# Research Papers — 2025-10 · bundle page 43 of 217 > Full-text markdown of papers #2101–2150 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/43 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/42.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/44.md) ### Uncertainty quantification in model discovery by distilling interpretable material constitutive models from Gaussian process posteriors Authors: David Anton, Henning Wessels, Ulrich Römer, Alexander Henkes, Jorge-Humberto Urrea-Quintero Published: 2025-10-25 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.22345v2 Constitutive model discovery refers to the task of identifying an appropriate model structure, usually from a predefined model library, while simultaneously inferring its material parameters. The data used for model discovery are measured in mechanical tests and are thus inevitably affected by noise which, in turn, induces uncertainties. Previously proposed methods for uncertainty quantification in model discovery either require the selection of a prior for the material parameters, are restricted to linear coefficients of the model library or are limited in the flexibility of the inferred parameter probability distribution. We therefore propose a partially Bayesian framework for uncertainty quantification in model discovery that does not require prior selection for the material parameters and also allows for the discovery of constitutive models with inner-non-linear parameters: First, we augment the available stress-deformation data with a Gaussian process. Second, we approximate the parameter distribution by a normalizing flow, which allows for modeling complex joint distributions. Third, we distill the parameter distribution by matching the distribution of stress-deformation functions induced by the parameters with the Gaussian process posterior. Fourth, we perform a Sobol' sensitivity analysis to obtain a sparse and interpretable model. We demonstrate the capability of our framework for both isotropic and experimental anisotropic data. --- ### FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented Generation Authors: Mohammad Aghajani Asl, Majid Asgari-Bidhendi, Behrooz Minaei-Bidgoli Published: 2025-10-25 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2510.22344v1 While Retrieval-Augmented Generation (RAG) mitigates hallucination and knowledge staleness in Large Language Models (LLMs), existing frameworks often falter on complex, multi-hop queries that require synthesizing information from disparate sources. Current advanced RAG methods, employing iterative or adaptive strategies, lack a robust mechanism to systematically identify and fill evidence gaps, often propagating noise or failing to gather a comprehensive context. We introduce FAIR-RAG, a novel agentic framework that transforms the standard RAG pipeline into a dynamic, evidence-driven reasoning process. At its core is an Iterative Refinement Cycle governed by a module we term Structured Evidence Assessment (SEA). The SEA acts as an analytical gating mechanism: it deconstructs the initial query into a checklist of required findings and audits the aggregated evidence to identify confirmed facts and, critically, explicit informational gaps. These gaps provide a precise signal to an Adaptive Query Refinement agent, which generates new, targeted sub-queries to retrieve missing information. This cycle repeats until the evidence is verified as sufficient, ensuring a comprehensive context for a final, strictly faithful generation. We conducted experiments on challenging multi-hop QA benchmarks, including HotpotQA, 2WikiMultiHopQA, and MusiQue. In a unified experimental setup, FAIR-RAG significantly outperforms strong baselines. On HotpotQA, it achieves an F1-score of 0.453 -- an absolute improvement of 8.3 points over the strongest iterative baseline -- establishing a new state-of-the-art for this class of methods on these benchmarks. Our work demonstrates that a structured, evidence-driven refinement process with explicit gap analysis is crucial for unlocking reliable and accurate reasoning in advanced RAG systems for complex, knowledge-intensive tasks. --- ### DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry Authors: Changti Wu, Shijie Lian, Zihao Liu, Lei Zhang, Laurence Tianruo Yang, Kai Chen Published: 2025-10-25 Categories: cs.AI, cs.CL, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.22340v2 Solid geometry problem solving demands spatial mathematical reasoning that integrates spatial intelligence and symbolic reasoning. However, most existing multimodal mathematical reasoning benchmarks focus primarily on 2D plane geometry, rely on static datasets prone to data contamination and memorization, and evaluate models solely by final answers, overlooking the reasoning process. To address these limitations, we introduce DynaSolidGeo, the first dynamic benchmark for evaluating genuine spatial reasoning in Vision-Language Models (VLMs). Constructed through a semi-automatic annotation pipeline, DynaSolidGeo contains 503 expert-curated seed questions that can, in principle, dynamically generate an unbounded number of diverse multimodal text-visual instances. Beyond answer accuracy, we incorporate process evaluation based on expert-annotated reasoning chains to measure logical validity and causal coherence. Experiments across representative open-source and closed-source VLMs reveal large performance gaps, severe degradation in dynamic settings, and poor performance on tasks requiring high-level spatial intelligence, such as mental rotation and visualization. The code and dataset are available at \href{https://zgca-ai4edu.github.io/DynaSolidGeo/}{DynaSolidGeo}. --- ### GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation Authors: Phillip Mueller, Talip Uenlue, Sebastian Schmidt, Marcel Kollovieh, Jiajie Fan, Stephan Guennemann, Lars Mikelsons Published: 2025-10-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.22337v1 Precise geometric control in image generation is essential for engineering \& product design and creative industries to control 3D object features accurately in image space. Traditional 3D editing approaches are time-consuming and demand specialized skills, while current image-based generative methods lack accuracy in geometric conditioning. To address these challenges, we propose GeoDiffusion, a training-free framework for accurate and efficient geometric conditioning of 3D features in image generation. GeoDiffusion employs a class-specific 3D object as a geometric prior to define keypoints and parametric correlations in 3D space. We ensure viewpoint consistency through a rendered image of a reference 3D object, followed by style transfer to meet user-defined appearance specifications. At the core of our framework is GeoDrag, improving accuracy and speed of drag-based image editing on geometry guidance tasks and general instructions on DragBench. Our results demonstrate that GeoDiffusion enables precise geometric modifications across various iterative design workflows. --- ### Toward Humanoid Brain-Body Co-design: Joint Optimization of Control and Morphology for Fall Recovery Authors: Bo Yue, Sheng Xu, Kui Jia, Guiliang Liu Published: 2025-10-25 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2510.22336v2 Humanoid robots represent a central frontier in embodied intelligence, as their anthropomorphic form enables natural deployment in humans' workspace. Brain-body co-design for humanoids presents a promising approach to realizing this potential by jointly optimizing control policies and physical morphology. Within this context, fall recovery emerges as a critical capability. It not only enhances safety and resilience but also integrates naturally with locomotion systems, thereby advancing the autonomy of humanoids. In this paper, we propose RoboCraft, a scalable humanoid co-design framework for fall recovery that iteratively improves performance through the coupled updates of control policy and morphology. A shared policy pretrained across multiple designs is progressively finetuned on high-performing morphologies, enabling efficient adaptation without retraining from scratch. Concurrently, morphology search is guided by human-inspired priors and optimization algorithms, supported by a priority buffer that balances reevaluation of promising candidates with the exploration of novel designs. Experiments show that RoboCraft achieves an average performance gain of 44.55% on seven public humanoid robots, with morphology optimization drives at least 40% of improvements in co-designing four humanoid robots, underscoring the critical role of humanoid co-design. --- ### Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction Authors: Xu Zhang, Ruijie Quan, Wenguan Wang, Yi Yang Published: 2025-10-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.22335v2 Reconstructing visual stimuli from fMRI signals is a central challenge bridging machine learning and neuroscience. Recent diffusion-based methods typically map fMRI activity to a single neural embedding, using it as static guidance throughout the entire generation process. However, this fixed guidance collapses hierarchical neural information and is misaligned with the stage-dependent demands of image reconstruction. In response, we propose MindHier, a coarse-to-fine fMRI-to-image reconstruction framework built on scale-wise autoregressive modeling. MindHier introduces three components: a Hierarchical fMRI Encoder to extract multi-level neural embeddings, a Hierarchy-to-Hierarchy Alignment scheme to enforce layer-wise correspondence with CLIP features, and a Scale-Aware Coarse-to-Fine Neural Guidance strategy to inject these embeddings into autoregression at matching scales. These designs make MindHier an efficient and cognitively aligned alternative to diffusion-based methods by enabling a hierarchical reconstruction process that synthesizes global semantics before refining local details, akin to human visual perception. Extensive experiments on the NSD dataset show that MindHier achieves superior semantic fidelity, 4.67$\times$ faster inference, and more deterministic results than the diffusion-based baselines. --- ### Multilingual Target-Stance Extraction Authors: Ethan Mines, Bonnie Dorr Published: 2025-10-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.22334v1 Social media enables data-driven analysis of public opinion on contested issues. Target-Stance Extraction (TSE) is the task of identifying the target discussed in a document and the document's stance towards that target. Many works classify stance towards a given target in a multilingual setting, but all prior work in TSE is English-only. This work introduces the first multilingual TSE benchmark, spanning Catalan, Estonian, French, Italian, Mandarin, and Spanish corpora. It manages to extend the original TSE pipeline to a multilingual setting without requiring separate models for each language. Our model pipeline achieves a modest F1 score of 12.78, underscoring the increased difficulty of the multilingual task relative to English-only setups and highlighting target prediction as the primary bottleneck. We are also the first to demonstrate the sensitivity of TSE's F1 score to different target verbalizations. Together these serve as a much-needed baseline for resources, algorithms, and evaluation criteria in multilingual TSE. --- ### LIFT: Interpretable truck driving risk prediction with literature-informed fine-tuned LLMs Authors: Xiao Hu, Yuansheng Lian, Ke Zhang, Yunxuan Li, Yuelong Su, Meng Li Published: 2025-10-25 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.22333v1 This study proposes an interpretable prediction framework with literature-informed fine-tuned (LIFT) LLMs for truck driving risk prediction. The framework integrates an LLM-driven Inference Core that predicts and explains truck driving risk, a Literature Processing Pipeline that filters and summarizes domain-specific literature into a literature knowledge base, and a Result Evaluator that evaluates the prediction performance as well as the interpretability of the LIFT LLM. After fine-tuning on a real-world truck driving risk dataset, the LIFT LLM achieved accurate risk prediction, outperforming benchmark models by 26.7% in recall and 10.1% in F1-score. Furthermore, guided by the literature knowledge base automatically constructed from 299 domain papers, the LIFT LLM produced variable importance ranking consistent with that derived from the benchmark model, while demonstrating robustness in interpretation results to various data sampling conditions. The LIFT LLM also identified potential risky scenarios by detecting key combination of variables in truck driving risk, which were verified by PERMANOVA tests. Finally, we demonstrated the contribution of the literature knowledge base and the fine-tuning process in the interpretability of the LIFT LLM, and discussed the potential of the LIFT LLM in data-driven knowledge discovery. --- ### Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders Authors: Mengyu Ye, Jun Suzuki, Tatsuro Inaba, Tatsuki Kuribayashi Published: 2025-10-25 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.22332v1 Recent interpretability work on large language models (LLMs) has been increasingly dominated by a feature-discovery approach with the help of proxy modules. Then, the quality of features learned by, e.g., sparse auto-encoders (SAEs), is evaluated. This paradigm naturally raises a critical question: do such learned features have better properties than those already represented within the original model parameters, and unfortunately, only a few studies have made such comparisons systematically so far. In this work, we revisit the interpretability of feature vectors stored in feed-forward (FF) layers, given the perspective of FF as key-value memories, with modern interpretability benchmarks. Our extensive evaluation revealed that SAE and FFs exhibits a similar range of interpretability, although SAEs displayed an observable but minimal improvement in some aspects. Furthermore, in certain aspects, surprisingly, even vanilla FFs yielded better interpretability than the SAEs, and features discovered in SAEs and FFs diverged. These bring questions about the advantage of SAEs from both perspectives of feature quality and faithfulness, compared to directly interpreting FF feature vectors, and FF key-value parameters serve as a strong baseline in modern interpretability research. --- ### Graph-Coarsening Approach for the Capacitated Vehicle Routing Problem with Time Windows Authors: Mustafa Mert Özyılmaz Published: 2025-10-25 Categories: cs.AI, math.OC arXiv: https://arxiv.org/abs/2510.22329v2 The Capacitated Vehicle Routing Problem with Time Windows (CVRPTW) is a fundamental NP-hard optimization problem in logistics. Solving large-scale instances remains computationally challenging for exact solvers. This paper introduces a multilevel graph coarsening and refinement strategy that aggregates customers into meta-nodes based on a spatio-temporal distance metric. The reduced problem is solved using both classical heuristics and quantum annealing hardware, then expanded back into the original space with arrival times recomputed and constraint violations recorded. Comprehensive experiments on Solomon benchmarks demonstrate that our method significantly reduces computation time while preserving solution quality for classical heuristics. For quantum solvers, experiments across all 56 Solomon instances at $N=5$ and $N=10$ customers show that coarsening consistently reduces computation time and, on clustered (C-type) instances, simultaneously reduces vehicle count and route duration with no feasibility loss. Coarsening effectiveness is strongly instance-structure dependent: C-type instances achieve %100 post-coarsening feasibility with measurable quality improvements, while narrow-window random (R-type) instances present structural constraints that limit achievable coarsening depth. --- ### Monitoring State Transitions in Markovian Systems with Sampling Cost Authors: Kumar Saurav, Ness B. Shroff, Yingbin Liang Published: 2025-10-25 Categories: cs.LG, cs.IT, stat.ML arXiv: https://arxiv.org/abs/2510.22327v1 We consider a node-monitor pair, where the node's state varies with time. The monitor needs to track the node's state at all times; however, there is a fixed cost for each state query. So the monitor may instead predict the state using time-series forecasting methods, including time-series foundation models (TSFMs), and query only when prediction uncertainty is high. Since query decisions influence prediction accuracy, determining when to query is nontrivial. A natural approach is a greedy policy that predicts when the expected prediction loss is below the query cost and queries otherwise. We analyze this policy in a Markovian setting, where the optimal (OPT) strategy is a state-dependent threshold policy minimizing the time-averaged sum of query cost and prediction losses. We show that, in general, the greedy policy is suboptimal and can have an unbounded competitive ratio, but under common conditions such as identically distributed transition probabilities, it performs close to OPT. For the case of unknown transition probabilities, we further propose a projected stochastic gradient descent (PSGD)-based learning variant of the greedy policy, which achieves a favorable predict-query tradeoff with improved computational efficiency compared to OPT. --- ### Beyond Augmentation: Leveraging Inter-Instance Relation in Self-Supervised Representation Learning Authors: Ali Javidani, Babak Nadjar Araabi, Mohammad Amin Sadeghi Published: 2025-10-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.22322v1 This paper introduces a novel approach that integrates graph theory into self-supervised representation learning. Traditional methods focus on intra-instance variations generated by applying augmentations. However, they often overlook important inter-instance relationships. While our method retains the intra-instance property, it further captures inter-instance relationships by constructing k-nearest neighbor (KNN) graphs for both teacher and student streams during pretraining. In these graphs, nodes represent samples along with their latent representations. Edges encode the similarity between instances. Following pretraining, a representation refinement phase is performed. In this phase, Graph Neural Networks (GNNs) propagate messages not only among immediate neighbors but also across multiple hops, thereby enabling broader contextual integration. Experimental results on CIFAR-10, ImageNet-100, and ImageNet-1K demonstrate accuracy improvements of 7.3%, 3.2%, and 1.0%, respectively, over state-of-the-art methods. These results highlight the effectiveness of the proposed graph based mechanism. The code is publicly available at https://github.com/alijavidani/SSL-GraphNNCLR. --- ### GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping Authors: Jing Wang, Jiajun Liang, Jie Liu, Henglin Liu, Gongye Liu, Jun Zheng, Wanyuan Pang, Ao Ma, Zhenyu Xie, Xintao Wang, Meng Wang, Pengfei Wan et al. Published: 2025-10-25 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.22319v2 Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. Within these frameworks, the policy update relies on importance-ratio clipping to constrain overconfident positive and negative gradients. However, in practice, we observe a systematic shift in the importance-ratio distribution-its mean falls below 1 and its variance differs substantially across timesteps. This left-shifted and inconsistent distribution prevents positive-advantage samples from entering the clipped region, causing the mechanism to fail in constraining overconfident positive updates. As a result, the policy model inevitably enters an implicit over-optimization stage-while the proxy reward continues to increase, essential metrics such as image quality and text-prompt alignment deteriorate sharply, ultimately making the learned policy impractical for real-world use. To address this issue, we introduce GRPO-Guard, a simple yet effective enhancement to existing GRPO frameworks. Our method incorporates ratio normalization, which restores a balanced and step-consistent importance ratio, ensuring that PPO clipping properly constrains harmful updates across denoising timesteps. In addition, a gradient reweighting strategy equalizes policy gradients over noise conditions, preventing excessive updates from particular timestep regions. Together, these designs act as a regulated clipping mechanism, stabilizing optimization and substantially mitigating implicit over-optimization without relying on heavy KL regularization. Extensive experiments on multiple diffusion backbones (e.g., SD3.5M, Flux.1-dev) and diverse proxy tasks demonstrate that GRPO-Guard significantly reduces over-optimization while maintaining or even improving generation quality. --- ### Harnessing the Power of Large Language Models for Software Testing Education: A Focus on ISTQB Syllabus Authors: Tuan-Phong Ngo, Bao-Ngoc Duong, Tuan-Anh Hoang, Joshua Dwight, Ushik Shrestha Khwakhali Published: 2025-10-25 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.22318v1 Software testing is a critical component in the software engineering field and is important for software engineering education. Thus, it is vital for academia to continuously improve and update educational methods to reflect the current state of the field. The International Software Testing Qualifications Board (ISTQB) certification framework is globally recognized and widely adopted in industry and academia. However, ISTQB-based learning has been rarely applied with recent generative artificial intelligence advances. Despite the growing capabilities of large language models (LLMs), ISTQB-based learning and instruction with LLMs have not been thoroughly explored. This paper explores and evaluates how LLMs can complement the ISTQB framework for higher education. The findings present four key contributions: (i) the creation of a comprehensive ISTQB-aligned dataset spanning over a decade, consisting of 28 sample exams and 1,145 questions; (ii) the development of a domain-optimized prompt that enhances LLM precision and explanation quality on ISTQB tasks; (iii) a systematic evaluation of state-of-the-art LLMs on this dataset; and (iv) actionable insights and recommendations for integrating LLMs into software testing education. These findings highlight the promise of LLMs in supporting ISTQB certification preparation and offer a foundation for their broader use in software engineering at higher education. --- ### Memory-based Language Models: An Efficient, Explainable, and Eco-friendly Approach to Large Language Modeling Authors: Antal van den Bosch, Ainhoa Risco Patón, Teun Buijse, Peter Berck, Maarten van Gompel Published: 2025-10-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.22317v1 We present memory-based language modeling as an efficient, eco-friendly alternative to deep neural network-based language modeling. It offers log-linearly scalable next-token prediction performance and strong memorization capabilities. Implementing fast approximations of k-nearest neighbor classification, memory-based language modeling leaves a relatively small ecological footprint both in training and in inference mode, as it relies fully on CPUs and attains low token latencies. Its internal workings are simple and fully transparent. We compare our implementation of memory-based language modeling, OLIFANT, with GPT-2 and GPT-Neo on next-token prediction accuracy, estimated emissions and speeds, and offer some deeper analyses of the model. --- ### LacMaterial: Large Language Models as Analogical Chemists for Materials Discovery Authors: Hongyu Guo Published: 2025-10-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.22312v1 Analogical reasoning, the transfer of relational structures across contexts (e.g., planet is to sun as electron is to nucleus), is fundamental to scientific discovery. Yet human insight is often constrained by domain expertise and surface-level biases, limiting access to deeper, structure-driven analogies both within and across disciplines. Large language models (LLMs), trained on vast cross-domain data, present a promising yet underexplored tool for analogical reasoning in science. Here, we demonstrate that LLMs can generate novel battery materials by (1) retrieving cross-domain analogs and analogy-guided exemplars to steer exploration beyond conventional dopant substitutions, and (2) constructing in-domain analogical templates from few labeled examples to guide targeted exploitation. These explicit analogical reasoning strategies yield candidates outside established compositional spaces and outperform standard prompting baselines. Our findings position LLMs as interpretable, expert-like hypothesis generators that leverage analogy-driven generalization for scientific innovation. --- ### AnyECG-Lab: An Exploration Study of Fine-tuning an ECG Foundation Model to Estimate Laboratory Values from Single-Lead ECG Signals Authors: Yujie Xiao, Gongzhen Tang, Wenhui Liu, Jun Li, Guangkun Nie, Zhuoran Kan, Deyun Zhang, Qinghao Zhao, Shenda Hong Published: 2025-10-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.22301v1 Timely access to laboratory values is critical for clinical decision-making, yet current approaches rely on invasive venous sampling and are intrinsically delayed. Electrocardiography (ECG), as a non-invasive and widely available signal, offers a promising modality for rapid laboratory estimation. Recent progress in deep learning has enabled the extraction of latent hematological signatures from ECGs. However, existing models are constrained by low signal-to-noise ratios, substantial inter-individual variability, limited data diversity, and suboptimal generalization, especially when adapted to low-lead wearable devices. In this work, we conduct an exploratory study leveraging transfer learning to fine-tune ECGFounder, a large-scale pre-trained ECG foundation model, on the Multimodal Clinical Monitoring in the Emergency Department (MC-MED) dataset from Stanford. We generated a corpus of more than 20 million standardized ten-second ECG segments to enhance sensitivity to subtle biochemical correlates. On internal validation, the model demonstrated strong predictive performance (area under the curve above 0.65) for thirty-three laboratory indicators, moderate performance (between 0.55 and 0.65) for fifty-nine indicators, and limited performance (below 0.55) for sixteen indicators. This study provides an efficient artificial-intelligence driven solution and establishes the feasibility scope for real-time, non-invasive estimation of laboratory values. --- ### T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model Authors: Chenyu Zhang, Tairen Zhang, Lanjun Wang, Ruidong Chen, Wenhui Li, Anan Liu Published: 2025-10-25 Categories: cs.CR, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2510.22300v2 Using risky text prompts, such as pornography and violent prompts, to test the safety of text-to-image (T2I) models is a critical task. However, existing risky prompt datasets are limited in three key areas: 1) limited risky categories, 2) coarse-grained annotation, and 3) low effectiveness. To address these limitations, we introduce T2I-RiskyPrompt, a comprehensive benchmark designed for evaluating safety-related tasks in T2I models. Specifically, we first develop a hierarchical risk taxonomy, which consists of 6 primary categories and 14 fine-grained subcategories. Building upon this taxonomy, we construct a pipeline to collect and annotate risky prompts. Finally, we obtain 6,432 effective risky prompts, where each prompt is annotated with both hierarchical category labels and detailed risk reasons. Moreover, to facilitate the evaluation, we propose a reason-driven risky image detection method that explicitly aligns the MLLM with safety annotations. Based on T2I-RiskyPrompt, we conduct a comprehensive evaluation of eight T2I models, nine defense methods, five safety filters, and five attack strategies, offering nine key insights into the strengths and limitations of T2I model safety. Finally, we discuss potential applications of T2I-RiskyPrompt across various research fields. The dataset and code are provided in https://github.com/datar001/T2I-RiskyPrompt. --- ### Stable neural networks and connections to continuous dynamical systems Authors: Matthias J. Ehrhardt, Davide Murari, Ferdia Sherry Published: 2025-10-25 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2510.22299v1 The existence of instabilities, for example in the form of adversarial examples, has given rise to a highly active area of research concerning itself with understanding and enhancing the stability of neural networks. We focus on a popular branch within this area which draws on connections to continuous dynamical systems and optimal control, giving a bird's eye view of this area. We identify and describe the fundamental concepts that underlie much of the existing work in this area. Following this, we go into more detail on a specific approach to designing stable neural networks, developing the theoretical background and giving a description of how these networks can be implemented. We provide code that implements the approach that can be adapted and extended by the reader. The code further includes a notebook with a fleshed-out toy example on adversarial robustness of image classification that can be run without heavy requirements on the reader's computer. We finish by discussing this toy example so that the reader can interactively follow along on their computer. This work will be included as a chapter of a book on scientific machine learning, which is currently under revision and aimed at students. --- ### MetaCaDI: A Meta-Learning Framework for Causal Discovery from Multiple Environments with Unknown Interventions Authors: Hans Jarett Ong, Yoichi Chikahara, Tomoharu Iwata Published: 2025-10-25 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.22298v2 Uncovering the causal mechanisms of complex real-world systems remains a significant challenge, as these systems often entail high data collection costs and involve unknown interventions. We introduce MetaCaDI, the first framework to cast the identification of unknown interventions as a meta-learning problem, explicitly leveraging a jointly learned causal graph. MetaCaDI is a Bayesian framework that learns a shared causal structure across multiple environments and is optimized to rapidly adapt to new, few-shot intervention target identification tasks. A key innovation is our model's analytical adaptation, which uses a closed-form solution to bypass expensive and potentially unstable gradient-based bilevel optimization. Extensive experiments on synthetic and complex gene expression data demonstrate that MetaCaDI significantly outperforms state-of-the-art methods. It excels at identifying intervention targets from as few as 3 samples - where existing methods collapse to random chance - while robustly recovering the shared causal graph, proving its effectiveness in data-scarce scenarios. --- ### VietLyrics: A Large-Scale Dataset and Models for Vietnamese Automatic Lyrics Transcription Authors: Quoc Anh Nguyen, Bernard Cheng, Kelvin Soh Published: 2025-10-25 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.22295v2 Automatic Lyrics Transcription (ALT) for Vietnamese music presents unique challenges due to its tonal complexity and dialectal variations, but remains largely unexplored due to the lack of a dedicated dataset. Therefore, we curated the first large-scale Vietnamese ALT dataset (VietLyrics), comprising 647 hours of songs with line-level aligned lyrics and metadata to address these issues. Our evaluation of current ASRbased approaches reveal significant limitations, including frequent transcription errors and hallucinations in non-vocal segments. To improve performance, we fine-tuned Whisper models on the VietLyrics dataset, achieving superior results compared to existing multilingual ALT systems, including LyricWhiz. We publicly release VietLyrics and our models, aiming to advance Vietnamese music computing research while demonstrating the potential of this approach for ALT in low-resource language and music. --- ### Predicting Metabolic Dysfunction-Associated Steatotic Liver Disease using Machine Learning Methods: A Retrospective Cohort Study Authors: Mary E. An, Paul M. Griffin, Jonathan G. Stine, Balakrishnan S. Ramakrishna, Soundar R. T. Kumara Published: 2025-10-25 Categories: cs.LG, cs.CY, q-bio.QM arXiv: https://arxiv.org/abs/2510.22293v4 Background: Metabolic dysfunction-associated steatotic liver disease (MASLD) affects 30-40% of US adults and is the most common chronic liver disease. Although often asymptomatic, progression can lead to cirrhosis. The objective of the study was to develop and evaluate an electronic health record (EHR) based prediction model to support early detection of MASLD in primary care settings. Methods: We evaluated LASSO logistic regression, random forest, XGBoost, and a neural network model for MASLD prediction using clinical feature subsets from a large EHR database, including the top 10 ranked features. To reduce disparities in true positive rates across racial and ethnic subgroups, we applied an equal opportunity postprocessing method in a prediction model called MASLD EHR Static Risk Prediction (MASER). Results: This retrospective cohort study included 59,492 participants in the training data, 24,198 in the validating data, and 25,188 in the testing data. The LASSO logistic regression model with the top 10 features was selected for its interpretability and comparable performance. Before fairness adjustment, the model achieved AUROC of 0.84, accuracy of 78%, sensitivity of 72%, specificity of 79%, and F1-score of 0.617. After equal opportunity postprocessing, accuracy modestly increased to 81% and specificity to 94%, while sensitivity decreased to 41% and F1-score to 0.515, reflecting the fairness trade-off. Conclusions: MASER achieved competitive performance for MASLD prediction, comparable to previously reported ensemble and tree-based models, while using a limited and routinely collected feature set and a diverse study population. The model is designed to support early detection and potential integration into primary care workflows. MASER demonstrates EHR-ready MASLD prediction with fairness adjustments, supporting future primary care implementation pending prospective validation. --- ### Does Homophily Help in Robust Test-time Node Classification? Authors: Yan Jiang, Ruihong Qiu, Zi Huang Published: 2025-10-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.22289v1 Homophily, the tendency of nodes from the same class to connect, is a fundamental property of real-world graphs, underpinning structural and semantic patterns in domains such as citation networks and social networks. Existing methods exploit homophily through designing homophily-aware GNN architectures or graph structure learning strategies, yet they primarily focus on GNN learning with training graphs. However, in real-world scenarios, test graphs often suffer from data quality issues and distribution shifts, such as domain shifts across users from different regions in social networks and temporal evolution shifts in citation network graphs collected over varying time periods. These factors significantly compromise the pre-trained model's robustness, resulting in degraded test-time performance. With empirical observations and theoretical analysis, we reveal that transforming the test graph structure by increasing homophily in homophilic graphs or decreasing it in heterophilic graphs can significantly improve the robustness and performance of pre-trained GNNs on node classifications, without requiring model training or update. Motivated by these insights, a novel test-time graph structural transformation method grounded in homophily, named GrapHoST, is proposed. Specifically, a homophily predictor is developed to discriminate test edges, facilitating adaptive test-time graph structural transformation by the confidence of predicted homophily scores. Extensive experiments on nine benchmark datasets under a range of test-time data quality issues demonstrate that GrapHoST consistently achieves state-of-the-art performance, with improvements of up to 10.92%. Our code has been released at https://github.com/YanJiangJerry/GrapHoST. --- ### Machine Learning Enabled Early Warning System For Financial Distress Using Real-Time Digital Signals Authors: Laxmi pant, Syed Ali Reza, Md Khalilor Rahman, MD Saifur Rahman, Shamima Sharmin, Md Fazlul Huq Mithu, Kazi Nehal Hasnain, Adnan Farabi, Mahamuda khanom, Raisul Kabir Published: 2025-10-25 Categories: cs.LG, cs.CY arXiv: https://arxiv.org/abs/2510.22287v1 The growing instability of both global and domestic economic environments has increased the risk of financial distress at the household level. However, traditional econometric models often rely on delayed and aggregated data, limiting their effectiveness. This study introduces a machine learning-based early warning system that utilizes real-time digital and macroeconomic signals to identify financial distress in near real-time. Using a panel dataset of 750 households tracked over three monitoring rounds spanning 13 months, the framework combines socioeconomic attributes, macroeconomic indicators (such as GDP growth, inflation, and foreign exchange fluctuations), and digital economy measures (including ICT demand and market volatility). Through data preprocessing and feature engineering, we introduce lagged variables, volatility measures, and interaction terms to capture both gradual and sudden changes in financial stability. We benchmark baseline classifiers, such as logistic regression and decision trees, against advanced ensemble models including random forests, XGBoost, and LightGBM. Our results indicate that the engineered features from the digital economy significantly enhance predictive accuracy. The system performs reliably for both binary distress detection and multi-class severity classification, with SHAP-based explanations identifying inflation volatility and ICT demand as key predictors. Crucially, the framework is designed for scalable deployment in national agencies and low-bandwidth regional offices, ensuring it is accessible for policymakers and practitioners. By implementing machine learning in a transparent and interpretable manner, this study demonstrates the feasibility and impact of providing near-real-time early warnings of financial distress. This offers actionable insights that can strengthen household resilience and guide preemptive intervention strategies. --- ### Supervised Fine-Tuning or In-Context Learning? Evaluating LLMs for Clinical NER Authors: Andrei Baroian Published: 2025-10-25 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.22285v1 We study clinical Named Entity Recognition (NER) on the CADEC corpus and compare three families of approaches: (i) BERT-style encoders (BERT Base, BioClinicalBERT, RoBERTa-large), (ii) GPT-4o used with few-shot in-context learning (ICL) under simple vs.\ complex prompts, and (iii) GPT-4o with supervised fine-tuning (SFT). All models are evaluated on standard NER metrics over CADEC's five entity types (ADR, Drug, Disease, Symptom, Finding). RoBERTa-large and BioClinicalBERT offer limited improvements over BERT Base, showing the limit of these family of models. Among LLM settings, simple ICL outperforms a longer, instruction-heavy prompt, and SFT achieves the strongest overall performance (F1 $\approx$ 87.1%), albeit with higher cost. We find that the LLM achieve higher accuracy on simplified tasks, restricting classification to two labels. --- ### Adapting Noise-Driven PUF and AI for Secure WBG ICS: A Proof-of-Concept Study Authors: Devon A. Kelly, Christiana Chamon Published: 2025-10-25 Categories: cs.CR, cs.LG, eess.SY, physics.app-ph arXiv: https://arxiv.org/abs/2510.22283v1 Wide-bandgap (WBG) technologies offer unprecedented improvements in power system efficiency, size, and performance, but also introduce unique sensor corruption and cybersecurity risks in industrial control systems (ICS), particularly due to high-frequency noise and sophisticated cyber-physical threats. This proof-of-concept (PoC) study demonstrates the adaptation of a noise-driven physically unclonable function (PUF) and machine learning (ML)-assisted anomaly detection framework to the demanding environment of WBG-based ICS sensor pathways. By extracting entropy from unavoidable WBG switching noise (up to 100 kHz) as a PUF source, and simultaneously using this noise as a real-time threat indicator, the proposed system unites hardware-level authentication and anomaly detection. Our approach integrates hybrid machine learning (ML) models with adaptive Bayesian filtering, providing robust and low-latency detection capabilities resilient to both natural electromagnetic interference (EMI) and active adversarial manipulation. Through detailed simulations of WBG modules under benign and attack scenarios--including EMI injection, signal tampering, and node impersonation--we achieve 95% detection accuracy and sub-millisecond processing latency. These results demonstrate the feasibility of physics-driven, dual-use noise exploitation as a scalable ICS defense primitive. Our findings lay the groundwork for next-generation security strategies that leverage inherent device characteristics, bridging hardware and artificial intelligence (AI) for enhanced protection of critical ICS infrastructure. --- ### CityRiSE: Reasoning Urban Socio-Economic Status in Large Vision-Language Models via Reinforcement Learning Authors: Tianhui Liu, Hetian Pang, Xin Zhang, Jie Feng, Pan Hui, Yong Li Published: 2025-10-25 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.22282v2 Urban socio-economic sensing plays a vital role in advancing global sustainable development goals. With the advent of Large Vision-Language Models (LVLMs), new opportunities have emerged to address this challenge by framing it as a multi-modal perception and reasoning task. However, recent studies show that LVLMs still struggle to make accurate and interpretable socio-economic predictions from visual data. To overcome these limitations and fully exploit the potential of LVLMs, we propose CityRiSE, a novel framework for Reasoning urban Socio-Economic status in LVLMs via reinforcement learning (RL). With carefully curated multi-modal dataset and verifiable reward design, our approach guides the LVLM to focus on semantically meaningful visual cues, enabling structured and goal-oriented reasoning for generalist socio-economic status prediction. Experiments demonstrate that CityRiSE, equipped with emergent reasoning, significantly outperforms existing baselines, improving both prediction accuracy and generalization across diverse urban contexts, especially on unseen cities and unseen indicators. This work highlights the promise of combining RL and LVLMs for interpretable and generalist urban socio-economic sensing. --- ### WAON: A Large-Scale Japanese Image-Text Dataset for Cultural Adaptation in Contrastive Vision-Language Models Authors: Issa Sugiura, Shuhei Kurita, Yusuke Oda, Daisuke Kawahara, Yasuo Okabe, Naoaki Okazaki Published: 2025-10-25 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2510.22276v4 Contrastive vision-language models have achieved remarkable progress through large-scale pretraining. Recent work has shown that removing English-only caption filters and pretraining on global data is effective for improving multicultural performance. We study whether such global pretraining is sufficient for culture-specific understanding, or whether further adaptation with natively sourced data can boost performance beyond what global pretraining alone achieves. To enable this investigation, we present WAON, the largest publicly available native Japanese image-text dataset constructed from native Japanese web content in Common Crawl, containing approximately 155 million examples. We also introduce WAON-Bench, a manually curated Japanese cultural benchmark spanning 374 classes. Through comparative fine-tuning experiments on multiple Japanese image-text datasets, we observe that models fine-tuned on WAON consistently achieve stronger performance on Japanese cultural benchmarks than those fine-tuned on English-to-Japanese translated data. Controlled experiments at matched scale, filtering, and training budget across two model families further indicate that native web origin is the primary driver of this gain. We release our dataset, benchmark, model, and code. --- ### SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning Attacks Authors: Anum Paracha, Junaid Arshad, Mohamed Ben Farah, Khalid Ismail Published: 2025-10-25 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2510.22274v1 Data poisoning attacks are a potential threat to machine learning (ML) models, aiming to manipulate training datasets to disrupt their performance. Existing defenses are mostly designed to mitigate specific poisoning attacks or are aligned with particular ML algorithms. Furthermore, most defenses are developed to secure deep neural networks or binary classifiers. However, traditional multiclass classifiers need attention to be secure from data poisoning attacks, as these models are significant in developing multi-modal applications. Therefore, this paper proposes SecureLearn, a two-layer attack-agnostic defense to defend multiclass models from poisoning attacks. It comprises two components of data sanitization and a new feature-oriented adversarial training. To ascertain the effectiveness of SecureLearn, we proposed a 3D evaluation matrix with three orthogonal dimensions: data poisoning attack, data sanitization and adversarial training. Benchmarking SecureLearn in a 3D matrix, a detailed analysis is conducted at different poisoning levels (10%-20%), particularly analysing accuracy, recall, F1-score, detection and correction rates, and false discovery rate. The experimentation is conducted for four ML algorithms, namely Random Forest (RF), Decision Tree (DT), Gaussian Naive Bayes (GNB) and Multilayer Perceptron (MLP), trained with three public datasets, against three poisoning attacks and compared with two existing mitigations. Our results highlight that SecureLearn is effective against the provided attacks. SecureLearn has strengthened resilience and adversarial robustness of traditional multiclass models and neural networks, confirming its generalization beyond algorithm-specific defenses. It consistently maintained accuracy above 90%, recall and F1-score above 75%. For neural networks, SecureLearn achieved 97% recall and F1-score against all selected poisoning attacks. --- ### From Slides to Chatbots: Enhancing Large Language Models with University Course Materials Authors: Tu Anh Dinh, Philipp Nicolas Schumacher, Jan Niehues Published: 2025-10-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.22272v2 Large Language Models (LLMs) have advanced rapidly in recent years. One application of LLMs is to support student learning in educational settings. However, prior work has shown that LLMs still struggle to answer questions accurately within university-level computer science courses. In this work, we investigate how incorporating university course materials can enhance LLM performance in this setting. A key challenge lies in leveraging diverse course materials such as lecture slides and transcripts, which differ substantially from typical textual corpora: slides also contain visual elements like images and formulas, while transcripts contain spoken, less structured language. We compare two strategies, Retrieval-Augmented Generation (RAG) and Continual Pre-Training (CPT), to extend LLMs with course-specific knowledge. For lecture slides, we further explore a multi-modal RAG approach, where we present the retrieved content to the generator in image form. Our experiments reveal that, given the relatively small size of university course materials, RAG is more effective and efficient than CPT. Moreover, incorporating slides as images in the multi-modal setting significantly improves performance over text-only retrieval. These findings highlight practical strategies for developing AI assistants that better support learning and teaching, and we hope they inspire similar efforts in other educational contexts. --- ### GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification Authors: Qiao Li, Jie Li, Yukang Zhang, Lei Tan, Jing Chen, Jiayi Ji Published: 2025-10-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.22268v2 Aerial-Ground person re-identification (AG-ReID) is an emerging yet challenging task that aims to match pedestrian images captured from drastically different viewpoints, typically from unmanned aerial vehicles (UAVs) and ground-based surveillance cameras. The task poses significant challenges due to extreme viewpoint discrepancies, occlusions, and domain gaps between aerial and ground imagery. While prior works have made progress by learning cross-view representations, they remain limited in handling severe pose variations and spatial misalignment. To address these issues, we propose a Geometric and Semantic Alignment Network (GSAlign) tailored for AG-ReID. GSAlign introduces two key components to jointly tackle geometric distortion and semantic misalignment in aerial-ground matching: a Learnable Thin Plate Spline (LTPS) Module and a Dynamic Alignment Module (DAM). The LTPS module adaptively warps pedestrian features based on a set of learned keypoints, effectively compensating for geometric variations caused by extreme viewpoint changes. In parallel, the DAM estimates visibility-aware representation masks that highlight visible body regions at the semantic level, thereby alleviating the negative impact of occlusions and partial observations in cross-view correspondence. A comprehensive evaluation on CARGO with four matching protocols demonstrates the effectiveness of GSAlign, achieving significant improvements of +18.8\% in mAP and +16.8\% in Rank-1 accuracy over previous state-of-the-art methods on the aerial-ground setting. --- ### A Multi-level Analysis of Factors Associated with Student Performance: A Machine Learning Approach to the SAEB Microdata Authors: Rodrigo Tertulino, Laércio Alencar Published: 2025-10-25 Categories: cs.LG, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2510.22266v3 Identifying the factors that influence student performance in basic education is a central challenge for formulating effective public policies in Brazil. This study introduces a multi-level machine learning approach to classify the proficiency of 9th-grade and high school students using microdata from the System of Assessment of Basic Education (SAEB). Our model uniquely integrates four data sources: student socioeconomic characteristics, teacher professional profiles, school indicators, and principal management profiles. A comparative analysis of four ensemble algorithms confirmed the superiority of a Random Forest model, which achieved 90.2% accuracy and an Area Under the Curve (AUC) of 96.7%. To move beyond prediction, we applied Explainable AI (XAI) using SHAP, which revealed that the school's average socioeconomic level is the most dominant predictor, demonstrating that systemic factors have a greater impact than individual characteristics in isolation. The primary conclusion is that academic performance is a systemic phenomenon deeply tied to the school's ecosystem. This study provides a data-driven, interpretable tool to inform policies aimed at promoting educational equity by addressing disparities between schools. --- ### PatenTEB: A Comprehensive Benchmark and Model Family for Patent Text Embedding Authors: Iliass Ayaou, Denis Cavallucci Published: 2025-10-25 Categories: cs.CL, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2510.22264v1 Patent text embeddings enable prior art search, technology landscaping, and patent analysis, yet existing benchmarks inadequately capture patent-specific challenges. We introduce PatenTEB, a comprehensive benchmark comprising 15 tasks across retrieval, classification, paraphrase, and clustering, with 2.06 million examples. PatenTEB employs domain-stratified splits, domain specific hard negative mining, and systematic coverage of asymmetric fragment-to-document matching scenarios absent from general embedding benchmarks. We develop the patembed model family through multi-task training, spanning 67M to 344M parameters with context lengths up to 4096 tokens. External validation shows strong generalization: patembed-base achieves state-of-the-art on MTEB BigPatentClustering.v2 (0.494 V-measure vs. 0.445 previous best), while patembed-large achieves 0.377 NDCG@100 on DAPFAM. Systematic ablations reveal that multi-task training improves external generalization despite minor benchmark costs, and that domain-pretrained initialization provides consistent advantages across task families. All resources will be made available at https://github.com/iliass-y/patenteb. Keywords: patent retrieval, sentence embeddings, multi-task learning, asymmetric retrieval, benchmark evaluation, contrastive learning. --- ### Epistemic Deep Learning: Enabling Machine Learning Models to Know When They Do Not Know Authors: Shireen Kudukkil Manchingal Published: 2025-10-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.22261v1 Machine learning has achieved remarkable successes, yet its deployment in safety-critical domains remains hindered by an inherent inability to manage uncertainty, resulting in overconfident and unreliable predictions when models encounter out-of-distribution data, adversarial perturbations, or naturally fluctuating environments. This thesis, titled Epistemic Deep Learning: Enabling Machine Learning Models to 'Know When They Do Not Know', addresses these critical challenges by advancing the paradigm of Epistemic Artificial Intelligence, which explicitly models and quantifies epistemic uncertainty: the uncertainty arising from limited, biased, or incomplete training data, as opposed to the irreducible randomness of aleatoric uncertainty, thereby empowering models to acknowledge their limitations and refrain from overconfident decisions when uncertainty is high. Central to this work is the development of the Random-Set Neural Network (RS-NN), a novel methodology that leverages random set theory to predict belief functions over sets of classes, capturing the extent of epistemic uncertainty through the width of associated credal sets, applications of RS-NN, including its adaptation to Large Language Models (LLMs) and its deployment in weather classification for autonomous racing. In addition, the thesis proposes a unified evaluation framework for uncertainty-aware classifiers. Extensive experiments validate that integrating epistemic awareness into deep learning not only mitigates the risks associated with overconfident predictions but also lays the foundation for a paradigm shift in artificial intelligence, where the ability to 'know when it does not know' becomes a hallmark of robust and dependable systems. The title encapsulates the core philosophy of this work, emphasizing that true intelligence involves recognizing and managing the limits of one's own knowledge. --- ### Accident Anticipation via Temporal Occurrence Prediction Authors: Tianhao Zhao, Yiyang Zou, Zihao Mao, Peilun Xiao, Yulin Huang, Hongda Yang, Yuxuan Li, Qun Li, Guobin Wu, Yutian Lin Published: 2025-10-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.22260v1 Accident anticipation aims to predict potential collisions in an online manner, enabling timely alerts to enhance road safety. Existing methods typically predict frame-level risk scores as indicators of hazard. However, these approaches rely on ambiguous binary supervision (labeling all frames in accident videos as positive) despite the fact that risk varies continuously over time, leading to unreliable learning and false alarms. To address this, we propose a novel paradigm that shifts the prediction target from current-frame risk scoring to directly estimating accident scores at multiple future time steps (e.g., 0.1s-2.0s ahead), leveraging precisely annotated accident timestamps as supervision. Our method employs a snippet-level encoder to jointly model spatial and temporal dynamics, and a Transformer-based temporal decoder that predicts accident scores for all future horizons simultaneously using dedicated temporal queries. Furthermore, we introduce a refined evaluation protocol that reports Time-to-Accident (TTA) and recall (evaluated at multiple pre-accident intervals (0.5s, 1.0s, and 1.5s)) only when the false alarm rate (FAR) remains within an acceptable range, ensuring practical relevance. Experiments show that our method achieves superior performance in both recall and TTA under realistic FAR constraints. --- ### LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis Authors: Berkay Döner, Thorir Mar Ingolfsson, Luca Benini, Yawei Li Published: 2025-10-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.22257v1 Electroencephalography (EEG) offers a non-invasive lens into human brain activity, but building large-scale models is hampered by topological heterogeneity: each public EEG data defines its own electrode layout, limiting generalization. We introduce LUNA (Latent Unified Network Architecture), a self-supervised foundation model that reconciles disparate electrode geometries while scaling linearly -- not quadratically -- with channel count. LUNA compresses multi-channel EEG into a fixed-size, topology-agnostic latent space via learned queries and cross-attention. Downstream transformer blocks then operate exclusively on this latent representation using patch-wise temporal self-attention, decoupling computation from electrode count. Pre-trained on TUEG and Siena (over 21,000 hours of raw EEG across diverse montages) using a masked-patch reconstruction objective, LUNA transfers effectively to four downstream tasks: abnormality detection, artifact rejection, slowing classification, and emotion recognition. It demonstrates highly competitive performance across several benchmarks, achieving state-of-the-art results on TUAR and TUSL, e.g., 0.921 AUROC on TUAR, while reducing FLOPs by 300x and trimming GPU memory use by up to 10x. Critically, these gains are consistent across all evaluated electrode configurations. Code is available at https://github.com/pulp-bio/BioFoundation --- ### SteerX: Disentangled Steering for LLM Personalization Authors: Xiaoyan Zhao, Ming Yan, Yilun Qiu, Haoting Ni, Yang Zhang, Fuli Feng, Hong Cheng, Tat-Seng Chua Published: 2025-10-25 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.22256v1 Large language models (LLMs) have shown remarkable success in recent years, enabling a wide range of applications, including intelligent assistants that support users' daily life and work. A critical factor in building such assistants is personalizing LLMs, as user preferences and needs vary widely. Activation steering, which directly leverages directions representing user preference in the LLM activation space to adjust its behavior, offers a cost-effective way to align the model's outputs with individual users. However, existing methods rely on all historical data to compute the steering vector, ignoring that not all content reflects true user preferences, which undermines the personalization signal. To address this, we propose SteerX, a disentangled steering method that isolates preference-driven components from preference-agnostic components. Grounded in causal inference theory, SteerX estimates token-level causal effects to identify preference-driven tokens, transforms these discrete signals into a coherent description, and then leverages them to steer personalized LLM generation. By focusing on the truly preference-driven information, SteerX produces more accurate activation steering vectors and enhances personalization. Experiments on two representative steering backbone methods across real-world datasets demonstrate that SteerX consistently enhances steering vector quality, offering a practical solution for more effective LLM personalization. --- ### PACR: Progressively Ascending Confidence Reward for LLM Reasoning Authors: Eunseop Yoon, Hee Suk Yoon, Jaehyun Jang, SooHwan Eom, Qi Dai, Chong Luo, Mark A. Hasegawa-Johnson, Chang D. Yoo Published: 2025-10-25 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.22255v1 Reinforcement Learning with Verifiable Rewards (RLVR) has significantly improved LLM reasoning, but its sparse, outcome-based reward provides no guidance for intermediate steps, slowing exploration. We propose Progressively Ascending Confidence Reward (PACR), a dense, model-intrinsic reward computed directly from the model's evolving belief in the correct answer. PACR encodes the inductive bias that, along a well-formed reasoning trajectory, the probability of the ground-truth answer should have a generally ascending trend. We provide empirical and theoretical analysis validating that such an inductive bias constrains the exploration search space to regions richer in logically sound reasoning. We demonstrate that PACR accelerates exploration, reaches reward saturation with fewer trajectories, and yields improvements on multiple benchmarks. Our results suggest that dense, model-intrinsic shaping signals can make RLVR training more effective and reliable. --- ### You Don't Need Prompt Engineering Anymore: The Prompting Inversion Authors: Imran Khan Published: 2025-10-25 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.22251v1 Prompt engineering, particularly Chain-of-Thought (CoT) prompting, significantly enhances LLM reasoning capabilities. We introduce "Sculpting," a constrained, rule-based prompting method designed to improve upon standard CoT by reducing errors from semantic ambiguity and flawed common sense. We evaluate three prompting strategies (Zero Shot, standard CoT, and Sculpting) across three OpenAI model generations (gpt-4o-mini, gpt-4o, gpt-5) using the GSM8K mathematical reasoning benchmark (1,317 problems). Our findings reveal a "Prompting Inversion": Sculpting provides advantages on gpt-4o (97% vs. 93% for standard CoT), but becomes detrimental on gpt-5 (94.00% vs. 96.36% for CoT on full benchmark). We trace this to a "Guardrail-to-Handcuff" transition where constraints preventing common-sense errors in mid-tier models induce hyper-literalism in advanced models. Our detailed error analysis demonstrates that optimal prompting strategies must co-evolve with model capabilities, suggesting simpler prompts for more capable models. --- ### Real-Time Semantic Segmentation on FPGA for Autonomous Vehicles Using LMIINet with the CGRA4ML Framework Authors: Amir Mohammad Khadem Hosseini, Sattar Mirzakuchaki Published: 2025-10-25 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.22243v1 Semantic segmentation has emerged as a fundamental problem in computer vision, gaining particular importance in real-time applications such as autonomous driving. The main challenge is achieving high accuracy while operating under computational and hardware constraints. In this research, we present an FPGA-based implementation of real-time semantic segmentation leveraging the lightweight LMIINet architecture and the Coarse-Grained Reconfigurable Array for Machine Learning (CGRA4ML) hardware framework. The model was trained using Quantization-Aware Training (QAT) with 8-bit precision on the Cityscapes dataset, reducing memory footprint by a factor of four while enabling efficient fixed-point computations. Necessary modifications were applied to adapt the model to CGRA4ML constraints, including simplifying skip connections, employing hardware-friendly operations such as depthwise-separable and 1A-1 convolutions, and redesigning parts of the Flatten Transformer. Our implementation achieves approximately 90% pixel accuracy and 45% mean Intersection-over-Union (mIoU), operating in real-time at 20 frames per second (FPS) with 50.1 ms latency on the ZCU104 FPGA board. The results demonstrate the potential of CGRA4ML, with its flexibility in mapping modern layers and off-chip memory utilization for skip connections, provides a path for implementing advanced semantic segmentation networks on FPGA for real-time applications to outperform traditional GPU solutions in terms of power efficiency while maintaining competitive accuracy. The code for this project is publicly available at https://github.com/STAmirr/ cgra4ml_semantic_segmentation --- ### PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading Authors: Yutao Wu, Xiao Liu, Yunhao Feng, Jiale Ding, Xingjun Ma Published: 2025-10-25 Categories: cs.IR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.22242v1 Large Language Models (LLMs) increasingly serve as research assistants, yet their reliability in scholarly tasks remains under-evaluated. In this work, we introduce PaperAsk, a benchmark that systematically evaluates LLMs across four key research tasks: citation retrieval, content extraction, paper discovery, and claim verification. We evaluate GPT-4o, GPT-5, and Gemini-2.5-Flash under realistic usage conditions-via web interfaces where search operations are opaque to the user. Through controlled experiments, we find consistent reliability failures: citation retrieval fails in 48-98% of multi-reference queries, section-specific content extraction fails in 72-91% of cases, and topical paper discovery yields F1 scores below 0.32, missing over 60% of relevant literature. Further human analysis attributes these failures to the uncontrolled expansion of retrieved context and the tendency of LLMs to prioritize semantically relevant text over task instructions. Across basic tasks, the LLMs display distinct failure behaviors: ChatGPT often withholds responses rather than risk errors, whereas Gemini produces fluent but fabricated answers. To address these issues, we develop lightweight reliability classifiers trained on PaperAsk data to identify unreliable outputs. PaperAsk provides a reproducible and diagnostic framework for advancing the reliability evaluation of LLM-based scholarly assistance systems. --- ### Synthetic-to-Real Transfer Learning for Chromatin-Sensitive PWS Microscopy Authors: Jahidul Arafat, Sanjaya Poudel Published: 2025-10-25 Categories: eess.IV, cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2510.22239v1 Chromatin sensitive partial wave spectroscopic (csPWS) microscopy enables label free detection of nanoscale chromatin packing alterations that occur before visible cellular transformation. However, manual nuclear segmentation limits population scale analysis needed for biomarker discovery in early cancer detection. The lack of annotated csPWS imaging data prevents direct use of standard deep learning methods. We present CFU Net, a hierarchical segmentation architecture trained with a three stage curriculum on synthetic multimodal data. CFU Net achieves near perfect performance on held out synthetic test data that represent diverse spectroscopic imaging conditions without manual annotations (Dice 0.9879, IoU 0.9895). Our approach uses physics based rendering that incorporates empirically supported chromatin packing statistics, Mie scattering models, and modality specific noise, combined with a curriculum that progresses from adversarial RGB pretraining to spectroscopic fine tuning and histology validation. CFU Net integrates five architectural elements (ConvNeXt backbone, Feature Pyramid Network, UNet plus plus dense connections, dual attention, and deep supervision) that together improve Dice over a baseline UNet by 8.3 percent. We demonstrate deployment ready INT8 quantization with 74.9 percent compression and 0.15 second inference, giving a 240 times throughput gain over manual analysis. Applied to more than ten thousand automatically segmented nuclei from synthetic test data, the pipeline extracts chromatin biomarkers that distinguish normal from pre cancerous tissue with large effect sizes (Cohens d between 1.31 and 2.98), reaching 94 percent classification accuracy. This work provides a general framework for synthetic to real transfer learning in specialized microscopy and open resources for community validation on clinical specimens. --- ### Bridging the Perceptual-Statistical Gap in Dysarthria Assessment: Why Machine Learning Still Falls Short Authors: Krishna Gurugubelli Published: 2025-10-25 Categories: eess.AS, cs.LG arXiv: https://arxiv.org/abs/2510.22237v1 Automated dysarthria detection and severity assessment from speech have attracted significant research attention due to their potential clinical impact. Despite rapid progress in acoustic modeling and deep learning, models still fall short of human expert performance. This manuscript provides a comprehensive analysis of the reasons behind this gap, emphasizing a conceptual divergence we term the ``perceptual-statistical gap''. We detail human expert perceptual processes, survey machine learning representations and methods, review existing literature on feature sets and modeling strategies, and present a theoretical analysis of limits imposed by label noise and inter-rater variability. We further outline practical strategies to narrow the gap, perceptually motivated features, self-supervised pretraining, ASR-informed objectives, multimodal fusion, human-in-the-loop training, and explainability methods. Finally, we propose experimental protocols and evaluation metrics aligned with clinical goals to guide future research toward clinically reliable and interpretable dysarthria assessment tools. --- ### DiffusionLane: Diffusion Model for Lane Detection Authors: Kunyang Zhou, Yeqin Shao Published: 2025-10-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.22236v1 In this paper, we present a novel diffusion-based model for lane detection, called DiffusionLane, which treats the lane detection task as a denoising diffusion process in the parameter space of the lane. Firstly, we add the Gaussian noise to the parameters (the starting point and the angle) of ground truth lanes to obtain noisy lane anchors, and the model learns to refine the noisy lane anchors in a progressive way to obtain the target lanes. Secondly, we propose a hybrid decoding strategy to address the poor feature representation of the encoder, resulting from the noisy lane anchors. Specifically, we design a hybrid diffusion decoder to combine global-level and local-level decoders for high-quality lane anchors. Then, to improve the feature representation of the encoder, we employ an auxiliary head in the training stage to adopt the learnable lane anchors for enriching the supervision on the encoder. Experimental results on four benchmarks, Carlane, Tusimple, CULane, and LLAMAS, show that DiffusionLane possesses a strong generalization ability and promising detection performance compared to the previous state-of-the-art methods. For example, DiffusionLane with ResNet18 surpasses the existing methods by at least 1\% accuracy on the domain adaptation dataset Carlane. Besides, DiffusionLane with MobileNetV4 gets 81.32\% F1 score on CULane, 96.89\% accuracy on Tusimple with ResNet34, and 97.59\% F1 score on LLAMAS with ResNet101. Code will be available at https://github.com/zkyntu/UnLanedet. --- ### Rational Adversaries and the Maintenance of Fragility: A Game-Theoretic Theory of Rational Stagnation Authors: Daisuke Hirota Published: 2025-10-25 Categories: cs.GT, cs.AI, econ.TH arXiv: https://arxiv.org/abs/2510.22232v1 Cooperative systems often remain in persistently suboptimal yet stable states. This paper explains such "rational stagnation" as an equilibrium sustained by a rational adversary whose utility follows the principle of potential loss, $u_{D} = U_{ideal} - U_{actual}$. Starting from the Prisoner's Dilemma, we show that the transformation $u_{i}' = a\,u_{i} + b\,u_{j}$ and the ratio of mutual recognition $w = b/a$ generate a fragile cooperation band $(w_{\min},\,w_{\max})$ where both (C,C) and (D,D) are equilibria. Extending to a dynamic model with stochastic cooperative payoffs $R_{t}$ and intervention costs $(C_{c},\,C_{m})$, a Bellman-style analysis yields three strategic regimes: immediate destruction, rational stagnation, and intervention abandonment. The appendix further generalizes the utility to a reference-dependent nonlinear form and proves its stability under reference shifts, ensuring robustness of the framework. Applications to social-media algorithms and political trust illustrate how adversarial rationality can deliberately preserve fragility. --- ### Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation Authors: Jeongin Kim, Wonho Bae, YouLee Han, Giyeong Oh, Youngjae Yu, Danica J. Sutherland, Junhyug Noh Published: 2025-10-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.22229v1 Semantic segmentation demands dense pixel-level annotations, which can be prohibitively expensive - especially under extremely constrained labeling budgets. In this paper, we address the problem of low-budget active learning for semantic segmentation by proposing a novel two-stage selection pipeline. Our approach leverages a pre-trained diffusion model to extract rich multi-scale features that capture both global structure and fine details. In the first stage, we perform a hierarchical, representation-based candidate selection by first choosing a small subset of representative pixels per image using MaxHerding, and then refining these into a diverse global pool. In the second stage, we compute an entropy-augmented disagreement score (eDALD) over noisy multi-scale diffusion features to capture both epistemic uncertainty and prediction confidence, selecting the most informative pixels for annotation. This decoupling of diversity and uncertainty lets us achieve high segmentation accuracy with only a tiny fraction of labeled pixels. Extensive experiments on four benchmarks (CamVid, ADE-Bed, Cityscapes, and Pascal-Context) demonstrate that our method significantly outperforms existing baselines under extreme pixel-budget regimes. Our code is available at https://github.com/jn-kim/two-stage-edald. --- ### When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs Authors: Keyu Wang, Tian Lyu, Guinan Su, Lu Yin, Marco Canini, Jonas Geiping, Shiwei Liu Published: 2025-10-25 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.22228v2 Layer pruning has emerged as a widely adopted technique for improving the efficiency of large language models (LLMs). Although existing methods demonstrate strong performance retention on general knowledge tasks, their effect on long-chain reasoning, a more brittle yet crucial capability, remains largely unexplored. In this work, we study the impact of layer pruning on long-chain reasoning through the lens of test-time scaling, a key mechanism in modern LLMs that enables strong reasoning capacity by allocating more computation at inference time. With extensive experiments, we demonstrate that pruning even one or two layers can severely impair test-time scaling, with performance collapsing drastically on long reasoning benchmarks even when performance on knowledge-intensive and shallow reasoning tasks remains stable. Furthermore, we find that standard supervised fine-tuning remedies fail to recover test-time scaling once it has deteriorated. Through in-depth analyses, we identify the mechanisms underlying this fragility of test-time scaling and highlight the fundamental risks of applying layer pruning to reasoning-intensive LLMs. These findings call for a rethinking of layer pruning strategies and provide insights for developing methods that preserve the robustness of reasoning. We open-source the codebase in \href{https://github.com/keyu-wang-2002/Layer-Pruning-Harms-Inference-Scaling}{https://github.com/keyu-wang-2002/Layer-Pruning-Harms-Inference-Scaling}. --- ### Audio Frequency-Time Dual Domain Evaluation on Depression Diagnosis Authors: Yu Luo, Nan Huang, Sophie Yu, Hendry Xu, Jerry Wang, Colin Wang, Zhichao Liu, Chen Zeng Published: 2025-10-25 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.22225v1 Depression, as a typical mental disorder, has become a prevalent issue significantly impacting public health. However, the prevention and treatment of depression still face multiple challenges, including complex diagnostic procedures, ambiguous criteria, and low consultation rates, which severely hinder timely assessment and intervention. To address these issues, this study adopts voice as a physiological signal and leverages its frequency-time dual domain multimodal characteristics along with deep learning models to develop an intelligent assessment and diagnostic algorithm for depression. Experimental results demonstrate that the proposed method achieves excellent performance in the classification task for depression diagnosis, offering new insights and approaches for the assessment, screening, and diagnosis of depression. --- ### Taming Silent Failures: A Framework for Verifiable AI Reliability Authors: Guan-Yan Yang, Farn Wang Published: 2025-10-25 Categories: cs.SE, cs.AI, cs.LG, cs.LO, eess.SY arXiv: https://arxiv.org/abs/2510.22224v1 The integration of Artificial Intelligence (AI) into safety-critical systems introduces a new reliability paradigm: silent failures, where AI produces confident but incorrect outputs that can be dangerous. This paper introduces the Formal Assurance and Monitoring Environment (FAME), a novel framework that confronts this challenge. FAME synergizes the mathematical rigor of offline formal synthesis with the vigilance of online runtime monitoring to create a verifiable safety net around opaque AI components. We demonstrate its efficacy in an autonomous vehicle perception system, where FAME successfully detected 93.5% of critical safety violations that were otherwise silent. By contextualizing our framework within the ISO 26262 and ISO/PAS 8800 standards, we provide reliability engineers with a practical, certifiable pathway for deploying trustworthy AI. FAME represents a crucial shift from accepting probabilistic performance to enforcing provable safety in next-generation systems. --- ### HPC-Driven Modeling with ML-Based Surrogates for Magnon-Photon Dynamics in Hybrid Quantum Systems Authors: Jialin Song, Yingheng Tang, Pu Ren, Shintaro Takayoshi, Saurabh Sawant, Yujie Zhu, Jia-Mian Hu, Andy Nonaka, Michael W. Mahoney, Benjamin Erichson, Zhi Yao Published: 2025-10-25 Categories: quant-ph, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2510.22221v3 Simulating hybrid magnonic quantum systems remains a challenge due to the large disparity between the timescales of the two systems. We present a massively parallel GPU-based simulation framework that enables fully coupled, large-scale modeling of on-chip magnon-photon circuits. Our approach resolves the dynamic interaction between ferromagnetic and electromagnetic fields with high spatiotemporal fidelity. To accelerate design workflows, we develop a physics-informed machine learning surrogate trained on the simulation data, reducing computational cost while maintaining accuracy. This combined approach reveals real-time energy exchange dynamics and reproduces key phenomena such as anti-crossing behavior and the suppression of ferromagnetic resonance under strong electromagnetic fields. By addressing the multiscale and multiphysics challenges in magnon-photon modeling, our framework enables scalable simulation and rapid prototyping of next-generation quantum and spintronic devices. ---