperties on the executions of different strategy profiles. In this paper, we study the relation between SL$_\mathit{ii}$ and HyperSL. Our main result is that both logics (restricted to formulas where no state formulas are nested within path formulas) are equivalent in the sense that we can encode SL$_\mathit{ii}$ instances into HyperSL instances and vice versa. For the former direction, we build on the well-known observation that imperfect information is a hyperproperty. For the latter direction, we construct a self-composition of MASs and show how we can simulate hyperproperties using imperfect information. --- ### What Is The Performance Ceiling of My Classifier? Utilizing Category-Wise Influence Functions for Pareto Frontier Analysis Authors: Shahriar Kabir Nahin, Wenxiao Xiao, Joshua Liu, Anshuman Chhabra, Hongfu Liu Published: 2025-10-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.03950v2 Data-centric learning seeks to improve model performance from the perspective of data quality, and has been drawing increasing attention in the machine learning community. Among its key tools, influence functions provide a powerful framework to quantify the impact of individual training samples on model predictions, enabling practitioners to identify detrimental samples and retrain models on a cleaner dataset for improved performance. However, most existing work focuses on the question: "what data benefits the learning model?" In this paper, we take a step further and investigate a more fundamental question: "what is the performance ceiling of the learning model?" Unlike prior studies that primarily measure improvement through overall accuracy, we emphasize category-wise accuracy and aim for Pareto improvements, ensuring that every class benefits, rather than allowing tradeoffs where some classes improve at the expense of others. To address this challenge, we propose category-wise influence functions and introduce an influence vector that quantifies the impact of each training sample across all categories. Leveraging these influence vectors, we develop a principled criterion to determine whether a model can still be improved, and further design a linear programming-based sample reweighting framework to achieve Pareto performance improvements. Through extensive experiments on synthetic datasets, vision, and text benchmarks, we demonstrate the effectiveness of our approach in estimating and achieving a model's performance improvement across multiple categories of interest. --- ### Analysis of kinetic Langevin Monte Carlo under the stochastic exponential Euler discretization from underdamped all the way to overdamped Authors: Kyurae Kim, Samuel Gruffaz, Ji Won Park, Alain Oliviero Durmus Published: 2025-10-04 Categories: stat.CO, math.NA, math.PR, stat.ML arXiv: https://arxiv.org/abs/2510.03949v4 Simulating the kinetic Langevin dynamics is a popular approach for sampling from distributions, where only their unnormalized densities are available. Various discretizations of the kinetic Langevin dynamics have been considered, where the resulting algorithm is collectively referred to as the kinetic Langevin Monte Carlo (KLMC) or underdamped Langevin Monte Carlo. Specifically, the stochastic exponential Euler discretization, or exponential integrator for short, has previously been studied under strongly log-concave and log-Lipschitz smooth potentials via the synchronous Wasserstein coupling strategy. Existing analyses, however, impose restrictions on the parameters that do not explain the behavior of KLMC under various choices of parameters. In particular, all known results fail to hold in the overdamped regime, suggesting that the exponential integrator degenerates in the overdamped limit. In this work, we revisit the synchronous Wasserstein coupling analysis of KLMC with the exponential integrator. Our refined analysis results in Wasserstein contractions and bounds on the asymptotic bias that hold under weaker restrictions on the parameters, which assert that the exponential integrator is capable of stably simulating the kinetic Langevin dynamics in the overdamped regime, as long as proper time acceleration is applied. --- ### On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection Authors: Weiqing He, Xiang Li, Tianqi Shang, Li Shen, Weijie Su, Qi Long Published: 2025-10-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.03944v2 Large language models (LLMs) raise concerns about content authenticity and integrity because they can generate human-like text at scale. Text watermarks, which embed detectable statistical signals into generated text, offer a provable way to verify content origin. Many detection methods rely on pivotal statistics that are i.i.d. under human-written text, making goodness-of-fit (GoF) tests a natural tool for watermark detection. However, GoF tests remain largely underexplored in this setting. In this paper, we systematically evaluate eight GoF tests across three popular watermarking schemes, using three open-source LLMs, two datasets, various generation temperatures, and multiple post-editing methods. We find that general GoF tests can improve both the detection power and robustness of watermark detectors. Notably, we observe that text repetition, common in low-temperature settings, gives GoF tests a unique advantage not exploited by existing methods. Our results highlight that classic GoF tests are a simple yet powerful and underused tool for watermark detection in LLMs. --- ### Super-resolution image projection over an extended depth of field using a diffractive decoder Authors: Hanlong Chen, Cagatay Isil, Tianyi Gan, Mona Jarrahi, Aydogan Ozcan Published: 2025-10-04 Categories: physics.optics, cs.CV, cs.NE, physics.app-ph arXiv: https://arxiv.org/abs/2510.03938v1 Image projection systems must be efficient in data storage, computation and transmission while maintaining a large space-bandwidth-product (SBP) at their output. Here, we introduce a hybrid image projection system that achieves extended depth-of-field (DOF) with improved resolution, combining a convolutional neural network (CNN)-based digital encoder with an all-optical diffractive decoder. A CNN-based encoder compresses input images into compact phase representations, which are subsequently displayed by a low-resolution (LR) projector and processed by an analog diffractive decoder for all-optical image reconstruction. This optical decoder is completely passive, designed to synthesize pixel super-resolved image projections that feature an extended DOF while eliminating the need for additional power consumption for super-resolved image reconstruction. Our pixel super-resolution (PSR) image projection system demonstrates high-fidelity image synthesis over an extended DOF of ~267xW, where W is the illumination wavelength, concurrently offering up to ~16-fold SBP improvement at each lateral plane. The proof of concept of this approach is validated through an experiment conducted in the THz spectrum, and the system is scalable across different parts of the electromagnetic spectrum. This image projection architecture can reduce data storage and transmission requirements for display systems without imposing additional power constraints on the optical decoder. Beyond extended DOF PSR image projection, the underlying principles of this approach can be extended to various applications, including optical metrology and microscopy. --- ### LLM Chemistry Estimation for Multi-LLM Recommendation Authors: Huascar Sanchez, Briland Hitaj Published: 2025-10-04 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.03930v1 Multi-LLM collaboration promises accurate, robust, and context-aware solutions, yet existing approaches rely on implicit selection and output assessment without analyzing whether collaborating models truly complement or conflict. We introduce LLM Chemistry -- a framework that measures when LLM combinations exhibit synergistic or antagonistic behaviors that shape collective performance beyond individual capabilities. We formalize the notion of chemistry among LLMs, propose algorithms that quantify it by analyzing interaction dependencies, and recommend optimal model ensembles accordingly. Our theoretical analysis shows that chemistry among collaborating LLMs is most evident under heterogeneous model profiles, with its outcome impact shaped by task type, group size, and complexity. Evaluation on classification, summarization, and program repair tasks provides initial evidence for these task-dependent effects, thereby reinforcing our theoretical results. This establishes LLM Chemistry as both a diagnostic factor in multi-LLM systems and a foundation for ensemble recommendation. --- ### Self-Speculative Masked Diffusions Authors: Andrew Campbell, Valentin De Bortoli, Jiaxin Shi, Arnaud Doucet Published: 2025-10-04 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.03929v2 We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate samples. Standard masked diffusion models predict factorized logits over currently masked positions. A number of masked positions are then sampled, however, the factorization approximation means that sampling too many positions in one go leads to poor sample quality. As a result, many simulation steps and therefore neural network function evaluations are required to generate high-quality data. We reduce the computational burden by generating non-factorized predictions over masked positions. This is achieved by modifying the final transformer attention mask from non-causal to causal, enabling draft token generation and parallel validation via a novel, model-integrated speculative sampling mechanism. This results in a non-factorized predictive distribution over masked positions in a single forward pass. We apply our method to GPT2 scale text modelling and protein sequence generation, finding that we can achieve a ~2x reduction in the required number of network forward passes relative to standard masked diffusion models. --- ### Sliding Window Attention for Learned Video Compression Authors: Alexander Kopte, André Kaup Published: 2025-10-04 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2510.03926v1 To manage the complexity of transformers in video compression, local attention mechanisms are a practical necessity. The common approach of partitioning frames into patches, however, creates architectural flaws like irregular receptive fields. When adapted for temporal autoregressive models, this paradigm, exemplified by the Video Compression Transformer (VCT), also necessitates computationally redundant overlapping windows. This work introduces 3D Sliding Window Attention (SWA), a patchless form of local attention. By enabling a decoder-only architecture that unifies spatial and temporal context processing, and by providing a uniform receptive field, our method significantly improves rate-distortion performance, achieving Bjørntegaard Delta-rate savings of up to 18.6 % against the VCT baseline. Simultaneously, by eliminating the need for overlapping windows, our method reduces overall decoder complexity by a factor of 2.8, while its entropy model is nearly 3.5 times more efficient. We further analyze our model's behavior and show that while it benefits from long-range temporal context, excessive context can degrade performance. --- ### On the Convergence and Size Transferability of Continuous-depth Graph Neural Networks Authors: Mingsong Yan, Charles Kulick, Sui Tang Published: 2025-10-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.03923v2 Continuous-depth graph neural networks, also known as Graph Neural Differential Equations (GNDEs), combine the structural inductive bias of Graph Neural Networks (GNNs) with the continuous-depth architecture of Neural ODEs, offering a scalable and principled framework for modeling dynamics on graphs. In this paper, we present a rigorous convergence analysis of GNDEs with time-varying parameters in the infinite-node limit, providing theoretical insights into their size transferability. To this end, we introduce Graphon Neural Differential Equations (Graphon-NDEs) as the infinite-node limit of GNDEs and establish their well-posedness. Leveraging tools from graphon theory and dynamical systems, we prove the trajectory-wise convergence of GNDE solutions to Graphon-NDE solutions. Moreover, we derive explicit convergence rates under two deterministic graph sampling regimes: (1) weighted graphs sampled from smooth graphons, and (2) unweighted graphs sampled from $\{0,1\}$-valued (discontinuous) graphons. We further establish size transferability bounds, providing theoretical justification for the practical strategy of transferring GNDE models trained on moderate-sized graphs to larger, structurally similar graphs without retraining. Numerical experiments using synthetic and real data support our theoretical findings. --- ### Talking Tennis: Language Feedback from 3D Biomechanical Action Recognition Authors: Arushi Dashore, Aryan Anumala, Emily Hui, Olivia Yang Published: 2025-10-04 Categories: cs.CV, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2510.03921v1 Automated tennis stroke analysis has advanced significantly with the integration of biomechanical motion cues alongside deep learning techniques, enhancing stroke classification accuracy and player performance evaluation. Despite these advancements, existing systems often fail to connect biomechanical insights with actionable language feedback that is both accessible and meaningful to players and coaches. This research project addresses this gap by developing a novel framework that extracts key biomechanical features (such as joint angles, limb velocities, and kinetic chain patterns) from motion data using Convolutional Neural Network Long Short-Term Memory (CNN-LSTM)-based models. These features are analyzed for relationships influencing stroke effectiveness and injury risk, forming the basis for feedback generation using large language models (LLMs). Leveraging the THETIS dataset and feature extraction techniques, our approach aims to produce feedback that is technically accurate, biomechanically grounded, and actionable for end-users. The experimental setup evaluates this framework on classification performance and interpretability, bridging the gap between explainable AI and sports biomechanics. --- ### Transductive and Learning-Augmented Online Regression Authors: Vinod Raman, Shenghao Xie, Samson Zhou Published: 2025-10-04 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2510.03917v1 Motivated by the predictable nature of real-life in data streams, we study online regression when the learner has access to predictions about future examples. In the extreme case, called transductive online learning, the sequence of examples is revealed to the learner before the game begins. For this setting, we fully characterize the minimax expected regret in terms of the fat-shattering dimension, establishing a separation between transductive online regression and (adversarial) online regression. Then, we generalize this setting by allowing for noisy or \emph{imperfect} predictions about future examples. Using our results for the transductive online setting, we develop an online learner whose minimax expected regret matches the worst-case regret, improves smoothly with prediction quality, and significantly outperforms the worst-case regret when future example predictions are precise, achieving performance similar to the transductive online learner. This enables learnability for previously unlearnable classes under predictable examples, aligning with the broader learning-augmented model paradigm. --- ### OpenFLAME: Federated Visual Positioning System to Enable Large-Scale Augmented Reality Applications Authors: Sagar Bharadwaj, Harrison Williams, Luke Wang, Michael Liang, Tao Jin, Srinivasan Seshan, Anthony Rowe Published: 2025-10-04 Categories: cs.CV, cs.DC, cs.RO arXiv: https://arxiv.org/abs/2510.03915v1 World-scale augmented reality (AR) applications need a ubiquitous 6DoF localization backend to anchor content to the real world consistently across devices. Large organizations such as Google and Niantic are 3D scanning outdoor public spaces in order to build their own Visual Positioning Systems (VPS). These centralized VPS solutions fail to meet the needs of many future AR applications -- they do not cover private indoor spaces because of privacy concerns, regulations, and the labor bottleneck of updating and maintaining 3D scans. In this paper, we present OpenFLAME, a federated VPS backend that allows independent organizations to 3D scan and maintain a separate VPS service for their own spaces. This enables access control of indoor 3D scans, distributed maintenance of the VPS backend, and encourages larger coverage. Sharding of VPS services introduces several unique challenges -- coherency of localization results across spaces, quality control of VPS services, selection of the right VPS service for a location, and many others. We introduce the concept of federated image-based localization and provide reference solutions for managing and merging data across maps without sharing private data. --- ### Refactoring with LLMs: Bridging Human Expertise and Machine Understanding Authors: Yonnel Chen Kuang Piao, Jean Carlors Paul, Leuson Da Silva, Arghavan Moradi Dakhel, Mohammad Hamdaqa, Foutse Khomh Published: 2025-10-04 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.03914v1 Code refactoring is a fundamental software engineering practice aimed at improving code quality and maintainability. Despite its importance, developers often neglect refactoring due to the significant time, effort, and resources it requires, as well as the lack of immediate functional rewards. Although several automated refactoring tools have been proposed, they remain limited in supporting a broad spectrum of refactoring types. In this study, we explore whether instruction strategies inspired by human best-practice guidelines can enhance the ability of Large Language Models (LLMs) to perform diverse refactoring tasks automatically. Leveraging the instruction-following and code comprehension capabilities of state-of-the-art LLMs (e.g., GPT-mini and DeepSeek-V3), we draw on Martin Fowler's refactoring guidelines to design multiple instruction strategies that encode motivations, procedural steps, and transformation objectives for 61 well-known refactoring types. We evaluate these strategies on benchmark examples and real-world code snippets from GitHub projects. Our results show that instruction designs grounded in Fowler's guidelines enable LLMs to successfully perform all benchmark refactoring types and preserve program semantics in real-world settings, an essential criterion for effective refactoring. Moreover, while descriptive instructions are more interpretable to humans, our results show that rule-based instructions often lead to better performance in specific scenarios. Interestingly, allowing models to focus on the overall goal of refactoring, rather than prescribing a fixed transformation type, can yield even greater improvements in code quality. --- ### PsycholexTherapy: Simulating Reasoning in Psychotherapy with Small Language Models in Persian Authors: Mohammad Amin Abbasi, Hassan Naderi Published: 2025-10-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.03913v1 This study presents PsychoLexTherapy, a framework for simulating psychotherapeutic reasoning in Persian using small language models (SLMs). The framework tackles the challenge of developing culturally grounded, therapeutically coherent dialogue systems with structured memory for multi-turn interactions in underrepresented languages. To ensure privacy and feasibility, PsychoLexTherapy is optimized for on-device deployment, enabling use without external servers. Development followed a three-stage process: (i) assessing SLMs psychological knowledge with PsychoLexEval; (ii) designing and implementing the reasoning-oriented PsychoLexTherapy framework; and (iii) constructing two evaluation datasets-PsychoLexQuery (real Persian user questions) and PsychoLexDialogue (hybrid simulated sessions)-to benchmark against multiple baselines. Experiments compared simple prompting, multi-agent debate, and structured therapeutic reasoning paths. Results showed that deliberate model selection balanced accuracy, efficiency, and privacy. On PsychoLexQuery, PsychoLexTherapy outperformed all baselines in automatic LLM-as-a-judge evaluation and was ranked highest by human evaluators in a single-turn preference study. In multi-turn tests with PsychoLexDialogue, the long-term memory module proved essential: while naive history concatenation caused incoherence and information loss, the full framework achieved the highest ratings in empathy, coherence, cultural fit, and personalization. Overall, PsychoLexTherapy establishes a practical, privacy-preserving, and culturally aligned foundation for Persian psychotherapy simulation, contributing novel datasets, a reproducible evaluation pipeline, and empirical insights into structured memory for therapeutic reasoning. --- ### Generalized Fitted Q-Iteration with Clustered Data Authors: Liyuan Hu, Jitao Wang, Zhenke Wu, Chengchun Shi Published: 2025-10-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.03912v1 This paper focuses on reinforcement learning (RL) with clustered data, which is commonly encountered in healthcare applications. We propose a generalized fitted Q-iteration (FQI) algorithm that incorporates generalized estimating equations into policy learning to handle the intra-cluster correlations. Theoretically, we demonstrate (i) the optimalities of our Q-function and policy estimators when the correlation structure is correctly specified, and (ii) their consistencies when the structure is mis-specified. Empirically, through simulations and analyses of a mobile health dataset, we find the proposed generalized FQI achieves, on average, a half reduction in regret compared to the standard FQI. --- ### THEMIS: Unlocking Pretrained Knowledge with Foundation Model Embeddings for Anomaly Detection in Time Series Authors: Yadav Mahesh Lorik, Kaushik Sarveswaran, Nagaraj Sundaramahalingam, Aravindakumar Venugopalan Published: 2025-10-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.03911v1 Time series anomaly detection forms a very crucial area in several domains but poses substantial challenges. Due to time series data possessing seasonality, trends, noise, and evolving patterns (concept drift), it becomes very difficult to set a general notion of what constitutes normal behavior. Anomalies themselves could be varied, ranging from a single outlier to contextual or collective anomalies, and are normally very rare; hence, the dataset is largely imbalanced. Additional layers of complexities arise due to the problems of increased dimensionality of modern time series, real-time detection criteria, setting up appropriate detection thresholds, and arriving at results that are interpretable. To embrace these multifaceted challenges, very strong, flexible, and interpretable approaches are required. This paper presents THEMIS, a new framework for time series anomaly detection that exploits pretrained knowledge from foundation models. THEMIS extracts embeddings from the encoder of the Chronos time series foundation model and applies outlier detection techniques like Local Outlier Factor and Spectral Decomposition on the self-similarity matrix, to spot anomalies in the data. Our experiments show that this modular method achieves SOTA results on the MSL dataset and performs quite competitively on the SMAP and SWAT$^*$ datasets. Notably, THEMIS exceeds models trained specifically for anomaly detection, presenting hyperparameter robustness and interpretability by default. This paper advocates for pretrained representations from foundation models for performing efficient and adaptable anomaly detection for time series data. --- ### Generating Human Motion Videos using a Cascaded Text-to-Video Framework Authors: Hyelin Nam, Hyojun Go, Byeongjun Park, Byung-Hoon Kim, Hyungjin Chung Published: 2025-10-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.03909v1 Human video generation is becoming an increasingly important task with broad applications in graphics, entertainment, and embodied AI. Despite the rapid progress of video diffusion models (VDMs), their use for general-purpose human video generation remains underexplored, with most works constrained to image-to-video setups or narrow domains like dance videos. In this work, we propose CAMEO, a cascaded framework for general human motion video generation. It seamlessly bridges Text-to-Motion (T2M) models and conditional VDMs, mitigating suboptimal factors that may arise in this process across both training and inference through carefully designed components. Specifically, we analyze and prepare both textual prompts and visual conditions to effectively train the VDM, ensuring robust alignment between motion descriptions, conditioning signals, and the generated videos. Furthermore, we introduce a camera-aware conditioning module that connects the two stages, automatically selecting viewpoints aligned with the input text to enhance coherence and reduce manual intervention. We demonstrate the effectiveness of our approach on both the MovieGen benchmark and a newly introduced benchmark tailored to the T2M-VDM combination, while highlighting its versatility across diverse use cases. ---