# Research Papers — 2025-10 · bundle page 70 of 217 > Full-text markdown of papers #3451–3500 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/70 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/69.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/71.md) ### DiffGRM: Diffusion-based Generative Recommendation Model Authors: Zhao Liu, Yichen Zhu, Yiqing Yang, Xiao Lv, Guoping Tang, Rui Huang, Qiang Luo, Ruiming Tang, Kun Gai, Guorui Zhou Published: 2025-10-21 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.21805v2 Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID) and predicts the next item by autoregressively generating its SID conditioned on the user's history. However, two structural properties of SIDs make ARMs ill-suited. First, intra-item consistency: the n digits jointly specify one item, yet the left-to-right causality trains each digit only under its prefix and blocks bidirectional cross-digit evidence, collapsing supervision to a single causal path. Second, inter-digit heterogeneity: digits differ in semantic granularity and predictability, while the uniform next-token objective assigns equal weight to all digits, overtraining easy digits and undertraining hard digits. To address these two issues, we propose DiffGRM, a diffusion-based GR model that replaces the autoregressive decoder with a masked discrete diffusion model (MDM), thereby enabling bidirectional context and any-order parallel generation of SID digits for recommendation. Specifically, we tailor DiffGRM in three aspects: (1) tokenization with Parallel Semantic Encoding (PSE) to decouple digits and balance per-digit information; (2) training with On-policy Coherent Noising (OCN) that prioritizes uncertain digits via coherent masking to concentrate supervision on high-value signals; and (3) inference with Confidence-guided Parallel Denoising (CPD) that fills higher-confidence digits first and generates diverse Top-K candidates. Experiments show consistent gains over strong generative and discriminative recommendation baselines on multiple datasets, improving NDCG@10 by 6.9%-15.5%. Code is available at https://github.com/liuzhao09/DiffGRM. --- ### XRePIT: A deep learning-computational fluid dynamics hybrid framework implemented in OpenFOAM for fast, robust, and scalable unsteady simulations Authors: Shilaj Baral, Youngkyu Lee, Sangam Khanal, Joongoo Jeon Published: 2025-10-21 Categories: cs.LG, physics.flu-dyn arXiv: https://arxiv.org/abs/2510.21804v2 Autoregressive neural surrogates offer computational acceleration for fluid dynamics but inherently suffer from error accumulation and non-physical drift during long-term rollouts. Although hybrid strategies combining surrogate models and physics-based solvers have been proposed, they are limited to manual implementations for low-dimensional benchmarks. In this study, we propose an OpenFOAM-based hybrid framework, XRePIT (eXtensible Residual-based Physics-nformed Transfer learning), characterized by its fastness, robustness, and scalability. Unlike prior manual implementations (e.g., RePIT), XRePIT integrates a fully automated open-source workflow that manages the state transition between a neural surrogate and a traditional numerical solver (OpenFOAM) based on a monitored residual threshold. Using 3D buoyancy-driven flow as a testbed, we demonstrate that this residual-guided coupling enables stable long-term simulation-ell beyond the stability horizon of standalone surrogates. Our results indicate that the hybrid loop achieves up to 2.91x wall-clock acceleration while maintaining relative L2 errors within O(1E-03) Furthermore, we benchmark the framework's extensibility by introducing a finite-volume-based Fourier neural operator (FVFNO), confirming that the stabilizing effect of the residual guardrail is agnostic to the underlying neural architecture. This study provides a deployable methodology for fast, robust, and automated hybrid simulation in 3D unsteady flow. --- ### Can large audio language models understand child stuttering speech? speech summarization, and source separation Authors: Chibuzor Okocha, Maya Bakri, Christan Grant Published: 2025-10-21 Categories: eess.AS, cs.CL, cs.SD arXiv: https://arxiv.org/abs/2510.20850v1 Child speech differs from adult speech in acoustics, prosody, and language development, and disfluencies (repetitions, prolongations, blocks) further challenge Automatic Speech Recognition (ASR) and downstream Natural Language Processing (NLP). Recent large audio-language models (LALMs) demonstrate strong cross-modal audio understanding; however, their behavior in disfluent child speech remains underexplored. We evaluate several state-of-the-art LALMs in two settings: an interview (mixed speakers) and a reading task (single child). The tasks are (i) single-channel source separation to isolate the child and (ii) child-only summarization that preserves clinically relevant disfluencies and avoids adult-speech leakage. Evaluation combines Large Language Model (LLM) as a judge, human expert ratings, and BERTScore (F1), and we report agreement between models and between models and humans to assess reliability. Our findings delineate the conditions under which LALMs produce faithful child-only summaries from mixed audio and where they fail, offering practical guidance for clinical and educational deployments. We provide prompts and evaluation scripts to support replication. --- ### Cultural Alien Sampler: Open-ended art generation balancing originality and coherence Authors: Alejandro H. Artiles, Hiromu Yakura, Levin Brinkmann, Mar Canet Sola, Hassan Abu Alhaija, Ignacio Serna, Nasim Rahaman, Bernhard Schölkopf, Iyad Rahwan Published: 2025-10-21 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2510.20849v1 In open-ended domains like art, autonomous agents must generate ideas that are both original and internally coherent, yet current Large Language Models (LLMs) either default to familiar cultural patterns or sacrifice coherence when pushed toward novelty. We address this by introducing the Cultural Alien Sampler (CAS), a concept-selection method that explicitly separates compositional fit from cultural typicality. CAS uses two GPT-2 models fine-tuned on WikiArt concepts: a Concept Coherence Model that scores whether concepts plausibly co-occur within artworks, and a Cultural Context Model that estimates how typical those combinations are within individual artists' bodies of work. CAS targets combinations that are high in coherence and low in typicality, yielding ideas that maintain internal consistency while deviating from learned conventions and embedded cultural context. In a human evaluation (N = 100), our approach outperforms random selection and GPT-4o baselines and achieves performance comparable to human art students in both perceived originality and harmony. Additionally, a quantitative study shows that our method produces more diverse outputs and explores a broader conceptual space than its GPT-4o counterpart, demonstrating that artificial cultural alienness can unlock creative potential in autonomous agents. --- ### Integrated representational signatures strengthen specificity in brains and models Authors: Jialin Wu, Shreya Saha, Yiqing Bo, Meenakshi Khosla Published: 2025-10-21 Categories: q-bio.NC, cs.AI arXiv: https://arxiv.org/abs/2510.20847v2 The extent to which different neural or artificial neural networks (models) rely on equivalent representations to support similar tasks remains a central question in neuroscience and machine learning. Prior work has typically compared systems using a single representational similarity metric, yet each captures only one facet of representational structure. To address this, we leverage a suite of representational similarity metrics-each capturing a distinct facet of representational correspondence, such as geometry, unit-level tuning, or linear decodability-and assess brain region or model separability using multiple complementary measures. Metrics that preserve geometric or tuning structure (e.g., RSA, Soft Matching) yield stronger region-based discrimination, whereas more flexible mappings such as Linear Predictivity show weaker separation. These findings suggest that geometry and tuning encode brain-region- or model-family-specific signatures, while linearly decodable information tends to be more globally shared across regions or models. To integrate these complementary representational facets, we adapt Similarity Network Fusion (SNF), a framework originally developed for multi-omics data integration. SNF produces substantially sharper regional and model family-level separation than any single metric and yields robust composite similarity profiles. Moreover, clustering cortical regions using SNF-derived similarity scores reveals a clearer hierarchical organization that aligns closely with established anatomical and functional hierarchies of the visual cortex-surpassing the correspondence achieved by individual metrics. --- ### This EEG Looks Like These EEGs: Interpretable Interictal Epileptiform Discharge Detection With ProtoEEG-kNN Authors: Dennis Tang, Jon Donnelly, Alina Jade Barnett, Lesia Semenova, Jin Jing, Peter Hadar, Ioannis Karakis, Olga Selioutski, Kehan Zhao, M. Brandon Westover, Cynthia Rudin Published: 2025-10-21 Categories: q-bio.NC, cs.AI, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.20846v1 The presence of interictal epileptiform discharges (IEDs) in electroencephalogram (EEG) recordings is a critical biomarker of epilepsy. Even trained neurologists find detecting IEDs difficult, leading many practitioners to turn to machine learning for help. While existing machine learning algorithms can achieve strong accuracy on this task, most models are uninterpretable and cannot justify their conclusions. Absent the ability to understand model reasoning, doctors cannot leverage their expertise to identify incorrect model predictions and intervene accordingly. To improve the human-model interaction, we introduce ProtoEEG-kNN, an inherently interpretable model that follows a simple case-based reasoning process. ProtoEEG-kNN reasons by comparing an EEG to similar EEGs from the training set and visually demonstrates its reasoning both in terms of IED morphology (shape) and spatial distribution (location). We show that ProtoEEG-kNN can achieve state-of-the-art accuracy in IED detection while providing explanations that experts prefer over existing approaches. --- ### QKCV Attention: Enhancing Time Series Forecasting with Static Categorical Embeddings for Both Lightweight and Pre-trained Foundation Models Authors: Hao Wang, Baojun Ma Published: 2025-10-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.20222v1 In real-world time series forecasting tasks, category information plays a pivotal role in capturing inherent data patterns. This paper introduces QKCV (Query-Key-Category-Value) attention, an extension of the traditional QKV framework that incorporates a static categorical embedding C to emphasize category-specific information. As a versatile plug-in module, QKCV enhances the forecasting accuracy of attention-based models (e.g., Vanilla Transformer, Informer, PatchTST, TFT) across diverse real-world datasets. Furthermore, QKCV demonstrates remarkable adaptability in fine-tuning univariate time series foundation model by solely updating the static embedding C while preserving pretrained weights, thereby reducing computational overhead and achieving superior fine-tuning performance. --- ### Some Attention is All You Need for Retrieval Authors: Felix Michalak, Steven Abreu Published: 2025-10-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.19861v1 We demonstrate complete functional segregation in hybrid SSM-Transformer architectures: retrieval depends exclusively on self-attention layers. Across RecurrentGemma-2B/9B and Jamba-Mini-1.6, attention ablation causes catastrophic retrieval failure (0% accuracy), while SSM layers show no compensatory mechanisms even with improved prompting. Conversely, sparsifying attention to just 15% of heads maintains near-perfect retrieval while preserving 84% MMLU performance, suggesting self-attention specializes primarily for retrieval tasks. We identify precise mechanistic requirements for retrieval: needle tokens must be exposed during generation and sufficient context must be available during prefill or generation. This strict functional specialization challenges assumptions about redundancy in hybrid architectures and suggests these models operate as specialized modules rather than integrated systems, with immediate implications for architecture optimization and interpretability. --- ### Analysing Knowledge Construction in Online Learning: Adapting the Interaction Analysis Model for Unstructured Large-Scale Discourse Authors: Jindi Wang, Yidi Zhang, Zhaoxing Li, Pedro Bem Haja, Ioannis Ivrissimtzis, Zichen Zhao, Sebastian Stein Published: 2025-10-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.19858v3 The rapid expansion of online courses and social media has generated large volumes of unstructured learner-generated text. Understanding how learners construct knowledge in these spaces is crucial for analysing learning processes, informing content design, and providing feedback at scale. However, existing approaches typically rely on manual coding of well-structured discussion forums, which does not scale to the fragmented discourse found in online learning. This study proposes and validates a framework that combines a codebook inspired by the Interaction Analysis Model with an automated classifier to enable large-scale analysis of knowledge construction in unstructured online discourse. We adapt four comment-level categories of knowledge construction: Non-Knowledge Construction, Share, Explore, and Integrate. Three trained annotators coded a balanced sample of 20,000 comments from YouTube education channels. The codebook demonstrated strong reliability, with Cohen's kappa = 0.79 on the main dataset and 0.85--0.93 across four additional educational domains. For automated classification, bag-of-words baselines were compared with transformer-based language models using 10-fold cross-validation. A DeBERTa-v3-large model achieved the highest macro-averaged F1 score (0.841), outperforming all baselines and other transformer models. External validation on four domains yielded macro-F1 above 0.705, with stronger transfer in medicine and programming, where discourse was more structured and task-focused, and weaker transfer in language and music, where comments were more varied and context-dependent. Overall, the study shows that theory-driven, semi-automated analysis of knowledge construction at scale is feasible, enabling the integration of knowledge-construction indicators into learning analytics and the design of online learning environments. --- ### Multi-Resolution Analysis of the Convective Structure of Tropical Cyclones for Short-Term Intensity Guidance Authors: Elizabeth Cucuzzella, Tria McNeely, Kimberly Wood, Ann B. Lee Published: 2025-10-21 Categories: eess.IV, cs.LG arXiv: https://arxiv.org/abs/2510.19854v1 Accurate tropical cyclone (TC) short-term intensity forecasting with a 24-hour lead time is essential for disaster mitigation in the Atlantic TC basin. Since most TCs evolve far from land-based observing networks, satellite imagery is critical to monitoring these storms; however, these complex and high-resolution spatial structures can be challenging to qualitatively interpret in real time by forecasters. Here we propose a concise, interpretable, and descriptive approach to quantify fine TC structures with a multi-resolution analysis (MRA) by the discrete wavelet transform, enabling data analysts to identify physically meaningful structural features that strongly correlate with rapid intensity change. Furthermore, deep-learning techniques can build on this MRA for short-term intensity guidance. --- ### Can Reasoning Models Obfuscate Reasoning? Stress-Testing Chain-of-Thought Monitorability Authors: Artur Zolkowski, Wen Xing, David Lindner, Florian Tramèr, Erik Jenner Published: 2025-10-21 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2510.19851v1 Recent findings suggest that misaligned models may exhibit deceptive behavior, raising concerns about output trustworthiness. Chain-of-thought (CoT) is a promising tool for alignment monitoring: when models articulate their reasoning faithfully, monitors can detect and mitigate harmful behaviors before undesirable outcomes occur. However, a key uncertainty is: Can models obfuscate their CoT in order to pursue hidden adversarial objectives while evading detection? To answer this question and thus stress-test CoT monitorability, we develop a composable and quantifiable taxonomy of prompts to elicit CoT obfuscation. We evaluate both internal CoT (reasoning traces) and external CoT (prompted reasoning in outputs) using toy tasks and more realistic environments in SHADE-Arena. We show that: (i) CoT monitoring performs accurately and efficiently without obfuscation pressure. (ii) Under strong obfuscation pressure, some models successfully complete adversarial tasks while evading detection. (iii) Models do not obfuscate their internal CoT as much as their external CoT (under prompt pressure). These results suggest that while CoT provides valuable oversight in benign settings, robust deployment requires model-specific stress-testing of monitorability. --- ### Prompt Decorators: A Declarative and Composable Syntax for Reasoning, Formatting, and Control in LLMs Authors: Mostapha Kalami Heris Published: 2025-10-21 Categories: cs.PL, cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2510.19850v1 Large Language Models (LLMs) are central to reasoning, writing, and decision-support workflows, yet users lack consistent control over how they reason and express outputs. Conventional prompt engineering relies on verbose natural-language instructions, limiting reproducibility, modularity, and interpretability. This paper introduces Prompt Decorators, a declarative, composable syntax that governs LLM behavior through compact control tokens such as +++Reasoning, +++Tone(style=formal), and +++Import(topic="Systems Thinking"). Each decorator modifies a behavioral dimension, such as reasoning style, structure, or tone, without changing task content. The framework formalizes twenty core decorators organized into two functional families (Cognitive & Generative and Expressive & Systemic), each further decomposed into subcategories that govern reasoning, interaction, expression, and session-control. It defines a unified syntax, scoping model, and deterministic processing pipeline enabling predictable and auditable behavior composition. By decoupling task intent from execution behavior, Prompt Decorators create a reusable and interpretable interface for prompt design. Illustrative use cases demonstrate improved reasoning transparency, reduced prompt complexity, and standardized model behavior across domains. The paper concludes with implications for interoperability, behavioral consistency, and the development of declarative interfaces for scalable AI systems. --- ### Re-Activating Frozen Primitives for 3D Gaussian Splatting Authors: Yuxin Cheng, Binxiao Huang, Wenyong Zhou, Taiqiang Wu, Zhengwu Liu, Graziano Chesi, Ngai Wong Published: 2025-10-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.19653v1 3D Gaussian Splatting (3D-GS) achieves real-time photorealistic novel view synthesis, yet struggles with complex scenes due to over-reconstruction artifacts, manifesting as local blurring and needle-shape distortions. While recent approaches attribute these issues to insufficient splitting of large-scale Gaussians, we identify two fundamental limitations: gradient magnitude dilution during densification and the primitive frozen phenomenon, where essential Gaussian densification is inhibited in complex regions while suboptimally scaled Gaussians become trapped in local optima. To address these challenges, we introduce ReAct-GS, a method founded on the principle of re-activation. Our approach features: (1) an importance-aware densification criterion incorporating $α$-blending weights from multiple viewpoints to re-activate stalled primitive growth in complex regions, and (2) a re-activation mechanism that revitalizes frozen primitives through adaptive parameter perturbations. Comprehensive experiments across diverse real-world datasets demonstrate that ReAct-GS effectively eliminates over-reconstruction artifacts and achieves state-of-the-art performance on standard novel view synthesis metrics while preserving intricate geometric details. Additionally, our re-activation mechanism yields consistent improvements when integrated with other 3D-GS variants such as Pixel-GS, demonstrating its broad applicability. --- ### Training-Free Spectral Fingerprints of Voice Processing in Transformers Authors: Valentin Noël Published: 2025-10-21 Categories: cs.CL, cs.LG, eess.SP, stat.ML arXiv: https://arxiv.org/abs/2510.19131v1 Different transformer architectures implement identical linguistic computations via distinct connectivity patterns, yielding model imprinted ``computational fingerprints'' detectable through spectral analysis. Using graph signal processing on attention induced token graphs, we track changes in algebraic connectivity (Fiedler value, $Δλ_2$) under voice alternation across 20 languages and three model families, with a prespecified early window (layers 2--5). Our analysis uncovers clear architectural signatures: Phi-3-Mini shows a dramatic English specific early layer disruption ($\overline{Δλ_2}_{(2,5)}\!\approx\!-0.446$) while effects in 19 other languages are minimal, consistent with public documentation that positions the model primarily for English use. Qwen2.5-7B displays small, distributed shifts that are largest for morphologically rich languages, and LLaMA-3.2-1B exhibits systematic but muted responses. These spectral signatures correlate strongly with behavioral differences (Phi-3: $r=-0.976$) and are modulated by targeted attention head ablations, linking the effect to early attention structure and confirming functional relevance. Taken together, the findings are consistent with the view that training emphasis can leave detectable computational imprints: specialized processing strategies that manifest as measurable connectivity patterns during syntactic transformations. Beyond voice alternation, the framework differentiates reasoning modes, indicating utility as a simple, training free diagnostic for revealing architectural biases and supporting model reliability analysis. --- ### A Cross-Environment and Cross-Embodiment Path Planning Framework via a Conditional Diffusion Model Authors: Mehran Ghafarian Tamizi, Homayoun Honari, Amir Mehdi Soufi Enayati, Aleksey Nozdryn-Plotnicki, Homayoun Najjaran Published: 2025-10-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2510.19128v1 Path planning for a robotic system in high-dimensional cluttered environments needs to be efficient, safe, and adaptable for different environments and hardware. Conventional methods face high computation time and require extensive parameter tuning, while prior learning-based methods still fail to generalize effectively. The primary goal of this research is to develop a path planning framework capable of generalizing to unseen environments and new robotic manipulators without the need for retraining. We present GADGET (Generalizable and Adaptive Diffusion-Guided Environment-aware Trajectory generation), a diffusion-based planning model that generates joint-space trajectories conditioned on voxelized scene representations as well as start and goal configurations. A key innovation is GADGET's hybrid dual-conditioning mechanism that combines classifier-free guidance via learned scene encoding with classifier-guided Control Barrier Function (CBF) safety shaping, integrating environment awareness with real-time collision avoidance directly in the denoising process. This design supports zero-shot transfer to new environments and robotic embodiments without retraining. Experimental results show that GADGET achieves high success rates with low collision intensity in spherical-obstacle, bin-picking, and shelf environments, with CBF guidance further improving safety. Moreover, comparative evaluations indicate strong performance relative to both sampling-based and learning-based baselines. Furthermore, GADGET provides transferability across Franka Panda, Kinova Gen3 (6/7-DoF), and UR5 robots, and physical execution on a Kinova Gen3 demonstrates its ability to generate safe, collision-free trajectories in real-world settings. --- ### Steering Autoregressive Music Generation with Recursive Feature Machines Authors: Daniel Zhao, Daniel Beaglehole, Taylor Berg-Kirkpatrick, Julian McAuley, Zachary Novack Published: 2025-10-21 Categories: cs.LG, cs.AI, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2510.19127v2 Controllable music generation remains a significant challenge, with existing methods often requiring model retraining or introducing audible artifacts. We introduce MusicRFM, a framework that adapts Recursive Feature Machines (RFMs) to enable fine-grained, interpretable control over frozen, pre-trained music models by directly steering their internal activations. RFMs analyze a model's internal gradients to produce interpretable "concept directions", or specific axes in the activation space that correspond to musical attributes like notes or chords. We first train lightweight RFM probes to discover these directions within MusicGen's hidden states; then, during inference, we inject them back into the model to guide the generation process in real-time without per-step optimization. We present advanced mechanisms for this control, including dynamic, time-varying schedules and methods for the simultaneous enforcement of multiple musical properties. Our method successfully navigates the trade-off between control and generation quality: we can increase the accuracy of generating a target musical note from 0.23 to 0.82, while text prompt adherence remains within approximately 0.02 of the unsteered baseline, demonstrating effective control with minimal impact on prompt fidelity. We release code to encourage further exploration on RFMs in the music domain. --- ### Learning Peer Influence Probabilities with Linear Contextual Bandits Authors: Ahmed Sayeed Faruk, Mohammad Shahverdikondori, Elena Zheleva Published: 2025-10-21 Categories: cs.LG, cs.SI arXiv: https://arxiv.org/abs/2510.19119v2 In networked environments, it is common for users to share recommendations about content, products, services, and possible courses of action. Whether these recommendations are accepted and acted upon is highly context-dependent, influenced by the characteristics of the sender and recipient, the nature of their relationship, the attributes of the recommended item, and the communication context. Consequently, probabilities of peer influence exhibit substantial heterogeneity across individuals and settings. Accurate estimation of these probabilities is key to understanding information diffusion processes and to improving the effectiveness of viral marketing strategies. However, learning these probabilities from data is challenging; static data may capture correlations between peer recommendations and peer actions but fails to reveal influence relationships. Online learning algorithms can learn these probabilities from interventions but either waste resources by learning from random exploration or optimize for rewards, thus favoring exploration of the space with higher influence probabilities. In this work, we study learning peer influence probabilities under a contextual linear bandit framework. We show that a fundamental trade-off can arise between regret minimization and estimation error, characterize all achievable rate pairs, and propose an uncertainty-guided exploration algorithm that, by tuning a parameter, attains any pair within this trade-off. Our experiments on semi-synthetic network datasets show the advantages of our method over static methods and contextual bandits that ignore this trade-off. --- ### A Novel Approach to Breast Cancer Segmentation using U-Net Model with Attention Mechanisms and FedProx Authors: Eyad Gad, Mustafa Abou Khatwa, Mustafa A. Elattar, Sahar Selim Published: 2025-10-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.19118v1 Breast cancer is a leading cause of death among women worldwide, emphasizing the need for early detection and accurate diagnosis. As such Ultrasound Imaging, a reliable and cost-effective tool, is used for this purpose, however the sensitive nature of medical data makes it challenging to develop accurate and private artificial intelligence models. A solution is Federated Learning as it is a promising technique for distributed machine learning on sensitive medical data while preserving patient privacy. However, training on non-Independent and non-Identically Distributed (non-IID) local datasets can impact the accuracy and generalization of the trained model, which is crucial for accurate tumour boundary delineation in BC segmentation. This study aims to tackle this challenge by applying the Federated Proximal (FedProx) method to non-IID Ultrasonic Breast Cancer Imaging datasets. Moreover, we focus on enhancing tumour segmentation accuracy by incorporating a modified U-Net model with attention mechanisms. Our approach resulted in a global model with 96% accuracy, demonstrating the effectiveness of our method in enhancing tumour segmentation accuracy while preserving patient privacy. Our findings suggest that FedProx has the potential to be a promising approach for training precise machine learning models on non-IID local medical datasets. --- ### A Graph Signal Processing Framework for Hallucination Detection in Large Language Models Authors: Valentin Noël Published: 2025-10-21 Categories: cs.CL, cs.LG, eess.SP, stat.ML arXiv: https://arxiv.org/abs/2510.19117v1 Large language models achieve impressive results but distinguishing factual reasoning from hallucinations remains challenging. We propose a spectral analysis framework that models transformer layers as dynamic graphs induced by attention, with token embeddings as signals on these graphs. Through graph signal processing, we define diagnostics including Dirichlet energy, spectral entropy, and high-frequency energy ratios, with theoretical connections to computational stability. Experiments across GPT architectures suggest universal spectral patterns: factual statements exhibit consistent "energy mountain" behavior with low-frequency convergence, while different hallucination types show distinct signatures. Logical contradictions destabilize spectra with large effect sizes ($g>1.0$), semantic errors remain stable but show connectivity drift, and substitution hallucinations display intermediate perturbations. A simple detector using spectral signatures achieves 88.75% accuracy versus 75% for perplexity-based baselines, demonstrating practical utility. These findings indicate that spectral geometry may capture reasoning patterns and error behaviors, potentially offering a framework for hallucination detection in large language models. --- ### That's Deprecated! Understanding, Detecting, and Steering Knowledge Conflicts in Language Models for Code Generation Authors: Jaesung Bae, Cameron Churchwell, Mitchell Hermon, Tsun-An Hsieh, Jocelyn Xu, Yekaterina Yegorova, Mark Hasegawa-Johnson, Heng Ji Published: 2025-10-21 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.19116v1 This paper investigates how large language models (LLMs) behave when faced with discrepancies between their parametric knowledge and conflicting information contained in a prompt. Building on prior question-answering (QA) research, we extend the investigation of knowledge conflicts to the realm of code generation. We propose a domain-agnostic framework for constructing and interpreting such conflicts, along with a novel evaluation method and dataset tailored to code conflict scenarios. Our experiments indicate that sufficiently large LLMs encode the notion of a knowledge conflict in their parameters, enabling us to detect knowledge conflicts with up to \textbf{80.65\%} accuracy. Building on these insights, we show that activation-level steering can achieve up to a \textbf{12.6\%} improvement in steering success over a random baseline. However, effectiveness depends critically on balancing model size, task domain, and steering direction. The experiment code and data will be made publicly available after acceptance. --- ### Signature Kernel Scoring Rule: A Spatio-Temporal Diagnostic for Probabilistic Weather Forecasting Authors: Archer Dodson, Ritabrata Dutta Published: 2025-10-21 Categories: stat.ML, cs.LG, stat.AP arXiv: https://arxiv.org/abs/2510.19110v2 Modern weather forecasting has increasingly transitioned from numerical weather prediction (NWP) to data-driven machine learning forecasting techniques. While these new models produce probabilistic forecasts to quantify uncertainty, their training and evaluation may remain hindered by conventional scoring rules, primarily MSE, which are designed for single time point predictions and ignore the highly correlated data structures present in weather behaviour. This work introduces the signature kernel scoring rule to the domain of weather forecasting, which reframes weather variables as continuous paths to encode temporal and spatial dependencies through iterated integrals. Validated as strictly proper through the use of path augmentations to guarantee uniqueness, the signature kernel provides a theoretically robust metric for forecast verification and model training. Empirical evaluations through weather scorecards on WeatherBench 2 models demonstrate the signature kernel scoring rule's high discriminative power and unique capacity to capture path-dependent interactions. Following previous demonstration of successful adversarial-free probabilistic training, we train sliding window generative neural networks using a predictive-sequential scoring rule on ERA5 reanalysis weather data. Using a lightweight model, we demonstrate that signature kernel based training outperforms climatology for forecast paths of up to fifteen timesteps. --- ### Advancing Brain Tumor Segmentation via Attention-based 3D U-Net Architecture and Digital Image Processing Authors: Eyad Gad, Seif Soliman, M. Saeed Darweesh Published: 2025-10-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.19109v1 In the realm of medical diagnostics, rapid advancements in Artificial Intelligence (AI) have significantly yielded remarkable improvements in brain tumor segmentation. Encoder-Decoder architectures, such as U-Net, have played a transformative role by effectively extracting meaningful representations in 3D brain tumor segmentation from Magnetic resonance imaging (MRI) scans. However, standard U-Net models encounter challenges in accurately delineating tumor regions, especially when dealing with irregular shapes and ambiguous boundaries. Additionally, training robust segmentation models on high-resolution MRI data, such as the BraTS datasets, necessitates high computational resources and often faces challenges associated with class imbalance. This study proposes the integration of the attention mechanism into the 3D U-Net model, enabling the model to capture intricate details and prioritize informative regions during the segmentation process. Additionally, a tumor detection algorithm based on digital image processing techniques is utilized to address the issue of imbalanced training data and mitigate bias. This study aims to enhance the performance of brain tumor segmentation, ultimately improving the reliability of diagnosis. The proposed model is thoroughly evaluated and assessed on the BraTS 2020 dataset using various performance metrics to accomplish this goal. The obtained results indicate that the model outperformed related studies, exhibiting dice of 0.975, specificity of 0.988, and sensitivity of 0.995, indicating the efficacy of the proposed model in improving brain tumor segmentation, offering valuable insights for reliable diagnosis in clinical settings. --- ### MetaCluster: Enabling Deep Compression of Kolmogorov-Arnold Network Authors: Matthew Raffel, Adwaith Renjith, Lizhong Chen Published: 2025-10-21 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2510.19105v2 Kolmogorov-Arnold Networks (KANs) replace scalar weights with per-edge vectors of basis coefficients, thereby increasing expressivity and accuracy while also resulting in a multiplicative increase in parameters and memory. We propose MetaCluster, a framework that makes KANs highly compressible without sacrificing accuracy. Specifically, a lightweight meta-learner, trained jointly with the KAN, maps low-dimensional embeddings to coefficient vectors, thereby shaping them to lie on a low-dimensional manifold that is amenable to clustering. We then run K-means in coefficient space and replace per-edge vectors with shared centroids. Afterwards, the meta-learner can be discarded, and a brief fine-tuning of the centroid codebook recovers any residual accuracy loss. The resulting model stores only a small codebook and per-edge indices, exploiting the vector nature of KAN parameters to amortize storage across multiple coefficients. On MNIST, CIFAR-10, and CIFAR-100, across standard KANs and ConvKANs using multiple basis functions, MetaCluster achieves a reduction of up to $80\times$ in parameter storage, with no loss in accuracy. Similarly, on high-dimensional equation modeling tasks, MetaCluster achieves a parameter reduction of $124.1\times$, without impacting performance. Code will be released upon publication. --- ### What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning Authors: Yaning Jia, Chunhui Zhang, Xingjian Diao, Xiangchi Yuan, Zhongyu Ouyang, Chiyu Ma, Soroush Vosoughi Published: 2025-10-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.19099v2 Curriculum learning (CL) - ordering training data from easy to hard - has become a popular strategy for improving reasoning in large language models (LLMs). Yet prior work employs disparate difficulty metrics and training setups, leaving open fundamental questions: When does curriculum help? Which direction - forward or reverse - is better? And does the answer depend on what we measure? We address these questions through a unified offline evaluation framework that decomposes curriculum difficulty into five complementary dimensions: Problem Difficulty, Model Surprisal, Confidence Margin, Predictive Uncertainty, and Decision Variability. Through controlled post-training experiments on mathematical reasoning benchmarks with Llama3.1-8B, Mistral-7B, and Gemma3-4B, we find that (i) no curriculum strategy dominates universally - the relative effectiveness of forward versus reverse CL depends jointly on model capability and task complexity; (ii) even within a single metric, samples at different difficulty levels produce distinct gains depending on task demands; and (iii) task-aligned curricula focus on shaping the model's final representations and generalization, whereas inner-state curricula modulate internal states such as confidence and uncertainty. Our findings challenge the notion of a universal curriculum strategy and offer actionable guidance across model and task regimes, with some metrics indicating that prioritizing decision-uncertain samples can further enhance learning outcomes. --- ### Weight Decay may matter more than muP for Learning Rate Transfer in Practice Authors: Atli Kosson, Jeremy Welborn, Yang Liu, Martin Jaggi, Xi Chen Published: 2025-10-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.19093v2 Transferring the optimal learning rate from small to large neural networks can enable efficient training at scales where hyperparameter tuning is otherwise prohibitively expensive. To this end, the Maximal Update Parameterization (muP) proposes a learning rate scaling designed to keep the update dynamics of internal representations stable across different model widths. However, the scaling rules of muP rely on strong assumptions, particularly about the geometric alignment of a layer's inputs with both its weights and gradient updates. In this large-scale empirical investigation, we show that these assumptions hold only briefly at the start of training in the practical setups where learning rate transfer is most valuable, such as LLM training. For the remainder of training it is weight decay rather than muP that correctly stabilizes the update dynamics of internal representations across widths, facilitating learning rate transfer. This suggests muP's scaling primarily acts as a form of implicit learning rate warmup, allowing us to largely replace it with modified warmup schedules. Together these findings fundamentally challenge prevailing beliefs about learning rate transfer and can explain empirical observations such as why muP requires the independent weight decay variant for good transfer. --- ### Learning noisy tissue dynamics across time scales Authors: Ming Han, John Devany, Michel Fruchart, Margaret L. Gardel, Vincenzo Vitelli Published: 2025-10-21 Categories: cond-mat.soft, cs.LG, physics.bio-ph, q-bio.QM arXiv: https://arxiv.org/abs/2510.19090v2 Tissue dynamics play a crucial role in biological processes ranging from inflammation to morphogenesis. However, these noisy multicellular dynamics are notoriously hard to predict. Here, we introduce a biomimetic machine learning framework capable of inferring noisy multicellular dynamics directly from experimental movies. This generative model combines graph neural networks, normalizing flows and WaveNet algorithms to represent tissues as neural stochastic differential equations where cells are edges of an evolving graph. Cell interactions are encoded in a dual signaling graph capable of handling signaling cascades. The dual graph architecture of our neural networks reflects the architecture of the underlying biological tissues, substantially reducing the amount of data needed for training, compared to convolutional or fully-connected neural networks. Taking epithelial tissue experiments as a case study, we show that our model not only captures stochastic cell motion but also predicts the evolution of cell states in their division cycle. Finally, we demonstrate that our method can accurately generate the experimental dynamics of developmental systems, such as the fly wing, and cell signaling processes mediated by stochastic ERK waves, paving the way for its use as a digital twin in bioengineering and clinical contexts. --- ### UniHPR: Unified Human Pose Representation via Singular Value Contrastive Learning Authors: Zhongyu Jiang, Wenhao Chai, Lei Li, Zhuoran Zhou, Cheng-Yen Yang, Jenq-Neng Hwang Published: 2025-10-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.19078v1 In recent years, there has been a growing interest in developing effective alignment pipelines to generate unified representations from different modalities for multi-modal fusion and generation. As an important component of Human-Centric applications, Human Pose representations are critical in many downstream tasks, such as Human Pose Estimation, Action Recognition, Human-Computer Interaction, Object tracking, etc. Human Pose representations or embeddings can be extracted from images, 2D keypoints, 3D skeletons, mesh models, and lots of other modalities. Yet, there are limited instances where the correlation among all of those representations has been clearly researched using a contrastive paradigm. In this paper, we propose UniHPR, a unified Human Pose Representation learning pipeline, which aligns Human Pose embeddings from images, 2D and 3D human poses. To align more than two data representations at the same time, we propose a novel singular value-based contrastive learning loss, which better aligns different modalities and further boosts performance. To evaluate the effectiveness of the aligned representation, we choose 2D and 3D Human Pose Estimation (HPE) as our evaluation tasks. In our evaluation, with a simple 3D human pose decoder, UniHPR achieves remarkable performance metrics: MPJPE 49.9mm on the Human3.6M dataset and PA-MPJPE 51.6mm on the 3DPW dataset with cross-domain evaluation. Meanwhile, we are able to achieve 2D and 3D pose retrieval with our unified human pose representations in Human3.6M dataset, where the retrieval error is 9.24mm in MPJPE. --- ### Local Guidance for Configuration-Based Multi-Agent Pathfinding Authors: Tomoki Arita, Keisuke Okumura Published: 2025-10-21 Categories: cs.MA, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2510.19072v3 Guidance is an emerging concept that improves the empirical performance of real-time, sub-optimal multi-agent pathfinding (MAPF) methods. It offers additional information to MAPF algorithms to mitigate congestion on a global scale by considering the collective behavior of all agents across the entire workspace. This global perspective helps reduce agents' waiting times, thereby improving overall coordination efficiency. In contrast, this study explores an alternative approach: providing local guidance in the vicinity of each agent. While such localized methods involve recomputation as agents move and may appear computationally demanding, we empirically demonstrate that supplying informative spatiotemporal cues to the planner can significantly improve solution quality without exceeding a moderate time budget. When applied to LaCAM, a leading configuration-based solver, this form of guidance establishes a new performance frontier for MAPF. --- ### PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions Authors: Amith Ananthram, Elias Stengel-Eskin, Lorena A. Bradford, Julia Demarest, Adam Purvis, Keith Krut, Robert Stein, Rina Elster Pantalony, Mohit Bansal, Kathleen McKeown Published: 2025-10-21 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.19060v3 While vision-language models (VLMs) have advanced into detailed image description, evaluation remains a challenge. Standard metrics (e.g. CIDEr, SPICE) were designed for short texts and tuned to recognize errors that are now uncommon, such as object misidentification. In contrast, long texts require sensitivity to attribute and relation attachments and scores that localize errors to particular text spans. In this work, we introduce PoSh, a metric for detailed image description that uses scene graphs as structured rubrics to guide LLMs-as-a-Judge, producing aggregate scores grounded in fine-grained errors (e.g. mistakes in compositional understanding). PoSh is replicable, interpretable and a better proxy for human raters than existing metrics (including GPT4o-as-a-Judge). To validate PoSh, we introduce a challenging new dataset, DOCENT. This novel benchmark contains artwork, paired with expert-written references, and model-generated descriptions, augmented with granular and coarse judgments of their quality from art history students. Thus, DOCENT enables evaluating both detailed image description metrics and detailed image description itself in a challenging new domain. We show that PoSh achieves stronger correlations (+0.05 Spearman $ρ$) with the human judgments in DOCENT than the best open-weight alternatives, is robust to image type (using CapArena, an existing dataset of web imagery) and is a capable reward function, outperforming standard supervised fine-tuning. Then, using PoSh, we characterize the performance of open and closed models in describing the paintings, sketches and statues in DOCENT and find that foundation models struggle to achieve full, error-free coverage of images with rich scene dynamics, establishing a demanding new task to gauge VLM progress. Through both PoSh and DOCENT, we hope to enable advances in important areas such as assistive text generation. --- ### POLAR: Policy-based Layerwise Reinforcement Learning Method for Stealthy Backdoor Attacks in Federated Learning Authors: Kuai Yu, Xiaoyu Wu, Peishen Yan, Qingqian Yang, Linshan Jiang, Hao Wang, Yang Hua, Tao Song, Haibing Guan Published: 2025-10-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.19056v1 Federated Learning (FL) enables decentralized model training across multiple clients without exposing local data, but its distributed feature makes it vulnerable to backdoor attacks. Despite early FL backdoor attacks modifying entire models, recent studies have explored the concept of backdoor-critical (BC) layers, which poison the chosen influential layers to maintain stealthiness while achieving high effectiveness. However, existing BC layers approaches rely on rule-based selection without consideration of the interrelations between layers, making them ineffective and prone to detection by advanced defenses. In this paper, we propose POLAR (POlicy-based LAyerwise Reinforcement learning), the first pipeline to creatively adopt RL to solve the BC layer selection problem in layer-wise backdoor attack. Different from other commonly used RL paradigm, POLAR is lightweight with Bernoulli sampling. POLAR dynamically learns an attack strategy, optimizing layer selection using policy gradient updates based on backdoor success rate (BSR) improvements. To ensure stealthiness, we introduce a regularization constraint that limits the number of modified layers by penalizing large attack footprints. Extensive experiments demonstrate that POLAR outperforms the latest attack methods by up to 40% against six state-of-the-art (SOTA) defenses. --- ### The MUSE Benchmark: Probing Music Perception and Auditory Relational Reasoning in Audio LLMS Authors: Brandon James Carone, Iran R. Roman, Pablo Ripollés Published: 2025-10-21 Categories: cs.AI, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2510.19055v1 Multimodal Large Language Models (MLLMs) have demonstrated capabilities in audio understanding, but current evaluations may obscure fundamental weaknesses in relational reasoning. We introduce the Music Understanding and Structural Evaluation (MUSE) Benchmark, an open-source resource with 10 tasks designed to probe fundamental music perception skills. We evaluate four SOTA models (Gemini Pro and Flash, Qwen2.5-Omni, and Audio-Flamingo 3) against a large human baseline (N=200). Our results reveal a wide variance in SOTA capabilities and a persistent gap with human experts. While Gemini Pro succeeds on basic perception, Qwen and Audio Flamingo 3 perform at or near chance, exposing severe perceptual deficits. Furthermore, we find Chain-of-Thought (CoT) prompting provides inconsistent, often detrimental results. Our work provides a critical tool for evaluating invariant musical representations and driving development of more robust AI systems. --- ### Rectifying Shortcut Behaviors in Preference-based Reward Learning Authors: Wenqian Ye, Guangtao Zheng, Aidong Zhang Published: 2025-10-21 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.19050v1 In reinforcement learning from human feedback, preference-based reward models play a central role in aligning large language models to human-aligned behavior. However, recent studies show that these models are prone to reward hacking and often fail to generalize well due to over-optimization. They achieve high reward scores by exploiting shortcuts, that is, exploiting spurious features (e.g., response verbosity, agreeable tone, or sycophancy) that correlate with human preference labels in the training data rather than genuinely reflecting the intended objectives. In this paper, instead of probing these issues one at a time, we take a broader view of the reward hacking problem as shortcut behaviors and introduce a principled yet flexible approach to mitigate shortcut behaviors in preference-based reward learning. Inspired by the invariant theory in the kernel perspective, we propose Preference-based Reward Invariance for Shortcut Mitigation (PRISM), which learns group-invariant kernels with feature maps in a closed-form learning objective. Experimental results in several benchmarks show that our method consistently improves the accuracy of the reward model on diverse out-of-distribution tasks and reduces the dependency on shortcuts in downstream policy models, establishing a robust framework for preference-based alignment. --- ### REPAIR Approach for Social-based City Reconstruction Planning in case of natural disasters Authors: Ghulam Mudassir, Antinisca Di Marco, Giordano d'Aloisio Published: 2025-10-21 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2510.19048v1 Natural disasters always have several effects on human lives. It is challenging for governments to tackle these incidents and to rebuild the economic, social and physical infrastructures and facilities with the available resources (mainly budget and time). Governments always define plans and policies according to the law and political strategies that should maximise social benefits. The severity of damage and the vast resources needed to bring life back to normality make such reconstruction a challenge. This article is the extension of our previously published work by conducting comprehensive comparative analysis by integrating additional deep learning models plus random agent which is used as a baseline. Our prior research introduced a decision support system by using the Deep Reinforcement Learning technique for the planning of post-disaster city reconstruction, maximizing the social benefit of the reconstruction process, considering available resources, meeting the needs of the broad community stakeholders (like citizens' social benefits and politicians' priorities) and keeping in consideration city's structural constraints (like dependencies among roads and buildings). The proposed approach, named post disaster REbuilding plAn ProvIdeR (REPAIR) is generic. It can determine a set of alternative plans for local administrators who select the ideal one to implement, and it can be applied to areas of any extension. We show the application of REPAIR in a real use case, i.e., to the L'Aquila reconstruction process, damaged in 2009 by a major earthquake. --- ### Empowering Decision Trees via Shape Function Branching Authors: Nakul Upadhya, Eldan Cohen Published: 2025-10-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.19040v1 Decision trees are prized for their interpretability and strong performance on tabular data. Yet, their reliance on simple axis-aligned linear splits often forces deep, complex structures to capture non-linear feature effects, undermining human comprehension of the constructed tree. To address this limitation, we propose a novel generalization of a decision tree, the Shape Generalized Tree (SGT), in which each internal node applies a learnable axis-aligned shape function to a single feature, enabling rich, non-linear partitioning in one split. As users can easily visualize each node's shape function, SGTs are inherently interpretable and provide intuitive, visual explanations of the model's decision mechanisms. To learn SGTs from data, we propose ShapeCART, an efficient induction algorithm for SGTs. We further extend the SGT framework to bivariate shape functions (S$^2$GT) and multi-way trees (SGT$_K$), and present Shape$^2$CART and ShapeCART$_K$, extensions to ShapeCART for learning S$^2$GTs and SGT$_K$s, respectively. Experiments on various datasets show that SGTs achieve superior performance with reduced model size compared to traditional axis-aligned linear trees. --- ### From Memorization to Generalization: Fine-Tuning Large Language Models for Biomedical Term-to-Identifier Normalization Authors: Suswitha Pericharla, Daniel B. Hier, Tayo Obafemi-Ajayi Published: 2025-10-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.19036v1 Effective biomedical data integration depends on automated term normalization, the mapping of natural language biomedical terms to standardized identifiers. This linking of terms to identifiers is essential for semantic interoperability. Large language models (LLMs) show promise for this task but perform unevenly across terminologies. We evaluated both memorization (training-term performance) and generalization (validation-term performance) across multiple biomedical ontologies. Fine-tuning Llama 3.1 8B revealed marked differences by terminology. GO mappings showed strong memorization gains (up to 77% improvement in term-to-identifier accuracy), whereas HPO showed minimal improvement. Generalization occurred only for protein-gene (GENE) mappings (13.9% gain), while fine-tuning for HPO and GO yielded negligible transfer. Baseline accuracy varied by model scale, with GPT-4o outperforming both Llama variants for all terminologies. Embedding analyses showed tight semantic alignment between gene symbols and protein names but weak alignment between terms and identifiers for GO or HPO, consistent with limited lexicalization. Fine-tuning success depended on two interacting factors: identifier popularity and lexicalization. Popular identifiers were more likely encountered during pretraining, enhancing memorization. Lexicalized identifiers, such as gene symbols, enabled semantic generalization. By contrast, arbitrary identifiers in GO and HPO constrained models to rote learning. These findings provide a predictive framework for when fine-tuning enhances factual recall versus when it fails due to sparse or non-lexicalized identifiers. --- ### "Over-the-Hood" AI Inclusivity Bugs and How 3 AI Product Teams Found and Fixed Them Authors: Andrew Anderson, Fatima A. Moussaoui, Jimena Noa Guevara, Md Montaser Hamid, Margaret Burnett Published: 2025-10-21 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2510.19033v1 While much research has shown the presence of AI's "under-the-hood" biases (e.g., algorithmic, training data, etc.), what about "over-the-hood" inclusivity biases: barriers in user-facing AI products that disproportionately exclude users with certain problem-solving approaches? Recent research has begun to report the existence of such biases -- but what do they look like, how prevalent are they, and how can developers find and fix them? To find out, we conducted a field study with 3 AI product teams, to investigate what kinds of AI inclusivity bugs exist uniquely in user-facing AI products, and whether/how AI product teams might harness an existing (non-AI-oriented) inclusive design method to find and fix them. The teams' work resulted in identifying 6 types of AI inclusivity bugs arising 83 times, fixes covering 47 of these bug instances, and a new variation of the GenderMag inclusive design method, GenderMag-for-AI, that is especially effective at detecting certain kinds of AI inclusivity bugs. --- ### When Can We Trust LLMs in Mental Health? Large-Scale Benchmarks for Reliable LLM Evaluation Authors: Abeer Badawi, Elahe Rahimi, Md Tahmid Rahman Laskar, Sheri Grach, Lindsay Bertrand, Lames Danok, Jimmy Huang, Frank Rudzicz, Elham Dolatabadi Published: 2025-10-21 Categories: cs.CL, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2510.19032v1 Evaluating Large Language Models (LLMs) for mental health support is challenging due to the emotionally and cognitively complex nature of therapeutic dialogue. Existing benchmarks are limited in scale, reliability, often relying on synthetic or social media data, and lack frameworks to assess when automated judges can be trusted. To address the need for large-scale dialogue datasets and judge reliability assessment, we introduce two benchmarks that provide a framework for generation and evaluation. MentalBench-100k consolidates 10,000 one-turn conversations from three real scenarios datasets, each paired with nine LLM-generated responses, yielding 100,000 response pairs. MentalAlign-70k}reframes evaluation by comparing four high-performing LLM judges with human experts across 70,000 ratings on seven attributes, grouped into Cognitive Support Score (CSS) and Affective Resonance Score (ARS). We then employ the Affective Cognitive Agreement Framework, a statistical methodology using intraclass correlation coefficients (ICC) with confidence intervals to quantify agreement, consistency, and bias between LLM judges and human experts. Our analysis reveals systematic inflation by LLM judges, strong reliability for cognitive attributes such as guidance and informativeness, reduced precision for empathy, and some unreliability in safety and relevance. Our contributions establish new methodological and empirical foundations for reliable, large-scale evaluation of LLMs in mental health. We release the benchmarks and codes at: https://github.com/abeerbadawi/MentalBench/ --- ### CLiVR: Conversational Learning System in Virtual Reality with AI-Powered Patients Authors: Akilan Amithasagaran, Sagnik Dakshit, Bhavani Suryadevara, Lindsey Stockton Published: 2025-10-21 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2510.19031v1 Simulations constitute a fundamental component of medical and nursing education and traditionally employ standardized patients (SP) and high-fidelity manikins to develop clinical reasoning and communication skills. However, these methods require substantial resources, limiting accessibility and scalability. In this study, we introduce CLiVR, a Conversational Learning system in Virtual Reality that integrates large language models (LLMs), speech processing, and 3D avatars to simulate realistic doctor-patient interactions. Developed in Unity and deployed on the Meta Quest 3 platform, CLiVR enables trainees to engage in natural dialogue with virtual patients. Each simulation is dynamically generated from a syndrome-symptom database and enhanced with sentiment analysis to provide feedback on communication tone. Through an expert user study involving medical school faculty (n=13), we assessed usability, realism, and perceived educational impact. Results demonstrated strong user acceptance, high confidence in educational potential, and valuable feedback for improvement. CLiVR offers a scalable, immersive supplement to SP-based training. --- ### Re:Member: Emotional Question Generation from Personal Memories Authors: Zackary Rackauckas, Nobuaki Minematsu, Julia Hirschberg Published: 2025-10-21 Categories: cs.CL, cs.HC arXiv: https://arxiv.org/abs/2510.19030v2 We present Re:Member, a system that explores how emotionally expressive, memory-grounded interaction can support more engaging second language (L2) learning. By drawing on users' personal videos and generating stylized spoken questions in the target language, Re:Member is designed to encourage affective recall and conversational engagement. The system aligns emotional tone with visual context, using expressive speech styles such as whispers or late-night tones to evoke specific moods. It combines WhisperX-based transcript alignment, 3-frame visual sampling, and Style-BERT-VITS2 for emotional synthesis within a modular generation pipeline. Designed as a stylized interaction probe, Re:Member highlights the role of affect and personal media in learner-centered educational technologies. --- ### Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues Authors: Eunsu Kim, Junyeong Park, Juhyun Oh, Kiwoong Park, Seyoung Song, A. Seza Doğruöz, Alice Oh, Najoung Kim Published: 2025-10-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.19028v3 As LLMs are increasingly deployed in real-world interactions, their social reasoning in interpersonal communication becomes critical. To explore their capabilities, we introduce SCRIPTS, a 1.1k-dialogue dataset in English and Korean, sourced from movie scripts and propose a social reasoning task based on SCRIPTS that evaluates the capacity of LLMs to infer the social relationships (e.g., friends, lovers) between speakers in each dialogue. Evaluating nine models on our task, current LLMs achieve around 75--80% on the English dataset and 58--69% in Korean, and models predict an Unlikely relationship in 10--25% of responses in both languages. Furthermore, we find that thinking models and chain-of-thought prompting provide minimal benefits for social reasoning and occasionally amplify social biases. In sum, there are significant limitations in current LLMs' social reasoning capabilities, especially for Korean, highlighting the need for efforts to develop socially-aware LLMs across languages. --- ### FlexiDataGen: An Adaptive LLM Framework for Dynamic Semantic Dataset Generation in Sensitive Domains Authors: Hamed Jelodar, Samita Bai, Roozbeh Razavi-Far, Ali A. Ghorbani Published: 2025-10-21 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2510.19025v1 Dataset availability and quality remain critical challenges in machine learning, especially in domains where data are scarce, expensive to acquire, or constrained by privacy regulations. Fields such as healthcare, biomedical research, and cybersecurity frequently encounter high data acquisition costs, limited access to annotated data, and the rarity or sensitivity of key events. These issues-collectively referred to as the dataset challenge-hinder the development of accurate and generalizable machine learning models in such high-stakes domains. To address this, we introduce FlexiDataGen, an adaptive large language model (LLM) framework designed for dynamic semantic dataset generation in sensitive domains. FlexiDataGen autonomously synthesizes rich, semantically coherent, and linguistically diverse datasets tailored to specialized fields. The framework integrates four core components: (1) syntactic-semantic analysis, (2) retrieval-augmented generation, (3) dynamic element injection, and (4) iterative paraphrasing with semantic validation. Together, these components ensure the generation of high-quality, domain-relevant data. Experimental results show that FlexiDataGen effectively alleviates data shortages and annotation bottlenecks, enabling scalable and accurate machine learning model development. --- ### MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models Authors: Aritra Bhowmik, Denis Korzhenkov, Cees G. M. Snoek, Amirhossein Habibian, Mohsen Ghafoorian Published: 2025-10-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.19022v1 Text-to-video diffusion models have enabled high-quality video synthesis, yet often fail to generate temporally coherent and physically plausible motion. A key reason is the models' insufficient understanding of complex motions that natural videos often entail. Recent works tackle this problem by aligning diffusion model features with those from pretrained video encoders. However, these encoders mix video appearance and dynamics into entangled features, limiting the benefit of such alignment. In this paper, we propose a motion-centric alignment framework that learns a disentangled motion subspace from a pretrained video encoder. This subspace is optimized to predict ground-truth optical flow, ensuring it captures true motion dynamics. We then align the latent features of a text-to-video diffusion model to this new subspace, enabling the generative model to internalize motion knowledge and generate more plausible videos. Our method improves the physical commonsense in a state-of-the-art video diffusion model, while preserving adherence to textual prompts, as evidenced by empirical evaluations on VideoPhy, VideoPhy2, VBench, and VBench-2.0, along with a user study. --- ### Category learning in deep neural networks: Information content and geometry of internal representations Authors: Laurent Bonnasse-Gahot, Jean-Pierre Nadal Published: 2025-10-21 Categories: cs.LG, cs.IT, q-bio.NC arXiv: https://arxiv.org/abs/2510.19021v2 In humans and other animals, category learning enhances discrimination between stimuli close to the category boundary. This phenomenon, called categorical perception, was also empirically observed in artificial neural networks trained on classification tasks. In previous modeling works based on neuroscience data, we show that this expansion/compression is a necessary outcome of efficient learning. Here we extend our theoretical framework to artificial networks. We show that minimizing the Bayes cost (mean of the cross-entropy loss) implies maximizing the mutual information between the set of categories and the neural activities prior to the decision layer. Considering structured data with an underlying feature space of small dimension, we show that maximizing the mutual information implies (i) finding an appropriate projection space, and, (ii) building a neural representation with the appropriate metric. The latter is based on a Fisher information matrix measuring the sensitivity of the neural activity to changes in the projection space. Optimal learning makes this neural Fisher information follow a category-specific Fisher information, measuring the sensitivity of the category membership. Category learning thus induces an expansion of neural space near decision boundaries. We characterize the properties of the categorical Fisher information, showing that its eigenvectors give the most discriminant directions at each point of the projection space. We find that, unexpectedly, its maxima are in general not exactly at, but near, the class boundaries. Considering toy models and the MNIST dataset, we numerically illustrate how after learning the two Fisher information matrices match, and essentially align with the category boundaries. Finally, we relate our approach to the Information Bottleneck one, and we exhibit a bias-variance decomposition of the Bayes cost, of interest on its own. --- ### Calibrated Principal Component Regression Authors: Yixuan Florence Wu, Yilun Zhu, Lei Cao, Naichen Shi Published: 2025-10-21 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.19020v2 We propose a new method for statistical inference in generalized linear models. In the overparameterized regime, Principal Component Regression (PCR) reduces variance by projecting high-dimensional data to a low-dimensional principal subspace before fitting. However, PCR incurs truncation bias whenever the true regression vector has mass outside the retained principal components (PC). To mitigate the bias, we propose Calibrated Principal Component Regression (CPCR), which first learns a low-variance prior in the PC subspace and then calibrates the model in the original feature space via a centered Tikhonov step. CPCR leverages cross-fitting and controls the truncation bias by softening PCR's hard cutoff. Theoretically, we calculate the out-of-sample risk in the random matrix regime, which shows that CPCR outperforms standard PCR when the regression signal has non-negligible components in low-variance directions. Empirically, CPCR consistently improves prediction across multiple overparameterized problems. The results highlight CPCR's stability and flexibility in modern overparameterized settings. --- ### Prior-informed optimization of treatment recommendation via bandit algorithms trained on large language model-processed historical records Authors: Saman Nessari, Ali Bozorgi-Amiri Published: 2025-10-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2510.19014v1 Current medical practice depends on standardized treatment frameworks and empirical methodologies that neglect individual patient variations, leading to suboptimal health outcomes. We develop a comprehensive system integrating Large Language Models (LLMs), Conditional Tabular Generative Adversarial Networks (CTGAN), T-learner counterfactual models, and contextual bandit approaches to provide customized, data-informed clinical recommendations. The approach utilizes LLMs to process unstructured medical narratives into structured datasets (93.2% accuracy), uses CTGANs to produce realistic synthetic patient data (55% accuracy via two-sample verification), deploys T-learners to forecast patient-specific treatment responses (84.3% accuracy), and integrates prior-informed contextual bandits to enhance online therapeutic selection by effectively balancing exploration of new possibilities with exploitation of existing knowledge. Testing on stage III colon cancer datasets revealed that our KernelUCB approach obtained 0.60-0.61 average reward scores across 5,000 rounds, exceeding other reference methods. This comprehensive system overcomes cold-start limitations in online learning environments, improves computational effectiveness, and constitutes notable progress toward individualized medicine adapted to specific patient characteristics. --- ### Plural Voices, Single Agent: Towards Inclusive AI in Multi-User Domestic Spaces Authors: Joydeep Chandra, Satyam Kumar Navneet Published: 2025-10-21 Categories: cs.HC, cs.AI, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2510.19008v1 Domestic AI agents faces ethical, autonomy, and inclusion challenges, particularly for overlooked groups like children, elderly, and Neurodivergent users. We present the Plural Voices Model (PVM), a novel single-agent framework that dynamically negotiates multi-user needs through real-time value alignment, leveraging diverse public datasets on mental health, eldercare, education, and moral reasoning. Using human+synthetic curriculum design with fairness-aware scenarios and ethical enhancements, PVM identifies core values, conflicts, and accessibility requirements to inform inclusive principles. Our privacy-focused prototype features adaptive safety scaffolds, tailored interactions (e.g., step-by-step guidance for Neurodivergent users, simple wording for children), and equitable conflict resolution. In preliminary evaluations, PVM outperforms multi-agent baselines in compliance (76% vs. 70%), fairness (90% vs. 85%), safety-violation rate (0% vs. 7%), and latency. Design innovations, including video guidance, autonomy sliders, family hubs, and adaptive safety dashboards, demonstrate new directions for ethical and inclusive domestic AI, for building user-centered agentic systems in plural domestic contexts. Our Codes and Model are been open sourced, available for reproduction: https://github.com/zade90/Agora --- ### Dynamic Evaluation for Oversensitivity in LLMs Authors: Sophia Xiao Pu, Sitao Cheng, Xin Eric Wang, William Yang Wang Published: 2025-10-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.19005v1 Oversensitivity occurs when language models defensively reject prompts that are actually benign. This behavior not only disrupts user interactions but also obscures the boundary between harmful and harmless content. Existing benchmarks rely on static datasets that degrade overtime as models evolve, leading to data contamination and diminished evaluative power. To address this, we develop a framework that dynamically generates model-specific challenging datasets, capturing emerging defensive patterns and aligning with each model's unique behavior. Building on this approach, we construct OVERBENCH, a benchmark that aggregates these datasets across diverse LLM families, encompassing 450,000 samples from 25 models. OVERBENCH provides a dynamic and evolving perspective on oversensitivity, allowing for continuous monitoring of defensive triggers as models advance, highlighting vulnerabilities that static datasets overlook. --- ### $Δ$t-Mamba3D: A Time-Aware Spatio-Temporal State-Space Model for Breast Cancer Risk Prediction Authors: Zhengbo Zhou, Dooman Arefan, Margarita Zuley, Shandong Wu Published: 2025-10-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.19003v1 Longitudinal analysis of sequential radiological images is hampered by a fundamental data challenge: how to effectively model a sequence of high-resolution images captured at irregular time intervals. This data structure contains indispensable spatial and temporal cues that current methods fail to fully exploit. Models often compromise by either collapsing spatial information into vectors or applying spatio-temporal models that are computationally inefficient and incompatible with non-uniform time steps. We address this challenge with Time-Aware $Δ$t-Mamba3D, a novel state-space architecture adapted for longitudinal medical imaging. Our model simultaneously encodes irregular inter-visit intervals and rich spatio-temporal context while remaining computationally efficient. Its core innovation is a continuous-time selective scanning mechanism that explicitly integrates the true time difference between exams into its state transitions. This is complemented by a multi-scale 3D neighborhood fusion module that robustly captures spatio-temporal relationships. In a comprehensive breast cancer risk prediction benchmark using sequential screening mammogram exams, our model shows superior performance, improving the validation c-index by 2-5 percentage points and achieving higher 1-5 year AUC scores compared to established variants of recurrent, transformer, and state-space models. Thanks to its linear complexity, the model can efficiently process long and complex patient screening histories of mammograms, forming a new framework for longitudinal image analysis. --- ### Impartial Selection with Predictions Authors: Javier Cembrano, Felix Fischer, Max Klimm Published: 2025-10-21 Categories: cs.GT, cs.LG, econ.TH, math.OC arXiv: https://arxiv.org/abs/2510.19002v1 We study the selection of agents based on mutual nominations, a theoretical problem with many applications from committee selection to AI alignment. As agents both select and are selected, they may be incentivized to misrepresent their true opinion about the eligibility of others to influence their own chances of selection. Impartial mechanisms circumvent this issue by guaranteeing that the selection of an agent is independent of the nominations cast by that agent. Previous research has established strong bounds on the performance of impartial mechanisms, measured by their ability to approximate the number of nominations for the most highly nominated agents. We study to what extent the performance of impartial mechanisms can be improved if they are given a prediction of a set of agents receiving a maximum number of nominations. Specifically, we provide bounds on the consistency and robustness of such mechanisms, where consistency measures the performance of the mechanisms when the prediction is accurate and robustness its performance when the prediction is inaccurate. For the general setting where up to $k$ agents are to be selected and agents nominate any number of other agents, we give a mechanism with consistency $1-O\big(\frac{1}{k}\big)$ and robustness $1-\frac{1}{e}-O\big(\frac{1}{k}\big)$. For the special case of selecting a single agent based on a single nomination per agent, we prove that $1$-consistency can be achieved while guaranteeing $\frac{1}{2}$-robustness. A close comparison with previous results shows that (asymptotically) optimal consistency can be achieved with little to no sacrifice in terms of robustness. --- ### Robust Driving QA through Metadata-Grounded Context and Task-Specific Prompts Authors: Seungjun Yu, Junsung Park, Youngsun Lim, Hyunjung Shim Published: 2025-10-21 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2510.19001v1 We present a two-phase vision-language QA system for autonomous driving that answers high-level perception, prediction, and planning questions. In Phase-1, a large multimodal LLM (Qwen2.5-VL-32B) is conditioned on six-camera inputs, a short temporal window of history, and a chain-of-thought prompt with few-shot exemplars. A self-consistency ensemble (multiple sampled reasoning chains) further improves answer reliability. In Phase-2, we augment the prompt with nuScenes scene metadata (object annotations, ego-vehicle state, etc.) and category-specific question instructions (separate prompts for perception, prediction, planning tasks). In experiments on a driving QA benchmark, our approach significantly outperforms the baseline Qwen2.5 models. For example, using 5 history frames and 10-shot prompting in Phase-1 yields 65.1% overall accuracy (vs.62.61% with zero-shot); applying self-consistency raises this to 66.85%. Phase-2 achieves 67.37% overall. Notably, the system maintains 96% accuracy under severe visual corruption. These results demonstrate that carefully engineered prompts and contextual grounding can greatly enhance high-level driving QA with pretrained vision-language models. ---