# Research Papers — 2025-10 · bundle page 17 of 217 > Full-text markdown of papers #801–850 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/17 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/16.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/18.md) ### Ideology-Based LLMs for Content Moderation Authors: Stefano Civelli, Pietro Bernardelle, Nardiena A. Pratama, Gianluca Demartini Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25805v1 Large language models (LLMs) are increasingly used in content moderation systems, where ensuring fairness and neutrality is essential. In this study, we examine how persona adoption influences the consistency and fairness of harmful content classification across different LLM architectures, model sizes, and content modalities (language vs. vision). At first glance, headline performance metrics suggest that personas have little impact on overall classification accuracy. However, a closer analysis reveals important behavioral shifts. Personas with different ideological leanings display distinct propensities to label content as harmful, showing that the lens through which a model "views" input can subtly shape its judgments. Further agreement analyses highlight that models, particularly larger ones, tend to align more closely with personas from the same political ideology, strengthening within-ideology consistency while widening divergence across ideological groups. To show this effect more directly, we conducted an additional study on a politically targeted task, which confirmed that personas not only behave more coherently within their own ideology but also exhibit a tendency to defend their perspective while downplaying harmfulness in opposing views. Together, these findings highlight how persona conditioning can introduce subtle ideological biases into LLM outputs, raising concerns about the use of AI systems that may reinforce partisan perspectives under the guise of neutrality. --- ### Beyond Length: Quantifying Long-Range Information for Long-Context LLM Pretraining Data Authors: Haoran Deng, Yingyu Lin, Zhenghao Lin, Xiao Liu, Yizhou Sun, Yi-An Ma, Yeyun Gong Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25804v1 Long-context language models unlock advanced capabilities in reasoning, code generation, and document summarization by leveraging dependencies across extended spans of text. However, a significant portion of readily available long-text data lacks meaningful long-distance dependencies; most spans can be predicted using only local context. Training on such data is inefficient, making careful data selection crucial. Therefore, we introduce LongFilter, a framework for curating training data tailored to long-context pretraining. LongFilter measures the information gain provided by extended context by contrasting model predictions under long-context versus short-context settings, thereby identifying samples where long-range dependencies are essential. Experiments with LLaMA-3-8B, extending its context length from 8K to 64K, show that LongFilter efficiently selects high-quality data and yields substantial improvements on benchmarks such as HELMET, LongBench, and RULER. --- ### Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training Authors: Hong Wang, Haiyang Xin, Jie Wang, Xuanze Yang, Fei Zha, Huanshuo Dong, Yan Jiang Published: 2025-10-29 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2510.25803v2 Pre-training has proven effective in addressing data scarcity and performance limitations in solving PDE problems with neural operators. However, challenges remain due to the heterogeneity of PDE datasets in equation types, which leads to high errors in mixed training. Additionally, dense pre-training models that scale parameters by increasing network width or depth incur significant inference costs. To tackle these challenges, we propose a novel Mixture-of-Experts Pre-training Operator Transformer (MoE-POT), a sparse-activated architecture that scales parameters efficiently while controlling inference costs. Specifically, our model adopts a layer-wise router-gating network to dynamically select 4 routed experts from 16 expert networks during inference, enabling the model to focus on equation-specific features. Meanwhile, we also integrate 2 shared experts, aiming to capture common properties of PDE and reduce redundancy among routed experts. The final output is computed as the weighted average of the results from all activated experts. We pre-train models with parameters from 30M to 0.5B on 6 public PDE datasets. Our model with 90M activated parameters achieves up to a 40% reduction in zero-shot error compared with existing models with 120M activated parameters. Additionally, we conduct interpretability analysis, showing that dataset types can be inferred from router-gating network decisions, which validates the rationality and effectiveness of the MoE architecture. --- ### Attention Augmented GNN RNN-Attention Models for Advanced Cybersecurity Intrusion Detection Authors: Jayant Biradar, Smit Shah, Tanmay Naik Published: 2025-10-29 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2510.25802v1 In this paper, we propose a novel hybrid deep learning architecture that synergistically combines Graph Neural Networks (GNNs), Recurrent Neural Networks (RNNs), and multi-head attention mechanisms to significantly enhance cybersecurity intrusion detection capabilities. By leveraging the comprehensive UNSW-NB15 dataset containing diverse network traffic patterns, our approach effectively captures both spatial dependencies through graph structural relationships and temporal dynamics through sequential analysis of network events. The integrated attention mechanism provides dual benefits of improved model interpretability and enhanced feature selection, enabling cybersecurity analysts to focus computational resources on high-impact security events -- a critical requirement in modern real-time intrusion detection systems. Our extensive experimental evaluation demonstrates that the proposed hybrid model achieves superior performance compared to traditional machine learning approaches and standalone deep learning models across multiple evaluation metrics, including accuracy, precision, recall, and F1-score. The model achieves particularly strong performance in detecting sophisticated attack patterns such as Advanced Persistent Threats (APTs), Distributed Denial of Service (DDoS) attacks, and zero-day exploits, making it a promising solution for next-generation cybersecurity applications in complex network environments. --- ### Metis-SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start Authors: Kun Chen, Peng Shi, Haibo Qiu, Zhixiong Zeng, Siqi Yang, Wenji Mao, Lin Ma Published: 2025-10-29 Categories: cs.LG, cs.AI, cs.CL, cs.CV arXiv: https://arxiv.org/abs/2510.25801v3 Reinforcement learning (RL) with verifiable rewards has recently catalyzed a wave of "MLLM-r1" approaches that bring RL to vision language models. Most representative paradigms begin with a cold start, typically employing supervised fine-tuning (SFT), to initialize the policy before RL. However, SFT-based cold start adopts the reasoning paradigm intertwined with task solution and output format, which may induce instruction-style overfitting, weakens out-of-distribution generalization, and ultimately affects downstream RL. We revisit the cold start along two views, its training method and data construction, and introduce the Generalization Factor (GF) coefficient to quantify the generalization capability under different methods. Our empirical study finds that preference-based training methods (e.g. DPO) generalizes better than SFT-based methods in cold start. Motivated by this, we propose SPECS-a Self-distilled, Preference-based Cold Start framework that decouples multimodal learning: (1) generates introspective preference data pairs via self-distillation, avoiding reliance on larger teachers or manual annotation; (2) performs preference-based training to learn, focusing on shallow, transferable surface-form criteria (format, structure, style) rather than memorizing content; and (3) hands off to RL with verifiable rewards for deep reasoning results. Experimental results across multiple multimodal benchmarks show that our decoupling learning framework yields consistent performance gains over strong baselines, improving MEGA-Bench by 4.1% and MathVista by 12.2%. Additional experiments indicate that SPECS contributes to reducing in-distribution "stuckness," improving exploration, stabilizing training, and raising the performance ceiling. Project Page: https://kwen-chen.github.io/SPECS-VL/ --- ### FreIE: Low-Frequency Spectral Bias in Neural Networks for Time-Series Tasks Authors: Jialong Sun, Xinpeng Ling, Jiaxuan Zou, Jiawen Kang, Kejia Zhang Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25800v1 The inherent autocorrelation of time series data presents an ongoing challenge to multivariate time series prediction. Recently, a widely adopted approach has been the incorporation of frequency domain information to assist in long-term prediction tasks. Many researchers have independently observed the spectral bias phenomenon in neural networks, where models tend to fit low-frequency signals before high-frequency ones. However, these observations have often been attributed to the specific architectures designed by the researchers, rather than recognizing the phenomenon as a universal characteristic across models. To unify the understanding of the spectral bias phenomenon in long-term time series prediction, we conducted extensive empirical experiments to measure spectral bias in existing mainstream models. Our findings reveal that virtually all models exhibit this phenomenon. To mitigate the impact of spectral bias, we propose the FreLE (Frequency Loss Enhancement) algorithm, which enhances model generalization through both explicit and implicit frequency regularization. This is a plug-and-play model loss function unit. A large number of experiments have proven the superior performance of FreLE. Code is available at https://github.com/Chenxing-Xuan/FreLE. --- ### LISTEN to Your Preferences: An LLM Framework for Multi-Objective Selection Authors: Adam S. Jovine, Tinghan Ye, Francis Bahk, Jingjing Wang, Matthew Ford, David B. Shmoys, Peter I. Frazier Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25799v3 Human experts often struggle to select the best option from a large set of items with multiple competing objectives, a process bottlenecked by the difficulty of formalizing complex, implicit preferences. To address this, we introduce LISTEN (LLM-based Iterative Selection with Trade-off Evaluation from Natural-language), an agentic LLM-based framework that treats the LLM as a decision-making agent capable of iteratively refining its internal preference model and taking actions (e.g., proposing utilities or selecting candidates) to maximize alignment with a user's implicit goals. To operate within LLM constraints like context windows and inference costs, we propose two iterative algorithms: LISTEN-U, which uses the LLM to refine a parametric utility function, and LISTEN-T, a non-parametric method that performs tournament-style selections over small batches of solutions. Evaluated on diverse tasks including flight booking, shopping, and exam scheduling, our results show LISTEN-U excels when preferences are parametrically aligned (a property we measure with a novel concordance metric), while LISTEN-T offers more robust performance overall. This work explores a promising direction for steering complex multi-objective decisions directly with natural language, reducing the cognitive burden of traditional preference elicitation. Code is available at https://github.com/AdamJovine/LISTEN; data is available at https://huggingface.co/datasets/AdamJovine/LISTEN-benchmark. --- ### MemEIC: A Step Toward Continual and Compositional Knowledge Editing Authors: Jin Seong, Jiyun Park, Wencke Liermann, Hongseok Choi, Yoonji Nam, Hyun Kim, Soojong Lim, Namhoon Lee Published: 2025-10-29 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.25798v1 The dynamic nature of information necessitates continuously updating large vision-language models (LVLMs). While recent knowledge editing techniques hint at promising directions, they often focus on editing a single modality (vision or language) in isolation. This prevalent practice neglects the inherent multimodality of LVLMs and the continuous nature of knowledge updates, potentially leading to suboptimal editing outcomes when considering the interplay between modalities and the need for ongoing knowledge refinement. To address these limitations, we propose MemEIC, a novel method for Continual and Compositional Knowledge Editing (CCKE) in LVLMs. MemEIC enables compositional editing of both visual and textual knowledge sequentially. Our approach employs a hybrid external-internal editor featuring a dual external memory for cross-modal evidence retrieval and dual LoRA adapters that facilitate disentangled parameter updates for each modality. A key component is a brain-inspired knowledge connector, activated selectively for compositional reasoning, that integrates information across different modalities. Experiments demonstrate that MemEIC significantly improves performance on complex multimodal questions and effectively preserves prior edits, setting a new benchmark for CCKE in LVLMs. --- ### Enhancing Underwater Object Detection through Spatio-Temporal Analysis and Spatial Attention Networks Authors: Sai Likhith Karri, Ansh Saxena Published: 2025-10-29 Categories: cs.CV, cs.CL, cs.RO arXiv: https://arxiv.org/abs/2510.25797v1 This study examines the effectiveness of spatio-temporal modeling and the integration of spatial attention mechanisms in deep learning models for underwater object detection. Specifically, in the first phase, the performance of temporal-enhanced YOLOv5 variant T-YOLOv5 is evaluated, in comparison with the standard YOLOv5. For the second phase, an augmented version of T-YOLOv5 is developed, through the addition of a Convolutional Block Attention Module (CBAM). By examining the effectiveness of the already pre-existing YOLOv5 and T-YOLOv5 models and of the newly developed T-YOLOv5 with CBAM. With CBAM, the research highlights how temporal modeling improves detection accuracy in dynamic marine environments, particularly under conditions of sudden movements, partial occlusions, and gradual motion. The testing results showed that YOLOv5 achieved a mAP@50-95 of 0.563, while T-YOLOv5 and T-YOLOv5 with CBAM outperformed with mAP@50-95 scores of 0.813 and 0.811, respectively, highlighting their superior accuracy and generalization in detecting complex objects. The findings demonstrate that T-YOLOv5 significantly enhances detection reliability compared to the standard model, while T-YOLOv5 with CBAM further improves performance in challenging scenarios, although there is a loss of accuracy when it comes to simpler scenarios. --- ### VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning Authors: Baolu Li, Yiming Zhang, Qinghe Wang, Liqian Ma, Xiaoyu Shi, Xintao Wang, Pengfei Wan, Zhenfei Yin, Yunzhi Zhuge, Huchuan Lu, Xu Jia Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25772v1 Visual effects (VFX) are crucial to the expressive power of digital media, yet their creation remains a major challenge for generative AI. Prevailing methods often rely on the one-LoRA-per-effect paradigm, which is resource-intensive and fundamentally incapable of generalizing to unseen effects, thus limiting scalability and creation. To address this challenge, we introduce VFXMaster, the first unified, reference-based framework for VFX video generation. It recasts effect generation as an in-context learning task, enabling it to reproduce diverse dynamic effects from a reference video onto target content. In addition, it demonstrates remarkable generalization to unseen effect categories. Specifically, we design an in-context conditioning strategy that prompts the model with a reference example. An in-context attention mask is designed to precisely decouple and inject the essential effect attributes, allowing a single unified model to master the effect imitation without information leakage. In addition, we propose an efficient one-shot effect adaptation mechanism to boost generalization capability on tough unseen effects from a single user-provided video rapidly. Extensive experiments demonstrate that our method effectively imitates various categories of effect information and exhibits outstanding generalization to out-of-domain effects. To foster future research, we will release our code, models, and a comprehensive dataset to the community. --- ### Gaperon: A Peppered English-French Generative Language Model Suite Authors: Nathan Godey, Wissam Antoun, Rian Touchent, Rachel Bawden, Éric de la Clergerie, Benoît Sagot, Djamé Seddah Published: 2025-10-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.25771v1 We release Gaperon, a fully open suite of French-English-coding language models designed to advance transparency and reproducibility in large-scale model training. The Gaperon family includes 1.5B, 8B, and 24B parameter models trained on 2-4 trillion tokens, released with all elements of the training pipeline: French and English datasets filtered with a neural quality classifier, an efficient data curation and training framework, and hundreds of intermediate checkpoints. Through this work, we study how data filtering and contamination interact to shape both benchmark and generative performance. We find that filtering for linguistic quality enhances text fluency and coherence but yields subpar benchmark results, and that late deliberate contamination -- continuing training on data mixes that include test sets -- recovers competitive scores while only reasonably harming generation quality. We discuss how usual neural filtering can unintentionally amplify benchmark leakage. To support further research, we also introduce harmless data poisoning during pretraining, providing a realistic testbed for safety studies. By openly releasing all models, datasets, code, and checkpoints, Gaperon establishes a reproducible foundation for exploring the trade-offs between data curation, evaluation, safety, and openness in multilingual language model development. --- ### E-Scores for (In)Correctness Assessment of Generative Model Outputs Authors: Guneet S. Dhillon, Javier González, Teodora Pandeva, Alicia Curth Published: 2025-10-29 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.25770v2 While generative models, especially large language models (LLMs), are ubiquitous in today's world, principled mechanisms to assess their (in)correctness are limited. Using the conformal prediction framework, previous works construct sets of LLM responses where the probability of including an incorrect response, or error, is capped at a user-defined tolerance level. However, since these methods are based on p-values, they are susceptible to p-hacking, i.e., choosing the tolerance level post-hoc can invalidate the guarantees. We therefore leverage e-values to complement generative model outputs with e-scores as measures of incorrectness. In addition to achieving the guarantees as before, e-scores further provide users with the flexibility of choosing data-dependent tolerance levels while upper bounding size distortion, a post-hoc notion of error. We experimentally demonstrate their efficacy in assessing LLM outputs under different forms of correctness: mathematical factuality and property constraints satisfaction. --- ### Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions Authors: Naoki Kiyohara, Edward Johns, Yingzhen Li Published: 2025-10-29 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.25769v1 Stochastic differential equations (SDEs) are well suited to modelling noisy and irregularly sampled time series found in finance, physics, and machine learning. Traditional approaches require costly numerical solvers to sample between arbitrary time points. We introduce Neural Stochastic Flows (NSFs) and their latent variants, which directly learn (latent) SDE transition laws using conditional normalising flows with architectural constraints that preserve properties inherited from stochastic flows. This enables one-shot sampling between arbitrary states and yields up to two orders of magnitude speed-ups at large time gaps. Experiments on synthetic SDE simulations and on real-world tracking and video data show that NSFs maintain distributional accuracy comparable to numerical approaches while dramatically reducing computation for arbitrary time-point sampling. --- ### Decomposition-Enhanced Training for Post-Hoc Attributions In Language Models Authors: Sriram Balasubramanian, Samyadeep Basu, Koustava Goswami, Ryan Rossi, Varun Manjunatha, Roshan Santhosh, Ruiyi Zhang, Soheil Feizi, Nedim Lipka Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25766v3 Large language models (LLMs) are increasingly used for long-document question answering, where reliable attribution to sources is critical for trust. Existing post-hoc attribution methods work well for extractive QA but struggle in multi-hop, abstractive, and semi-extractive settings, where answers synthesize information across passages. To address these challenges, we argue that post-hoc attribution can be reframed as a reasoning problem, where answers are decomposed into constituent units, each tied to specific context. We first show that prompting models to generate such decompositions alongside attributions improves performance. Building on this, we introduce DecompTune, a post-training method that teaches models to produce answer decompositions as intermediate reasoning steps. We curate a diverse dataset of complex QA tasks, annotated with decompositions by a strong LLM, and post-train Qwen-2.5 (7B and 14B) using a two-stage SFT + GRPO pipeline with task-specific curated rewards. Across extensive experiments and ablations, DecompTune substantially improves attribution quality, outperforming prior methods and matching or exceeding state-of-the-art frontier models. --- ### FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion Authors: Chuhao Chen, Isabella Liu, Xinyue Wei, Hao Su, Minghua Liu Published: 2025-10-29 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2510.25765v2 Articulated 3D objects are central to many applications in robotics, AR/VR, and animation. Recent approaches to modeling such objects either rely on optimization-based reconstruction pipelines that require dense-view supervision or on feed-forward generative models that produce coarse geometric approximations and often overlook surface texture. In contrast, open-world 3D generation of static objects has achieved remarkable success, especially with the advent of native 3D diffusion models such as Trellis. However, extending these methods to articulated objects by training native 3D diffusion models poses significant challenges. In this work, we present FreeArt3D, a training-free framework for articulated 3D object generation. Instead of training a new model on limited articulated data, FreeArt3D repurposes a pre-trained static 3D diffusion model (e.g., Trellis) as a powerful shape prior. It extends Score Distillation Sampling (SDS) into the 3D-to-4D domain by treating articulation as an additional generative dimension. Given a few images captured in different articulation states, FreeArt3D jointly optimizes the object's geometry, texture, and articulation parameters without requiring task-specific training or access to large-scale articulated datasets. Our method generates high-fidelity geometry and textures, accurately predicts underlying kinematic structures, and generalizes well across diverse object categories. Despite following a per-instance optimization paradigm, FreeArt3D completes in minutes and significantly outperforms prior state-of-the-art approaches in both quality and versatility. Please check our website for more details: https://czzzzh.github.io/FreeArt3D --- ### DiagramEval: Evaluating LLM-Generated Diagrams via Graphs Authors: Chumeng Liang, Jiaxuan You Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25761v2 Diagrams play a central role in research papers for conveying ideas, yet they are often notoriously complex and labor-intensive to create. Although diagrams are presented as images, standard image generative models struggle to produce clear diagrams with well-defined structure. We argue that a promising direction is to generate demonstration diagrams directly in textual form as SVGs, which can leverage recent advances in large language models (LLMs). However, due to the complexity of components and the multimodal nature of diagrams, sufficiently discriminative and explainable metrics for evaluating the quality of LLM-generated diagrams remain lacking. In this paper, we propose DiagramEval, a novel evaluation metric designed to assess demonstration diagrams generated by LLMs. Specifically, DiagramEval conceptualizes diagrams as graphs, treating text elements as nodes and their connections as directed edges, and evaluates diagram quality using two new groups of metrics: node alignment and path alignment. For the first time, we effectively evaluate diagrams produced by state-of-the-art LLMs on recent research literature, quantitatively demonstrating the validity of our metrics. Furthermore, we show how the enhanced explainability of our proposed metrics offers valuable insights into the characteristics of LLM-generated diagrams. Code: https://github.com/ulab-uiuc/diagram-eval. --- ### Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks Authors: Xu Zheng, Zihao Dongfang, Lutao Jiang, Boyuan Zheng, Yulong Guo, Zhenquan Zhang, Giuliano Albanese, Runyi Yang, Mengjiao Ma, Zixin Zhang, Chenfei Liao, Dingcheng Zhen et al. Published: 2025-10-29 Categories: cs.CV arXiv: https://arxiv.org/abs/2510.25760v2 Humans possess spatial reasoning abilities that enable them to understand spaces through multimodal observations, such as vision and sound. Large multimodal reasoning models extend these abilities by learning to perceive and reason, showing promising performance across diverse spatial tasks. However, systematic reviews and publicly available benchmarks for these models remain limited. In this survey, we provide a comprehensive review of multimodal spatial reasoning tasks with large models, categorizing recent progress in multimodal large language models (MLLMs) and introducing open benchmarks for evaluation. We begin by outlining general spatial reasoning, focusing on post-training techniques, explainability, and architecture. Beyond classical 2D tasks, we examine spatial relationship reasoning, scene and layout understanding, as well as visual question answering and grounding in 3D space. We also review advances in embodied AI, including vision-language navigation and action models. Additionally, we consider emerging modalities such as audio and egocentric video, which contribute to novel spatial understanding through new sensors. We believe this survey establishes a solid foundation and offers insights into the growing field of multimodal spatial reasoning. Updated information about this survey, codes and implementation of the open benchmarks can be found at https://github.com/zhengxuJosh/Awesome-Spatial-Reasoning. --- ### Synthetic Data Reveals Generalization Gaps in Correlated Multiple Instance Learning Authors: Ethan Harvey, Dennis Johan Loevlie, Michael C. Hughes Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25759v2 Multiple instance learning (MIL) is often used in medical imaging to classify high-resolution 2D images by processing patches or classify 3D volumes by processing slices. However, conventional MIL approaches treat instances separately, ignoring contextual relationships such as the appearance of nearby patches or slices that can be essential in real applications. We design a synthetic classification task where accounting for adjacent instance features is crucial for accurate prediction. We demonstrate the limitations of off-the-shelf MIL approaches by quantifying their performance compared to the optimal Bayes estimator for this task, which is available in closed-form. We empirically show that newer correlated MIL methods still do not achieve the best possible performance when trained with ten thousand training samples, each containing many instances. --- ### TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling Authors: He Hu, Chiyuan Ma, Qianning Wang, Lin Liu, Yucheng Zhou, Laizhong Cui, Fei Ma, Qi Tian Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25758v2 The shortage of mental health professionals has driven the web to become a primary avenue for accessible psychological support. While Large Language Models (LLMs) offer promise for scalable web-based counseling, existing approaches often lack emotional understanding, adaptive strategies, and long-term memory. These limitations pose risks to digital well-being, as disjointed interactions can fail to support vulnerable users effectively. To address these gaps, we introduce TheraMind, a strategic and adaptive agent designed for trustworthy online longitudinal counseling. The cornerstone of TheraMind is a novel dual-loop architecture that decouples the complex counseling process into an Intra-Session Loop for tactical dialogue management and a Cross-Session Loop for strategic therapeutic planning. The Intra-Session Loop perceives the patient's emotional state to dynamically select response strategies while leveraging cross-session memory to ensure continuity. Crucially, the Cross-Session Loop empowers the agent with long-term adaptability by evaluating the efficacy of the applied therapy after each session and adjusting the method for subsequent interactions. We validate our approach in a high-fidelity simulation environment grounded in real clinical cases. Extensive evaluations show that TheraMind outperforms other methods, especially on multi-session metrics like Coherence, Flexibility, and Therapeutic Attunement, validating the effectiveness of its dual-loop design in emulating strategic, adaptive, and longitudinal therapeutic behavior. The code is publicly available at https://github.com/Emo-gml/TheraMind. --- ### MLPrE -- A tool for preprocessing and exploratory data analysis prior to machine learning model construction Authors: David S Maxwell, Michael Darkoh, Sidharth R Samudrala, Caroline Chung, Stephanie T Schmidt, Bissan Al-Lazikani Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25755v1 With the recent growth of Deep Learning for AI, there is a need for tools to meet the demand of data flowing into those models. In some cases, source data may exist in multiple formats, and therefore the source data must be investigated and properly engineered for a Machine Learning model or graph database. Overhead and lack of scalability with existing workflows limit integration within a larger processing pipeline such as Apache Airflow, driving the need for a robust, extensible, and lightweight tool to preprocess arbitrary datasets that scales with data type and size. To address this, we present Machine Learning Preprocessing and Exploratory Data Analysis, MLPrE, in which SparkDataFrames were utilized to hold data during processing and ensure scalability. A generalizable JSON input file format was utilized to describe stepwise changes to that DataFrame. Stages were implemented for input and output, filtering, basic statistics, feature engineering, and exploratory data analysis. A total of 69 stages were implemented into MLPrE, of which we highlight and demonstrate key stages using six diverse datasets. We further highlight MLPrE's ability to independently process multiple fields in flat files and recombine them, otherwise requiring an additional pipeline, using a UniProt glossary term dataset. Building on this advantage, we demonstrated the clustering stage with available wine quality data. Lastly, we demonstrate the preparation of data for a graph database in the final stages of MLPrE using phosphosite kinase data. Overall, our MLPrE tool offers a generalizable and scalable tool for preprocessing and early data analysis, filling a critical need for such a tool given the ever expanding use of machine learning. This tool serves to accelerate and simplify early stage development in larger workflows. --- ### How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs Authors: Samet Demir, Zafer Dogan Published: 2025-10-29 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2510.25753v2 Pretrained Transformers demonstrate remarkable in-context learning (ICL) capabilities, enabling them to adapt to new tasks from demonstrations without parameter updates. However, theoretical studies often rely on simplified architectures (e.g., omitting MLPs), plain data models (e.g., linear regression with isotropic inputs), and single-source training, limiting their relevance to realistic settings. In this work, we study ICL in pretrained Transformers with nonlinear MLP heads on nonlinear tasks drawn from multiple data sources with heterogeneous input, task, and noise distributions. We analyze a model where the MLP comprises two layers, with the first layer trained via a single gradient step and the second layer fully optimized. Under high-dimensional asymptotics, we prove that such models are equivalent in ICL error to structured polynomial predictors, leveraging results from the theory of Gaussian universality and orthogonal polynomials. This equivalence reveals that nonlinear MLPs meaningfully enhance ICL performance, particularly on nonlinear tasks, compared to linear baselines. It also enables a precise analysis of data mixing effects: we identify key properties of high-quality data sources (low noise, structured covariances) and show that feature learning emerges only when the task covariance exhibits sufficient structure. These results are validated empirically across various activation functions, model sizes, and data distributions. Finally, we experiment with a real-world scenario involving multilingual sentiment analysis where each language is treated as a different source. Our experimental results for this case exemplify how our findings extend to real-world cases. Overall, our work advances the theoretical foundations of ICL in Transformers and provides actionable insight into the role of architecture and data in ICL. --- ### Meshless solutions of PDE inverse problems on irregular geometries Authors: James V. Roggeveen, Michael P. Brenner Published: 2025-10-29 Categories: math.NA, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2510.25752v1 Solving inverse and optimization problems over solutions of nonlinear partial differential equations (PDEs) on complex spatial domains is a long-standing challenge. Here we introduce a method that parameterizes the solution using spectral bases on arbitrary spatiotemporal domains, whereby the basis is defined on a hyperrectangle containing the true domain. We find the coefficients of the basis expansion by solving an optimization problem whereby both the equations, the boundary conditions and any optimization targets are enforced by a loss function, building on a key idea from Physics-Informed Neural Networks (PINNs). Since the representation of the function natively has exponential convergence, so does the solution of the optimization problem, as long as it can be solved efficiently. We find empirically that the optimization protocols developed for machine learning find solutions with exponential convergence on a wide range of equations. The method naturally allows for the incorporation of data assimilation by including additional terms in the loss function, and for the efficient solution of optimization problems over the PDE solutions. --- ### Completion $\neq$ Collaboration: Scaling Collaborative Effort with Agents Authors: Shannon Zejiang Shen, Valerie Chen, Ken Gu, Alexis Ross, Zixian Ma, Jillian Ross, Alex Gu, Chenglei Si, Wayne Chi, Andi Peng, Jocelyn J Shen, Ameet Talwalkar et al. Published: 2025-10-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.25744v2 Current evaluations of agents remain centered around one-shot task completion, failing to account for the inherently iterative and collaborative nature of many real-world problems, where human goals are often underspecified and evolve. We argue for a shift from building and assessing task completion agents to developing collaborative agents, assessed not only by the quality of their final outputs but by how well they engage with and enhance human effort throughout the problem-solving process. To support this shift, we introduce collaborative effort scaling, a framework that captures how an agent's utility grows with increasing user involvement. Through case studies and simulated evaluations, we show that state-of-the-art agents often underperform in multi-turn, real-world scenarios, revealing a missing ingredient in agent design: the ability to sustain engagement and scaffold user understanding. Collaborative effort scaling offers a lens for diagnosing agent behavior and guiding development toward more effective interactions. --- ### Scaling Latent Reasoning via Looped Language Models Authors: Rui-Jie Zhu, Zixuan Wang, Kai Hua, Tianyu Zhang, Ziniu Li, Haoran Que, Boyi Wei, Zixin Wen, Fan Yin, He Xing, Lu Li, Jiajun Shi et al. Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25741v6 Modern LLMs are trained to "think" primarily via explicit text generation, such as chain-of-thought (CoT), which defers reasoning to post-training and under-leverages pre-training data. We present and open-source Ouro, named after the recursive Ouroboros, a family of pre-trained Looped Language Models (LoopLM) that instead build reasoning into the pre-training phase through (i) iterative computation in latent space, (ii) an entropy-regularized objective for learned depth allocation, and (iii) scaling to 7.7T tokens. Ouro 1.4B and 2.6B models enjoy superior performance that match the results of up to 12B SOTA LLMs across a wide range of benchmarks. Through controlled experiments, we show this advantage stems not from increased knowledge capacity, but from superior knowledge manipulation capabilities. We also show that LoopLM yields reasoning traces more aligned with final outputs than explicit CoT. We hope our results show the potential of LoopLM as a novel scaling direction in the reasoning era. Our model is available here: http://ouro-llm.github.io. --- ### Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation Authors: Zhi-Kai Chen, Jun-Peng Jiang, Han-Jia Ye, De-Chuan Zhan Published: 2025-10-29 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.25739v1 Autoregressive (AR) image generation models are capable of producing high-fidelity images but often suffer from slow inference due to their inherently sequential, token-by-token decoding process. Speculative decoding, which employs a lightweight draft model to approximate the output of a larger AR model, has shown promise in accelerating text generation without compromising quality. However, its application to image generation remains largely underexplored. The challenges stem from a significantly larger sampling space, which complicates the alignment between the draft and target model outputs, coupled with the inadequate use of the two-dimensional spatial structure inherent in images, thereby limiting the modeling of local dependencies. To overcome these challenges, we introduce Hawk, a new approach that harnesses the spatial structure of images to guide the speculative model toward more accurate and efficient predictions. Experimental results on multiple text-to-image benchmarks demonstrate a 1.71x speedup over standard AR models, while preserving both image fidelity and diversity. --- ### What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMs Authors: Aakriti Shah, Yifan Hu, Thai Le Published: 2025-10-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.25732v2 Unlearning in large language models (LLMs) is usually evaluated as whether an "unlearned" fact can be recovered. We instead ask whether a fact's structural entanglement with the rest of a model's knowledge predicts whether it leaks after unlearning, whether this relationship changes systematically, and whether it is causal. Across varied unlearning algorithms (WHP and GA+KL), two domains (both fictional Harry Potter and non-fictional U.S. Senators, 2000-2010), and four models (2.7B-13B parameters), we find that before unlearning, more entangled facts are recalled more often (r = +0.39 to +0.51). WHP weakens this relationship but stays positive (r = +0.16 to +0.33); GA+KL inverts it in every domain and model size (r = -0.14 to -0.25). To our knowledge, this is the first report of this specific reversal in the unlearning literature. To confirm this is causal beyond correlation, we directly manipulate a prompt's entanglement score, holding its content, target model fixed, and show recall moves in the predicted direction and reverses sign under GA+KL in the same direction as the correlational analysis. This manipulation is our central evidence that unlearning acts on the underlying knowledge structure, not just its output. Building on this, we train a predictive model that estimates a prompt's post-unlearning factuality/hallucination profile before unlearning is run, creating a unique way of model auditing in triaging which prompts are likely to leak. --- ### LieSolver: PDE-Constrained Learning for IBVPs via Lie Symmetries Authors: René P. Klausen, Ivan Timofeev, Jonas Naujoks, Johannes Frank, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek Published: 2025-10-29 Categories: cs.LG, cs.AI, math.NA, physics.comp-ph arXiv: https://arxiv.org/abs/2510.25731v2 Initial-boundary value problems (IBVPs) provide the essential framework for modelling a wide range of phenomena in physics and engineering. We introduce a novel method for efficiently solving IBVPs using Lie symmetries to enforce the associated partial differential equation (PDE) exactly by construction. By leveraging symmetry transformations, our model embeds the underlying physical laws and learns the solution solely from initial and boundary data. Consequently, the boundary loss directly quantifies domain-wide error, enabling rigorous error estimation for well-posed IBVPs. We implement LieSolver and demonstrate its application to linear homogeneous PDEs, showing that it outperforms physics-informed neural networks (PINNs) in both speed and accuracy while yielding compact models. Overall, our approach significantly enhances the efficiency and reliability of predictions for PDE-constrained problems. --- ### Physics-Guided Conditional Diffusion Networks for Microwave Image Reconstruction Authors: Shirin Chehelgami, Joe LoVetri, Vahab Khoshdel Published: 2025-10-29 Categories: eess.IV, cs.AI, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2510.25729v1 A conditional latent-diffusion based framework for solving the electromagnetic inverse scattering problem associated with microwave imaging is introduced. This generative machine-learning model explicitly mirrors the non-uniqueness of the ill-posed inverse problem. Unlike existing inverse solvers utilizing deterministic machine learning techniques that produce a single reconstruction, the proposed latent-diffusion model generates multiple plausible permittivity maps conditioned on measured scattered-field data, thereby generating several potential instances in the range-space of the non-unique inverse mapping. A forward electromagnetic solver is integrated into the reconstruction pipeline as a physics-based evaluation mechanism. The space of candidate reconstructions form a distribution of possibilities consistent with the conditioning data and the member of this space yielding the lowest scattered-field data discrepancy between the predicted and measured scattered fields is reported as the final solution. Synthetic and experimental labeled datasets are used for training and evaluation of the model. An innovative labeled synthetic dataset is created that exemplifies a varied set of scattering features. Training of the model using this new dataset produces high quality permittivity reconstructions achieving improved generalization with excellent fidelity to shape recognition. The results highlight the potential of hybrid generative physics frameworks as a promising direction for robust, data-driven microwave imaging. --- ### The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution Authors: Junlong Li, Wenshuo Zhao, Jian Zhao, Weihao Zeng, Haoze Wu, Xiaochen Wang, Rui Ge, Yuxuan Cao, Yuzhen Huang, Wei Liu, Junteng Liu, Zhaochen Su et al. Published: 2025-10-29 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.25726v2 Real-world language agents must handle complex, multi-step workflows across diverse Apps. For instance, an agent may manage emails by coordinating with calendars and file systems, or monitor a production database to detect anomalies and generate reports following an operating manual. However, existing language agent benchmarks often focus on narrow domains or simplified tasks that lack the diversity, realism, and long-horizon complexity required to evaluate agents' real-world performance. To address this gap, we introduce the Tool Decathlon (dubbed as Toolathlon), a benchmark for language agents offering diverse Apps and tools, realistic environment setup, and reliable execution-based evaluation. Toolathlon spans 32 software applications and 604 tools, ranging from everyday platforms such as Google Calendar and Notion to professional ones like WooCommerce, Kubernetes, and BigQuery. Most of the tools are based on a high-quality set of Model Context Protocol (MCP) servers that we may have revised or implemented ourselves. Unlike prior works, which primarily ensure functional realism but offer limited environment state diversity, we provide realistic initial environment states from real software, such as Canvas courses with dozens of students or real financial spreadsheets. This benchmark includes 108 manually sourced or crafted tasks in total, requiring interacting with multiple Apps over around 20 turns on average to complete. Each task is strictly verifiable through dedicated evaluation scripts. Comprehensive evaluation of SOTA models highlights their significant shortcomings: the best-performing model, Claude-4.5-Sonnet, achieves only a 38.6% success rate with 20.2 tool calling turns on average, while the top open-weights model DeepSeek-V3.2-Exp reaches 20.1%. We expect Toolathlon to drive the development of more capable language agents for real-world, long-horizon task execution. --- ### BambooKG: A Neurobiologically-inspired Frequency-Weight Knowledge Graph Authors: Vanya Arikutharam, Arkadiy Ukolov Published: 2025-10-29 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.25724v1 Retrieval-Augmented Generation allows LLMs to access external knowledge, reducing hallucinations and ageing-data issues. However, it treats retrieved chunks independently and struggles with multi-hop or relational reasoning, especially across documents. Knowledge graphs enhance this by capturing the relationships between entities using triplets, enabling structured, multi-chunk reasoning. However, these tend to miss information that fails to conform to the triplet structure. We introduce BambooKG, a knowledge graph with frequency-based weights on non-triplet edges which reflect link strength, drawing on the Hebbian principle of "fire together, wire together". This decreases information loss and results in improved performance on single- and multi-hop reasoning, outperforming the existing solutions. --- ### Scaling flow-based approaches for topology sampling in $\mathrm{SU}(3)$ gauge theory Authors: Claudio Bonanno, Andrea Bulgarelli, Elia Cellini, Alessandro Nada, Dario Panfalone, Davide Vadacchino, Lorenzo Verzichelli Published: 2025-10-29 Categories: hep-lat, cond-mat.stat-mech, cs.LG, hep-ph arXiv: https://arxiv.org/abs/2510.25704v2 We develop a methodology based on out-of-equilibrium simulations to mitigate topological freezing when approaching the continuum limit of lattice gauge theories. We reduce the autocorrelation of the topological charge employing open boundary conditions, while removing exactly their unphysical effects using a non-equilibrium Monte Carlo approach in which periodic boundary conditions are gradually switched on. We perform a detailed analysis of the computational costs of this strategy in the case of the four-dimensional $\mathrm{SU}(3)$ Yang-Mills theory. After achieving full control of the scaling, we outline a clear strategy to sample topology efficiently in the continuum limit, which we check at lattice spacings as small as $0.045$ fm. We also generalize this approach by designing a customized Stochastic Normalizing Flow for evolutions in the boundary conditions, obtaining superior performances with respect to the purely stochastic non-equilibrium approach, and paving the way for more efficient future flow-based solutions. --- ### Interpreting LLMs as Credit Risk Classifiers: Do Their Feature Explanations Align with Classical ML? Authors: Saeed AlMarri, Kristof Juhasz, Mathieu Ravaut, Gautier Marti, Hamdan Al Ahbabi, Ibrahim Elfadel Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25701v1 Large Language Models (LLMs) are increasingly explored as flexible alternatives to classical machine learning models for classification tasks through zero-shot prompting. However, their suitability for structured tabular data remains underexplored, especially in high-stakes financial applications such as financial risk assessment. This study conducts a systematic comparison between zero-shot LLM-based classifiers and LightGBM, a state-of-the-art gradient-boosting model, on a real-world loan default prediction task. We evaluate their predictive performance, analyze feature attributions using SHAP, and assess the reliability of LLM-generated self-explanations. While LLMs are able to identify key financial risk indicators, their feature importance rankings diverge notably from LightGBM, and their self-explanations often fail to align with empirical SHAP attributions. These findings highlight the limitations of LLMs as standalone models for structured financial risk prediction and raise concerns about the trustworthiness of their self-generated explanations. Our results underscore the need for explainability audits, baseline comparisons with interpretable models, and human-in-the-loop oversight when deploying LLMs in risk-sensitive financial environments. --- ### Convolutional Spiking-based GRU Cell for Spatio-temporal Data Authors: Yesmine Abdennadher, Eleonora Cicciarella, Michele Rossi Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25696v1 Spike-based temporal messaging enables SNNs to efficiently process both purely temporal and spatio-temporal time-series or event-driven data. Combining SNNs with Gated Recurrent Units (GRUs), a variant of recurrent neural networks, gives rise to a robust framework for sequential data processing; however, traditional RNNs often lose local details when handling long sequences. Previous approaches, such as SpikGRU, fail to capture fine-grained local dependencies in event-based spatio-temporal data. In this paper, we introduce the Convolutional Spiking GRU (CS-GRU) cell, which leverages convolutional operations to preserve local structure and dependencies while integrating the temporal precision of spiking neurons with the efficient gating mechanisms of GRUs. This versatile architecture excels on both temporal datasets (NTIDIGITS, SHD) and spatio-temporal benchmarks (MNIST, DVSGesture, CIFAR10DVS). Our experiments show that CS-GRU outperforms state-of-the-art GRU variants by an average of 4.35%, achieving over 90% accuracy on sequential tasks and up to 99.31% on MNIST. It is worth noting that our solution achieves 69% higher efficiency compared to SpikGRU. The code is available at: https://github.com/YesmineAbdennadher/CS-GRU. --- ### Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents Authors: Jiayi Kuang, Yinghui Li, Xin Zhang, Yangning Li, Di Yin, Xing Sun, Ying Shen, Philip S. Yu Published: 2025-10-29 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.25694v1 Large language model-based agents show promise for software engineering, but environment configuration remains a bottleneck due to heavy manual effort and scarce large-scale, high-quality datasets. Existing benchmarks assess only end-to-end build/test success, obscuring where and why agents succeed or fail. We introduce the Environment Configuration Diagnosis Benchmark, Enconda-bench, which provides process-level trajectory assessment of fine-grained agent capabilities during environment setup-planning, perception-driven error diagnosis, feedback-driven repair, and action to execute final environment configuration. Our task instances are automatically constructed by injecting realistic README errors and are validated in Docker for scalable, high-quality evaluation. Enconda-bench combines process-level analysis with end-to-end executability to enable capability assessments beyond aggregate success rates. Evaluations across state-of-the-art LLMs and agent frameworks show that while agents can localize errors, they struggle to translate feedback into effective corrections, limiting end-to-end performance. To our knowledge, Enconda-bench is the first framework to provide process-level internal capability assessment for environment configuration, offering actionable insights for improving software engineering agents. --- ### PyDPF: A Python Package for Differentiable Particle Filtering Authors: John-Joseph Brady, Benjamin Cox, Yunpeng Li, Víctor Elvira Published: 2025-10-29 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2510.25693v4 State-space models (SSMs) are a widely used tool in time series analysis. In the complex systems that arise from real-world data, it is common to employ particle filtering (PF), an efficient Monte Carlo method for estimating the hidden state corresponding to a sequence of observations. Applying particle filtering requires specifying both the parametric form and the parameters of the system, which are often unknown and must be estimated. Gradient-based optimisation techniques cannot be applied directly to standard particle filters, as the filters themselves are not differentiable. However, several recently proposed methods modify the resampling step to make particle filtering differentiable. In this paper, we present an implementation of several such differentiable particle filters (DPFs) with a unified API built on the popular PyTorch framework. Our implementation makes these algorithms easily accessible to a broader research community and facilitates straightforward comparison between them. We validate our framework by reproducing experiments from several existing studies and demonstrate how DPFs can be applied to address several common challenges with state space modelling. --- ### A Configuration-First Framework for Reproducible, Low-Code Machine Learning: a Localization Use Case Authors: Tim Strnad, Blaž Bertalanič, Carolina Fortuna Published: 2025-10-29 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2510.25692v5 As machine learning underpins more critical applications, the value of a reported result depends on whether it can be compared and repeated. In practice, this remains difficult: research groups often assemble their own tools for configuration, execution, versioning, and evaluation, while also repeating the domain-specific work such as dataset preparation and baseline implementation. We present a configuration-first design for application-specific ML experimentation frameworks that addresses these sources of repeated effort. An experiment is declared in human-readable configuration files; a workflow orchestrator executes each stage as an isolated process that communicates only through explicit inputs and outputs; and code, data, configurations, environment specifications, and generated artifacts are versioned together, so that a recorded run can be inspected and repeated. We instantiate the design as LOCALIZE for radio-localization research, which supplies preconfigured datasets, processing stages, model-development procedures, and experiment templates while leaving the underlying pipeline open to modification. A qualitative comparison against five experimentation platforms, together with controlled quantitative studies against matched Jupyter notebook and Kedro implementations, shows that for the localization workflows studied, changes covered by LOCALIZE's supplied components require fewer codebase edits, while total wall-clock time and peak memory usage remain comparable. In a controlled scaling experiment at 1x, 5x, and 10x the base dataset volume, total CPU and wall time grew sublinearly over the tested sizes. --- ### Model Inversion meets Cryptographic Fuzzy Extractors Authors: Mallika Prabhakar, Louise Xu, Prateek Saxena Published: 2025-10-29 Categories: cs.CR, cs.LG arXiv: https://arxiv.org/abs/2510.25687v4 Model inversion attacks pose an open challenge to privacy-sensitive applications that use machine learning (ML) models. For example, face authentication systems use modern ML models to compute embedding vectors from face images of the enrolled users and store them. If leaked, inversion attacks can accurately reconstruct user faces from the leaked vectors. A fuzzy extractor (FE) is a cryptographic primitive with properties that can help defend against model inversion, offering attack-agnostic security without requiring any re-training of the ML model it protects. To date, no systematic cryptanalysis of existing FE schemes that tolerate $\ell_2$ noise, as needed in modern ML-based face recognition systems, has been conducted. We perform the first in-depth security analysis of existing $\ell_2$-FE schemes showing that they offer weak security. We also show end-to-end inversion attacks that achieve high success rates in recovering original faces that are meant to be protected by FE schemes. We then offer a simple but new candidate scheme and prove its security formally. Our construction offers the first design point that offers practical runtime, stronger security, and usable accuracy for use in commodity ML-based face authentication. --- ### Graph Network-based Structural Simulator: Graph Neural Networks for Structural Dynamics Authors: Alessandro Lucchetti, Francesco Cadini, Marco Giglio, Luca Lomazzi Published: 2025-10-29 Categories: cs.LG, cs.AI, cs.CE, physics.comp-ph arXiv: https://arxiv.org/abs/2510.25683v1 Graph Neural Networks (GNNs) have recently been explored as surrogate models for numerical simulations. While their applications in computational fluid dynamics have been investigated, little attention has been given to structural problems, especially for dynamic cases. To address this gap, we introduce the Graph Network-based Structural Simulator (GNSS), a GNN framework for surrogate modeling of dynamic structural problems. GNSS follows the encode-process-decode paradigm typical of GNN-based machine learning models, and its design makes it particularly suited for dynamic simulations thanks to three key features: (i) expressing node kinematics in node-fixed local frames, which avoids catastrophic cancellation in finite-difference velocities; (ii) employing a sign-aware regression loss, which reduces phase errors in long rollouts; and (iii) using a wavelength-informed connectivity radius, which optimizes graph construction. We evaluate GNSS on a case study involving a beam excited by a 50kHz Hanning-modulated pulse. The results show that GNSS accurately reproduces the physics of the problem over hundreds of timesteps and generalizes to unseen loading conditions, where existing GNNs fail to converge or deliver meaningful predictions. Compared with explicit finite element baselines, GNSS achieves substantial inference speedups while preserving spatial and temporal fidelity. These findings demonstrate that locality-preserving GNNs with physics-consistent update rules are a competitive alternative for dynamic, wave-dominated structural simulations. --- ### PairUni: Pairwise Training for Unified Multimodal Language Models Authors: Jiani Zheng, Zhiyang Teng, Kunpeng Qiu, Xiangtai Li, Anran Wang, Yu Tian, Ye Tian, Haochen Wang, Zhuochen Wang Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25682v3 Unified Vision-Language Models (UVLMs) perform both understanding and generation within a single architecture. Since these models rely on heterogeneous data and supervision, balancing both generation and understanding in reinforcement learning (RL) is challenging. To address this challenge, we propose PairUni, a unified framework that reorganizes data into understanding-generation (UG) pairs and aligns optimization accordingly. Specifically, we construct a unified paired dataset by synthesizing aligned instances via cross-modal semantic completion and retrieving semantically related samples. These paired structures expose cross-task semantic correspondences and support consistent policy learning. To leverage this structure, we present PairGRPO, a pair-aware variant based on Group Relative Policy Optimization. It assigns a similarity score to each pair to modulate the advantage, strengthening learning from well-aligned examples and reducing task interference. Extensive experiments across diverse UVLM architectures (Autoregressive and Discrete Diffusion) and scales (1B to 14B) demonstrate that PairUni yields consistent improvements over strong baselines. Notably, our method also demonstrates strong generalization by improving performance on image editing tasks without using any editing-specific data. Codes are available at https://github.com/Haochen-Wang409/PairUni. --- ### Navigation in a Three-Dimensional Urban Flow using Deep Reinforcement Learning Authors: Federica Tonti, Ricardo Vinuesa Published: 2025-10-29 Categories: cs.AI, physics.flu-dyn arXiv: https://arxiv.org/abs/2510.25679v1 Unmanned Aerial Vehicles (UAVs) are increasingly populating urban areas for delivery and surveillance purposes. In this work, we develop an optimal navigation strategy based on Deep Reinforcement Learning. The environment is represented by a three-dimensional high-fidelity simulation of an urban flow, characterized by turbulence and recirculation zones. The algorithm presented here is a flow-aware Proximal Policy Optimization (PPO) combined with a Gated Transformer eXtra Large (GTrXL) architecture, giving the agent richer information about the turbulent flow field in which it navigates. The results are compared with a PPO+GTrXL without the secondary prediction tasks, a PPO combined with Long Short Term Memory (LSTM) cells and a traditional navigation algorithm. The obtained results show a significant increase in the success rate (SR) and a lower crash rate (CR) compared to a PPO+LSTM, PPO+GTrXL and the classical Zermelo's navigation algorithm, paving the way to a completely reimagined UAV landscape in complex urban environments. --- ### ZK-SenseLM: Verifiable Large-Model Wireless Sensing with Selective Abstention and Zero-Knowledge Attestation Authors: Hasan Akgul, Mari Eplik, Javier Rojas, Aina Binti Abdullah, Pieter van der Merwe Published: 2025-10-29 Categories: cs.CR, cs.CL arXiv: https://arxiv.org/abs/2510.25677v3 ZK-SenseLM is a secure and auditable wireless sensing framework that pairs a large-model encoder for Wi-Fi channel state information (and optionally mmWave radar or RFID) with a policy-grounded decision layer and end-to-end zero-knowledge proofs of inference. The encoder uses masked spectral pretraining with phase-consistency regularization, plus a light cross-modal alignment that ties RF features to compact, human-interpretable policy tokens. To reduce unsafe actions under distribution shift, we add a calibrated selective-abstention head; the chosen risk-coverage operating point is registered and bound into the proof. We implement a four-stage proving pipeline: (C1) feature sanity and commitment, (C2) threshold and version binding, (C3) time-window binding, and (C4) PLONK-style proofs that the quantized network, given the committed window, produced the logged action and confidence. Micro-batched proving amortizes cost across adjacent windows, and a gateway option offloads proofs from low-power devices. The system integrates with differentially private federated learning and on-device personalization without weakening verifiability: model hashes and the registered threshold are part of each public statement. Across activity, presence or intrusion, respiratory proxy, and RF fingerprinting tasks, ZK-SenseLM improves macro-F1 and calibration, yields favorable coverage-risk curves under perturbations, and rejects tamper and replay with compact proofs and fast verification. --- ### Mechanistic Interpretability of RNNs emulating Hidden Markov Models Authors: Elia Torre, Michele Viscione, Lucas Pompe, Benjamin F Grewe, Valerio Mante Published: 2025-10-29 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.25674v1 Recurrent neural networks (RNNs) provide a powerful approach in neuroscience to infer latent dynamics in neural populations and to generate hypotheses about the neural computations underlying behavior. However, past work has focused on relatively simple, input-driven, and largely deterministic behaviors - little is known about the mechanisms that would allow RNNs to generate the richer, spontaneous, and potentially stochastic behaviors observed in natural settings. Modeling with Hidden Markov Models (HMMs) has revealed a segmentation of natural behaviors into discrete latent states with stochastic transitions between them, a type of dynamics that may appear at odds with the continuous state spaces implemented by RNNs. Here we first show that RNNs can replicate HMM emission statistics and then reverse-engineer the trained networks to uncover the mechanisms they implement. In the absence of inputs, the activity of trained RNNs collapses towards a single fixed point. When driven by stochastic input, trajectories instead exhibit noise-sustained dynamics along closed orbits. Rotation along these orbits modulates the emission probabilities and is governed by transitions between regions of slow, noise-driven dynamics connected by fast, deterministic transitions. The trained RNNs develop highly structured connectivity, with a small set of "kick neurons" initiating transitions between these regions. This mechanism emerges during training as the network shifts into a regime of stochastic resonance, enabling it to perform probabilistic computations. Analyses across multiple HMM architectures - fully connected, cyclic, and linear-chain - reveal that this solution generalizes through the modular reuse of the same dynamical motif, suggesting a compositional principle by which RNNs can emulate complex discrete latent dynamics. --- ### Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy Authors: Phuc Tran, Nisheeth K. Vishnoi, Van H. Vu Published: 2025-10-29 Categories: cs.LG, cs.CR, cs.DS, math.NA, math.SP arXiv: https://arxiv.org/abs/2510.25670v1 A central challenge in machine learning is to understand how noise or measurement errors affect low-rank approximations, particularly in the spectral norm. This question is especially important in differentially private low-rank approximation, where one aims to preserve the top-$p$ structure of a data-derived matrix while ensuring privacy. Prior work often analyzes Frobenius norm error or changes in reconstruction quality, but these metrics can over- or under-estimate true subspace distortion. The spectral norm, by contrast, captures worst-case directional error and provides the strongest utility guarantees. We establish new high-probability spectral-norm perturbation bounds for symmetric matrices that refine the classical Eckart--Young--Mirsky theorem and explicitly capture interactions between a matrix $A \in \mathbb{R}^{n \times n}$ and an arbitrary symmetric perturbation $E$. Under mild eigengap and norm conditions, our bounds yield sharp estimates for $\|(A + E)_p - A_p\|$, where $A_p$ is the best rank-$p$ approximation of $A$, with improvements of up to a factor of $\sqrt{n}$. As an application, we derive improved utility guarantees for differentially private PCA, resolving an open problem in the literature. Our analysis relies on a novel contour bootstrapping method from complex analysis and extends it to a broad class of spectral functionals, including polynomials and matrix exponentials. Empirical results on real-world datasets confirm that our bounds closely track the actual spectral error under diverse perturbation regimes. --- ### ALDEN: Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents Authors: Tianyu Yang, Terry Ruas, Yijun Tian, Jan Philip Wahle, Daniel Kurzawe, Bela Gipp Published: 2025-10-29 Categories: cs.AI, cs.MM arXiv: https://arxiv.org/abs/2510.25668v1 Vision-language models (VLMs) excel at interpreting text-rich images but struggle with long, visually complex documents that demand analysis and integration of information spread across multiple pages. Existing approaches typically rely on fixed reasoning templates or rigid pipelines, which force VLMs into a passive role and hinder both efficiency and generalization. We present Active Long-DocumEnt Navigation (ALDEN), a multi-turn reinforcement learning framework that fine-tunes VLMs as interactive agents capable of actively navigating long, visually rich documents. ALDEN introduces a novel fetch action that directly accesses the page by index, complementing the classic search action and better exploiting document structure. For dense process supervision and efficient training, we propose a rule-based cross-level reward that provides both turn- and token-level signals. To address the empirically observed training instability caused by numerous visual tokens from long documents, we further propose a visual-semantic anchoring mechanism that applies a dual-path KL-divergence constraint to stabilize visual and textual representations separately during training. Trained on a corpus constructed from three open-source datasets, ALDEN achieves state-of-the-art performance on five long-document benchmarks. Overall, ALDEN marks a step beyond passive document reading toward agents that autonomously navigate and reason across long, visually rich documents, offering a robust path to more accurate and efficient long-document understanding. --- ### User Misconceptions of LLM-Based Conversational Programming Assistants Authors: Gabrielle O'Brien, Antonio Pedro Santos Alves, Sebastian Baltes, Grischa Liebel, Marcos Kalinowski Published: 2025-10-29 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2510.25662v3 Programming assistants powered by large language models (LLMs) have become widely available, with conversational assistants such as ChatGPT particularly accessible to novice programmers. However, varied tool capabilities and inconsistent availability of extensions (e.g., web search, code execution, retrieval-augmented generation) create opportunities for user misconceptions that may lead to over-reliance, unproductive practices, or insufficient quality control. We characterize the misconceptions that users of conversational LLM-based assistants may hold in programming contexts. We screened 11,429 Python-related conversations from the openly available WildChat dataset with a validated LLM annotation pipeline, then hand-annotated the 754 candidate conversations it flagged. Of these, 450 contain a prompt consistent with at least one of eight potential misconceptions: misplaced expectations about capabilities such as web access, code execution, non-text outputs, and session memory. We also characterize how the assistant responds when a prompt presupposes a capability it lacks: responses range from explicit refusal through qualified answers to fabricated compliance, and explicit refusals appear in only a minority of labeled conversations. Among the most frequent misconceptions, explicit refusals are rarest where compliance is easiest to fabricate. Our findings reinforce the need for LLM-based tools to communicate their capabilities to users through channels other than the conversation itself. --- ### Subgraph Federated Learning via Spectral Methods Authors: Javad Aliakbari, Johan Östman, Ashkan Panahi, Alexandre Graell i Amat Published: 2025-10-29 Categories: cs.LG, cs.AI, cs.IT arXiv: https://arxiv.org/abs/2510.25657v1 We consider the problem of federated learning (FL) with graph-structured data distributed across multiple clients. In particular, we address the prevalent scenario of interconnected subgraphs, where interconnections between clients significantly influence the learning process. Existing approaches suffer from critical limitations, either requiring the exchange of sensitive node embeddings, thereby posing privacy risks, or relying on computationally-intensive steps, which hinders scalability. To tackle these challenges, we propose FedLap, a novel framework that leverages global structure information via Laplacian smoothing in the spectral domain to effectively capture inter-node dependencies while ensuring privacy and scalability. We provide a formal analysis of the privacy of FedLap, demonstrating that it preserves privacy. Notably, FedLap is the first subgraph FL scheme with strong privacy guarantees. Extensive experiments on benchmark datasets demonstrate that FedLap achieves competitive or superior utility compared to existing techniques. --- ### Continuous subsurface property retrieval from sparse radar observations using physics informed neural networks Authors: Ishfaq Aziz, Mohamad Alipour Published: 2025-10-29 Categories: eess.SP, cs.LG arXiv: https://arxiv.org/abs/2510.25648v1 Estimating subsurface dielectric properties is essential for applications ranging from environmental surveys of soils to nondestructive evaluation of concrete in infrastructure. Conventional wave inversion methods typically assume few discrete homogeneous layers and require dense measurements or strong prior knowledge of material boundaries, limiting scalability and accuracy in realistic settings where properties vary continuously. We present a physics informed machine learning framework that reconstructs subsurface permittivity as a fully neural, continuous function of depth, trained to satisfy both measurement data and Maxwells equations. We validate the framework with both simulations and custom built radar experiments on multilayered natural materials. Results show close agreement with in-situ permittivity measurements (R^2=0.93), with sensitivity to even subtle variations (Delta eps_r=2). Parametric analysis reveals that accurate profiles can be recovered with as few as three strategically placed sensors in two layer systems. This approach reframes subsurface inversion from boundary-driven to continuous property estimation, enabling accurate characterization of smooth permittivity variations and advancing electromagnetic imaging using low cost radar systems. --- ### Learning to Plan & Schedule with Reinforcement-Learned Bimanual Robot Skills Authors: Weikang Wan, Fabio Ramos, Xuning Yang, Caelan Garrett Published: 2025-10-29 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2510.25634v2 Long-horizon contact-rich bimanual manipulation presents a significant challenge, requiring complex coordination involving a mixture of parallel execution and sequential collaboration between arms. In this paper, we introduce a hierarchical framework that frames this challenge as an integrated skill planning & scheduling problem, going beyond purely sequential decision-making to support simultaneous skill invocation. Our approach is built upon a library of single-arm and bimanual primitive skills, each trained using Reinforcement Learning (RL) in GPU-accelerated simulation. We then train a Transformer-based planner on a dataset of skill compositions to act as a high-level scheduler, simultaneously predicting the discrete schedule of skills as well as their continuous parameters. We demonstrate that our method achieves higher success rates on complex, contact-rich tasks than end-to-end RL approaches and produces more efficient, coordinated behaviors than traditional sequential-only planners. --- ### EHR-R1: A Reasoning-Enhanced Foundational Language Model for Electronic Health Record Analysis Authors: Yusheng Liao, Chaoyi Wu, Junwei Liu, Shuyang Jiang, Pengcheng Qiu, Haowen Wang, Yun Yue, Shuai Zhen, Jian Wang, Qianrui Fan, Jinjie Gu, Ya Zhang et al. Published: 2025-10-29 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.25628v2 Electronic Health Records (EHRs) contain rich yet complex information, and their automated analysis is critical for clinical decision-making. Despite recent advances of large language models (LLMs) in clinical workflows, their ability to analyze EHRs remains limited due to narrow task coverage and lack of EHR-oriented reasoning capabilities. This paper aims to bridge the gap, specifically, we present EHR-Ins, a large-scale, comprehensive EHR reasoning instruction dataset, comprising 300k high-quality reasoning cases and 4M non-reasoning cases across 42 distinct EHR tasks. Its core innovation is a thinking-graph-driven framework that enables to generate high-quality reasoning data at scale. Based on it, we develop EHR-R1, a series of reasoning-enhanced LLMs with up to 72B parameters tailored for EHR analysis. Through a multi-stage training paradigm, including domain adaptation, reasoning enhancement, and reinforcement learning, EHR-R1 systematically acquires domain knowledge and diverse reasoning capabilities, enabling accurate and robust EHR analysis. Lastly, we introduce EHR-Bench, a new benchmark curated from MIMIC-IV, spanning 42 tasks, to comprehensively assess reasoning and prediction across EHR scenarios. In experiments, we show that the resulting EHR-R1 consistently outperforms state-of-the-art commercial and open-source LLMs (including DeepSeek-V3 and GPT-4o), surpassing GPT-4o by over 30 points on MIMIC-Bench and achieving a 10\% higher zero-shot AUROC on EHRSHOT. Collectively, EHR-Ins, EHR-R1, and EHR-Bench have significantly advanced the development for more reliable and clinically relevant EHR analysis. --- ### Are Language Models Efficient Reasoners? A Perspective from Logic Programming Authors: Andreas Opedal, Yanick Zengaffinen, Haruki Shirakami, Clemente Pasti, Mrinmaya Sachan, Abulhair Saparov, Ryan Cotterell, Bernhard Schölkopf Published: 2025-10-29 Categories: cs.CL, cs.AI, cs.LG, cs.LO arXiv: https://arxiv.org/abs/2510.25626v2 Modern language models (LMs) exhibit strong deductive reasoning capabilities, yet standard evaluations emphasize correctness while overlooking a key aspect of reasoning: efficiency. In real-world reasoning scenarios, much of the available information is irrelevant, and effective deductive inference requires identifying and ignoring such distractions. We propose a framework for assessing LM reasoning efficiency through the lens of logic programming, introducing a simple method to align proofs written in natural language -- as generated by an LM -- with shortest proofs found by executing the logic program. Efficiency is quantified by measuring how well a model avoids unnecessary inference. Empirically, we construct a dataset of math word problems injected with various number of irrelevant axioms that vary in semantic overlap with the goal theorem. We find that current LMs show marked accuracy declines under such conditions -- even with minimal, domain-consistent distractions -- and the proofs they generate frequently exhibit detours through irrelevant inferences. ---