# Research Papers — 2025-10 · bundle page 53 of 217 > Full-text markdown of papers #2601–2650 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/53 [← Previous bundle](https://aipod.dev/papers/archive/2025-10/page/52.md) [Next bundle →](https://aipod.dev/papers/archive/2025-10/page/54.md) ### Exploration through Generation: Applying GFlowNets to Structured Search Authors: Mark Phillip Matovic Published: 2025-10-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.21886v1 This work applies Generative Flow Networks (GFlowNets) to three graph optimization problems: the Traveling Salesperson Problem, Minimum Spanning Tree, and Shortest Path. GFlowNets are generative models that learn to sample solutions proportionally to a reward function. The models are trained using the Trajectory Balance loss to build solutions sequentially, selecting edges for spanning trees, nodes for paths, and cities for tours. Experiments on benchmark instances of varying sizes show that GFlowNets learn to find optimal solutions. For each problem type, multiple graph configurations with different numbers of nodes were tested. The generated solutions match those from classical algorithms (Dijkstra for shortest path, Kruskal for spanning trees, and exact solvers for TSP). Training convergence depends on problem complexity, with the number of episodes required for loss stabilization increasing as graph size grows. Once training converges, the generated solutions match known optima from classical algorithms across the tested instances. This work demonstrates that generative models can solve combinatorial optimization problems through learned policies. The main advantage of this learning-based approach is computational scalability: while classical algorithms have fixed complexity per instance, GFlowNets amortize computation through training. With sufficient computational resources, the framework could potentially scale to larger problem instances where classical exact methods become infeasible. --- ### Preventing Catastrophic Forgetting: Behavior-Aware Sampling for Safer Language Model Fine-Tuning Authors: Anh Pham, Mihir Thalanki, Michael Sun, Aditya Chaloo, Ankita Gupta, Tian Xia, Aditya Mate, Ehimwenma Nosakhare, Soundararajan Srinivasan Published: 2025-10-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.21885v1 Large language models often lose previously aligned safety behaviors when fine-tuned on benign data, a phenomenon known as catastrophic forgetting. Prior work shows that adding random safety examples can mitigate this effect, but it remains unclear which examples are most effective. We propose a behavior-aware sampling framework that selects safety examples based on two complementary factors: instruction-response behavior (e.g., refusal versus compliance) and semantic diversity across harm categories. Systematic evaluation shows that this approach substantially reduces harmful outputs while maintaining helpfulness, achieving up to a 41% reduction in harmfulness with only 0.5% additional training data. These results highlight how targeted data selection can improve the safety and efficiency of fine-tuning at scale. --- ### Support-Contra Asymmetry in LLM Explanations Authors: Avinash Patil Published: 2025-10-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.21884v2 Large Language Models (LLMs) increasingly produce natural language explanations alongside their predictions, yet it remains unclear whether these explanations reference predictive cues present in the input text. In this work, we present an empirical study of how LLM-generated explanations align with predictive lexical evidence from an external model in text classification tasks. To analyze this relationship, we compare explanation content against interpretable feature importance signals extracted from transparent linear classifiers. These reference models allow us to partition predictive lexical cues into supporting and contradicting evidence relative to the predicted label. Across three benchmark datasets-WIKIONTOLOGY, AG NEWS, and IMDB-we observe a consistent empirical pattern that we term support-contra asymmetry. Explanations accompanying correct predictions tend to reference more supporting lexical cues and fewer contradicting cues, whereas explanations associated with incorrect predictions reference substantially more contradicting evidence. This pattern appears consistently across datasets, across reference model families (logistic regression and linear SVM), and across multiple feature retrieval depths. These results suggest that LLM explanations often reflect lexical signals that are predictive for the task when predictions are correct, while incorrect predictions are more frequently associated with explanations that reference misleading cues present in the input. Our findings provide a simple empirical perspective on explanation-evidence alignment and illustrate how external sources of predictive evidence can be used to analyze the behavior of LLM-generated explanations. --- ### Framework for Machine Evaluation of Reasoning Completeness in Large Language Models For Classification Tasks Authors: Avinash Patil Published: 2025-10-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.21884v1 The growing adoption of machine learning (ML) in sensitive domains has heightened the demand for transparent and interpretable artificial intelligence. Large Language Models (LLMs) are increasingly capable of producing natural language explanations, yet it remains unclear whether these rationales faithfully capture the predictive signals that underlie decisions. This paper introduces RACE-Reasoning Alignment for Completeness of Explanations, a systematic framework to evaluate the alignment between LLM-generated explanations and interpretable feature importance scores derived from a logistic regression baseline. We analyze four widely used text classification datasets-WIKI ONTOLOGY, AG NEWS, IMDB, and GOEMOTIONS-and compare LLM rationales against top-ranked supporting and contradicting lexical features. To capture alignment at multiple levels of granularity, RACE implements token-aware, exact string, and edit-distance matching techniques. Empirical results reveal a consistent asymmetry: correct predictions exhibit higher coverage of supporting features, while incorrect predictions are associated with elevated coverage of contradicting features. Edit-distance matching further uncovers paraphrastic overlaps, boosting coverage while preserving this asymmetry. These findings demonstrate that LLM rationales combine both surface-level and flexible evidence reuse, yet can also amplify misleading cues in error cases. RACE provides new insights into the faithfulness of LLM explanations and establishes a quantitative basis for evaluating reasoning completeness in neural language models. --- ### Language Ranker: A Lightweight Ranking framework for LLM Decoding Authors: Chenheng Zhang, Tianqi Du, Jizhe Zhang, Mingqing Xiao, Yifei Wang, Yisen Wang, Zhouchen Lin Published: 2025-10-23 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2510.21883v1 Conventional research on large language models (LLMs) has primarily focused on refining output distributions, while paying less attention to the decoding process that transforms these distributions into final responses. Recent advances, such as scaling the computation of inference time with reward models, have underscored the importance of decoding, but these methods often suffer from high computational costs and limited applicability. In this paper, we revisit LLM generation through the lens of recommender systems, conceptualizing the decoding process as analogous to the ranking stage in recommendation pipelines. From this perspective, we observe that both traditional decoding methods and reward models exhibit clear limitations such as redundancy. Motivated by this insight, we propose Language Ranker, a novel framework that introduces a lightweight module to rerank candidate responses using features extracted by the base model. Experiments across a wide range of tasks show that Language Ranker achieves performance comparable to large-scale reward models, while requiring only <0.5M additional parameters, significantly reducing the computational overhead during both training and inference stages. This highlights the efficiency and effectiveness of our method, showcasing its potential to fully unlock the capabilities of LLMs. --- ### GeoThought: A Dataset for Enhancing Mathematical Geometry Reasoning in Vision-Language Models Authors: Nannan Shi, Chuanyu Qin, Shipeng Song, Man Luo Published: 2025-10-23 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.21881v1 Large language models (LLMs) have demonstrated strong reasoning capabilities in text-based mathematical problem solving; however, when adapted to visual reasoning tasks, particularly geometric problem solving, their performance substantially declines because geometric problems present unique challenges. Specifically, these challenges stem from two key factors: first, the intrinsic complexity of geometry requiring detailed image comprehension and multi-step reasoning, and second, the limitations of existing datasets which lack sufficient scale, diversity, and explicit reasoning traces, consequently hindering effective model training. To address these challenges, we developed the GeoThoughts dataset, a comprehensive geometric reasoning corpus with two subsets: Geo-Thought-6K with 6,243 samples and its augmented version Geo-Thought-Augmented-10K containing 10,834 samples. Each entry includes visual descriptions, step-by-step solutions, explicit reasoning chains, reflection steps, and final answers. Using this dataset, we developed GeoThought-MLLM, a mathematical reasoning multimodal model that generates detailed thinking processes during problem-solving. Our model outperforms existing benchmarks in geometric tasks, demonstrating that training with our Chain-of-Thought dataset improves geometric reasoning capabilities across both in-domain and out-of-domain settings. Finally, we analyze failure cases and observe that errors primarily arise from incorrect interpretation of mathematical concepts or spatial misjudgment. By invoking CoT to correct these mistakes, the model produces correct answers. --- ### TernaryCLIP: Efficiently Compressing Vision-Language Models with Ternary Weights and Distilled Knowledge Authors: Shu-Hao Zhang, Wei-Cheng Tang, Chen Wu, Peng Hu, Nan Li, Liang-Jie Zhang, Qi Zhang, Shao-Qun Zhang Published: 2025-10-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.21879v1 Recent years have witnessed an increasing interest in image-text contrastive modeling, exemplified by models such as Contrastive Language-Image Pretraining (CLIP). In this paper, we propose the TernaryCLIP, a lightweight computational framework that converts connection weights of both vision and text encoders of CLIP into the ternary format, instead of full-precision or floating ones. TernaryCLIP incorporates quantization-aware training and distillation modules, preventing precision degradation and enabling low-cost and high-efficiency computations. Comprehensive experiments demonstrate that TernaryCLIP can achieve up to 99\% ternarized weights with 1.58-bit representation, 16.98 $\times$ compression ratio, 2.3 $\times$ inference acceleration, 16 $\times$ storage reduction, 10 $\times$ memory optimization, and 60\% sparsity while maintaining promising performance on zero-shot image classification and image-text retrieval tasks across 41 commonly used datasets. Our work highlights the feasibility of extreme quantization for large multimodal models, supporting effective and efficient deployment on resource-constrained devices. The model and code can be accessed from Hugging Face and GitHub. --- ### AI Powered Urban Green Infrastructure Assessment Through Aerial Imagery of an Industrial Township Authors: Anisha Dutta Published: 2025-10-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.21876v1 Accurate assessment of urban canopy coverage is crucial for informed urban planning, effective environmental monitoring, and mitigating the impacts of climate change. Traditional practices often face limitations due to inadequate technical requirements, difficulties in scaling and data processing, and the lack of specialized expertise. This study presents an efficient approach for estimating green canopy coverage using artificial intelligence, specifically computer vision techniques, applied to aerial imageries. Our proposed methodology utilizes object-based image analysis, based on deep learning algorithms to accurately identify and segment green canopies from high-resolution drone images. This approach allows the user for detailed analysis of urban vegetation, capturing variations in canopy density and understanding spatial distribution. To overcome the computational challenges associated with processing large datasets, it was implemented over a cloud platform utilizing high-performance processors. This infrastructure efficiently manages space complexity and ensures affordable latency, enabling the rapid analysis of vast amounts of drone imageries. Our results demonstrate the effectiveness of this approach in accurately estimating canopy coverage at the city scale, providing valuable insights for urban forestry management of an industrial township. The resultant data generated by this method can be used to optimize tree plantation and assess the carbon sequestration potential of urban forests. By integrating these insights into sustainable urban planning, we can foster more resilient urban environments, contributing to a greener and healthier future. --- ### A Physics-Informed Neural Network Approach for UAV Path Planning in Dynamic Environments Authors: Shuning Zhang Published: 2025-10-23 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2510.21874v2 Unmanned aerial vehicles (UAVs) operating in dynamic wind fields must generate safe and energy-efficient trajectories under physical and environmental constraints. Traditional planners, such as A* and kinodynamic RRT*, often yield suboptimal or non-smooth paths due to discretization and sampling limitations. This paper presents a physics-informed neural network (PINN) framework that embeds UAV dynamics, wind disturbances, and obstacle avoidance directly into the learning process. Without requiring supervised data, the PINN learns dynamically feasible and collision-free trajectories by minimizing physical residuals and risk-aware objectives. Comparative simulations show that the proposed method outperforms A* and Kino-RRT* in control energy, smoothness, and safety margin, while maintaining similar flight efficiency. The results highlight the potential of physics-informed learning to unify model-based and data-driven planning, providing a scalable and physically consistent framework for UAV trajectory optimization. --- ### GuitarFlow: Realistic Electric Guitar Synthesis From Tablatures via Flow Matching and Style Transfer Authors: Jackson Loth, Pedro Sarmento, Mark Sandler, Mathieu Barthet Published: 2025-10-23 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2510.21872v1 Music generation in the audio domain using artificial intelligence (AI) has witnessed steady progress in recent years. However for some instruments, particularly the guitar, controllable instrument synthesis remains limited in expressivity. We introduce GuitarFlow, a model designed specifically for electric guitar synthesis. The generative process is guided using tablatures, an ubiquitous and intuitive guitar-specific symbolic format. The tablature format easily represents guitar-specific playing techniques (e.g. bends, muted strings and legatos), which are more difficult to represent in other common music notation formats such as MIDI. Our model relies on an intermediary step of first rendering the tablature to audio using a simple sample-based virtual instrument, then performing style transfer using Flow Matching in order to transform the virtual instrument audio into more realistic sounding examples. This results in a model that is quick to train and to perform inference, requiring less than 6 hours of training data. We present the results of objective evaluation metrics, together with a listening test, in which we show significant improvement in the realism of the generated guitar audio from tablatures. --- ### Addressing Corner Cases in Autonomous Driving: A World Model-based Approach with Mixture of Experts and LLMs Authors: Haicheng Liao, Bonan Wang, Junxian Yang, Chengyue Wang, Zhengbin He, Guohui Zhang, Chengzhong Xu, Zhenning Li Published: 2025-10-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.21867v1 Accurate and reliable motion forecasting is essential for the safe deployment of autonomous vehicles (AVs), particularly in rare but safety-critical scenarios known as corner cases. Existing models often underperform in these situations due to an over-representation of common scenes in training data and limited generalization capabilities. To address this limitation, we present WM-MoE, the first world model-based motion forecasting framework that unifies perception, temporal memory, and decision making to address the challenges of high-risk corner-case scenarios. The model constructs a compact scene representation that explains current observations, anticipates future dynamics, and evaluates the outcomes of potential actions. To enhance long-horizon reasoning, we leverage large language models (LLMs) and introduce a lightweight temporal tokenizer that maps agent trajectories and contextual cues into the LLM's feature space without additional training, enriching temporal context and commonsense priors. Furthermore, a mixture-of-experts (MoE) is introduced to decompose complex corner cases into subproblems and allocate capacity across scenario types, and a router assigns scenes to specialized experts that infer agent intent and perform counterfactual rollouts. In addition, we introduce nuScenes-corner, a new benchmark that comprises four real-world corner-case scenarios for rigorous evaluation. Extensive experiments on four benchmark datasets (nuScenes, NGSIM, HighD, and MoCAD) showcase that WM-MoE consistently outperforms state-of-the-art (SOTA) baselines and remains robust under corner-case and data-missing conditions, indicating the promise of world model-based architectures for robust and generalizable motion forecasting in fully AVs. --- ### Capability Ceilings in Autoregressive Language Models: Empirical Evidence from Knowledge-Intensive Tasks Authors: Javier Marín Published: 2025-10-23 Categories: cs.AI arXiv: https://arxiv.org/abs/2510.21866v1 We document empirical capability ceilings in decoder-only autoregressive language models across knowledge-intensive tasks. Systematic evaluation of OPT and Pythia model families (70M-30B parameters, spanning 240 times scaling) reveals that knowledge retrieval tasks show negligible accuracy improvement despite smooth loss reduction. On MMLU mathematics benchmarks, accuracy remains flat at 19-20% (below 25% random chance) across all scales while cross-entropy loss decreases by 31%. In contrast, procedural tasks like arithmetic show conventional scaling where both metrics improve together. Attention intervention experiments reveal high sensitivity to perturbation: swapping attention patterns between models causes catastrophic performance collapse (complete accuracy loss) rather than graceful degradation. These measurements have immediate engineering implications: for knowledge-intensive applications using OPT and Pythia architectures, parameter scaling beyond 1-2B offers minimal accuracy gains despite continued loss improvement. Our findings quantify capability-specific scaling failures in these model families to inform resource allocation decisions. Whether these patterns reflect fundamental constraints of decoder-only architectures or implementation-specific limitations remains an open question requiring investigation across diverse architectural approaches. --- ### Prefetching Cache Optimization Using Graph Neural Networks: A Modular Framework and Conceptual Analysis Authors: F. I. Qowy Published: 2025-10-23 Categories: cs.PF, cs.LG, cs.SE arXiv: https://arxiv.org/abs/2510.21865v1 Caching and prefetching techniques are fundamental to modern computing, serving to bridge the growing performance gap between processors and memory. Traditional prefetching strategies are often limited by their reliance on predefined heuristics or simplified statistical models, which fail to capture the complex, non-linear dependencies in modern data access patterns. This paper introduces a modular framework leveraging Graph Neural Networks (GNNs) to model and predict access patterns within graph-structured data, focusing on web navigation and hierarchical file systems. The toolchain consists of: a route mapper for extracting structural information, a graph constructor for creating graph representations, a walk session generator for simulating user behaviors, and a gnn prefetch module for training and inference. We provide a detailed conceptual analysis showing how GNN-based approaches can outperform conventional methods by learning intricate dependencies. This work offers both theoretical foundations and a practical, replicable pipeline for future research in graph-driven systems optimization. --- ### LSF-Animation: Label-Free Speech-Driven Facial Animation via Implicit Feature Representation Authors: Xin Lu, Chuanqing Zhuang, Chenxi Jin, Zhengda Lu, Yiqun Wang, Wu Liu, Jun Xiao Published: 2025-10-23 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2510.21864v1 Speech-driven 3D facial animation has attracted increasing interest since its potential to generate expressive and temporally synchronized digital humans. While recent works have begun to explore emotion-aware animation, they still depend on explicit one-hot encodings to represent identity and emotion with given emotion and identity labels, which limits their ability to generalize to unseen speakers. Moreover, the emotional cues inherently present in speech are often neglected, limiting the naturalness and adaptability of generated animations. In this work, we propose LSF-Animation, a novel framework that eliminates the reliance on explicit emotion and identity feature representations. Specifically, LSF-Animation implicitly extracts emotion information from speech and captures the identity features from a neutral facial mesh, enabling improved generalization to unseen speakers and emotional states without requiring manual labels. Furthermore, we introduce a Hierarchical Interaction Fusion Block (HIFB), which employs a fusion token to integrate dual transformer features and more effectively integrate emotional, motion-related and identity-related cues. Extensive experiments conducted on the 3DMEAD dataset demonstrate that our method surpasses recent state-of-the-art approaches in terms of emotional expressiveness, identity generalization, and animation realism. The source code will be released at: https://github.com/Dogter521/LSF-Animation. --- ### A Multi-Stage Hybrid Framework for Automated Interpretation of Multi-View Engineering Drawings Using Vision Language Model Authors: Muhammad Tayyab Khan, Zane Yong, Lequn Chen, Wenhe Feng, Nicholas Yew Jin Tan, Seung Ki Moon Published: 2025-10-23 Categories: cs.CV, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2510.21862v2 Engineering drawings are fundamental to manufacturing communication, serving as the primary medium for conveying design intent, tolerances, and production details. However, interpreting complex multi-view drawings with dense annotations remains challenging using manual methods, generic optical character recognition (OCR) systems, or traditional deep learning approaches, due to varied layouts, orientations, and mixed symbolic-textual content. To address these challenges, this paper proposes a three-stage hybrid framework for the automated interpretation of 2D multi-view engineering drawings using modern detection and vision language models (VLMs). In the first stage, YOLOv11-det performs layout segmentation to localize key regions such as views, title blocks, and notes. The second stage uses YOLOv11-obb for orientation-aware, fine-grained detection of annotations, including measures, GD&T symbols, and surface roughness indicators. The third stage employs two Donut-based, OCR-free VLMs for semantic content parsing: the Alphabetical VLM extracts textual and categorical information from title blocks and notes, while the Numerical VLM interprets quantitative data such as measures, GD&T frames, and surface roughness. Two specialized datasets were developed to ensure robustness and generalization: 1,000 drawings for layout detection and 1,406 for annotation-level training. The Alphabetical VLM achieved an overall F1 score of 0.672, while the Numerical VLM reached 0.963, demonstrating strong performance in textual and quantitative interpretation, respectively. The unified JSON output enables seamless integration with CAD and manufacturing databases, providing a scalable solution for intelligent engineering drawing analysis. --- ### The Mirror Loop: Recursive Non-Convergence in Generative Reasoning Systems Authors: Bentley DeVilling Published: 2025-10-23 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2510.21861v2 Large language models are often described as capable of reflective reasoning, yet recursive self-evaluation without external feedback frequently yields reformulation rather than progress. We test this prediction in a cross-provider study of 144 reasoning sequences across three models (OpenAI GPT-4o-mini, Anthropic Claude 3 Haiku, and Google Gemini 2.0 Flash) and four task families (arithmetic, code, explanation, reflection), each iterated ten times under two conditions: ungrounded self-critique and a minimal grounding intervention (a single verification step at iteration three). Mean informational change (delta I, measured via normalized edit distance) declined by 55% from early (0.193) to late (0.087) iterations in ungrounded runs, with consistent patterns across all three providers. Grounded runs showed a +28% rebound in informational change immediately after the intervention and sustained non-zero variance thereafter. Complementary measures-n-gram novelty, embedding drift, and character-level entropy-converged on the same pattern: reflection without contact tends toward informational closure. We interpret this as evidence for a structural limit on self-correction in generative reasoning: without an exchange of information with an independent verifier or environment, recursive inference approaches an attractor state of epistemic stasis. Minimal grounding functions as dissipative coupling, reintroducing informational flux. The cross-architecture consistency suggests the mirror loop arises from shared autoregressive training objectives rather than provider-specific alignment schemes. The results delineate when reflection is performative rather than epistemic and motivate design principles for grounded, cooperative reasoning. Materials and code are publicly available. --- ### Butter-Bench: Evaluating LLM Controlled Robots for Practical Intelligence Authors: Callum Sharrock, Lukas Petersson, Hanna Petersson, Axel Backlund, Axel Wennström, Kristoffer Nordström, Elias Aronsson Published: 2025-10-23 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2510.21860v1 We present Butter-Bench, a benchmark evaluating large language model (LLM) controlled robots for practical intelligence, defined as the ability to navigate the messiness of the physical world. Current state-of-the-art robotic systems use a hierarchical architecture with LLMs in charge of high-level reasoning, and a Vision Language Action (VLA) model for low-level control. Butter-Bench evaluates the LLM part in isolation from the VLA. Although LLMs have repeatedly surpassed humans in evaluations requiring analytical intelligence, we find humans still outperform LLMs on Butter-Bench. The best LLMs score 40% on Butter-Bench, while the mean human score is 95%. LLMs struggled the most with multi-step spatial planning and social understanding. We also evaluate LLMs that are fine-tuned for embodied reasoning and conclude that this training does not improve their score on Butter-Bench. --- ### OpenEM: Large-scale multi-structural 3D datasets for electromagnetic methods Authors: Shuang Wang, Xuben Wang, Fei Deng, Peifan Jiang, Jian Chen, Gianluca Fiandaca Published: 2025-10-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.21859v3 Electromagnetic (EM) methods, owing to their efficiency and non-invasive nature, have become one of the most widely used techniques in geological exploration. Nevertheless, data processing for these methods remains highly time-consuming and labor-intensive. With the remarkable success of deep learning, applying such techniques to EM methods has emerged as a promising research direction to overcome the limitations of conventional approaches. The effectiveness of deep learning methods depends heavily on the quality of datasets, which directly influences model performance and generalization ability. Existing application studies often construct datasets from random one-dimensional or structurally simple threedimensional (3D) models, which fail to represent the complexity of real geological environments. Furthermore, the absence of standardized, publicly available 3D geoelectric datasets continues to hinder progress in deep learning based EM exploration. To address these limitations, we present OpenEM, a large-scale, multi-structural 3D geoelectric dataset that encompasses a broad range of geologically plausible subsurface structures. OpenEM consists of nine categories of geoelectric models, spanning from simple configurations with anomalous bodies in half-space to more complex structures such as flat layers, folded layers, flat faults, curved faults and their corresponding variants with anomalous bodies. In addition, we provide a 3D model generator that enables fully controllable 3D model construction, allowing flexible and extensible augmentation of OpenEM. OpenEM provides a unified, comprehensive, and large-scale dataset for common EM exploration systems to accelerate the application of deep learning in electromagnetic methods. The complete dataset and 3D model generator is publicly available at https://doi.org/10.5281/zenodo.17141981. --- ### Privacy-preserving Decision-focused Learning for Multi-energy Systems Authors: Yangze Zhou, Ruiyang Yao, Dalin Qin, Yixiong Jia, Yi Wang Published: 2025-10-23 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2510.21858v1 Decision-making for multi-energy system (MES) dispatch depends on accurate load forecasting. Traditionally, load forecasting and decision-making for MES are implemented separately. Forecasting models are typically trained to minimize forecasting errors, overlooking their impact on downstream decision-making. To address this, decision-focused learning (DFL) has been studied to minimize decision-making costs instead. However, practical adoption of DFL in MES faces significant challenges: the process requires sharing sensitive load data and model parameters across multiple sectors, raising serious privacy issues. To this end, we propose a privacy-preserving DFL framework tailored for MES. Our approach introduces information masking to safeguard private data while enabling recovery of decision variables and gradients required for model training. To further enhance security for DFL, we design a safety protocol combining matrix decomposition and homomorphic encryption, effectively preventing collusion and unauthorized data access. Additionally, we developed a privacy-preserving load pattern recognition algorithm, enabling the training of specialized DFL models for heterogeneous load patterns. Theoretical analysis and comprehensive case studies, including real-world MES data, demonstrate that our framework not only protects privacy but also consistently achieves lower average daily dispatch costs compared to existing methods. --- ### Poisson Flow Consistency Training Authors: Anthony Zhang, Mahmut Gokmen, Dennis Hein, Rongjun Ge, Wenjun Xia, Ge Wang, Jin Chen Published: 2025-10-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.21857v1 The Poisson Flow Consistency Model (PFCM) is a consistency-style model based on the robust Poisson Flow Generative Model++ (PFGM++) which has achieved success in unconditional image generation and CT image denoising. Yet the PFCM can only be trained in distillation which limits the potential of the PFCM in many data modalities. The objective of this research was to create a method to train the PFCM in isolation called Poisson Flow Consistency Training (PFCT). The perturbation kernel was leveraged to remove the pretrained PFGM++, and the sinusoidal discretization schedule and Beta noise distribution were introduced in order to facilitate adaptability and improve sample quality. The model was applied to the task of low dose computed tomography image denoising and improved the low dose image in terms of LPIPS and SSIM. It also displayed similar denoising effectiveness as models like the Consistency Model. PFCT is established as a valid method of training the PFCM from its effectiveness in denoising CT images, showing potential with competitive results to other generative models. Further study is needed in the precise optimization of PFCT and in its applicability to other generative modeling tasks. The framework of PFCT creates more flexibility for the ways in which a PFCM can be created and can be applied to the field of generative modeling. --- ### GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs Authors: Guanghao Zheng, Bowen Shi, Mingxing Xu, Ruoyu Sun, Peisen Zhao, Zhibo Zhang, Wenrui Dai, Junni Zou, Hongkai Xiong, Xiaopeng Zhang, Qi Tian Published: 2025-10-23 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2510.21501v1 Vision encoders are indispensable for allowing impressive performance of Multi-modal Large Language Models (MLLMs) in vision language tasks such as visual question answering and reasoning. However, existing vision encoders focus on global image representations but overlook fine-grained regional analysis. They are limited in fine grained perception due to the scarcity of fine grained annotated data and the lack of a fine grained pre-training paradigm. In this paper, we propose GranViT, a novel Vision Transformer that integrates fine-grained feature extraction with semantic alignment to Large Language Models (LLMs) via region level autoregressive training. We first construct Gran-29M, a dataset comprising 2million natural and OCR images paired with over 180 million high-quality region-level annotations, to enable large scale fine grained pretraining. Consequently, we develop a pretraining-adaptation framework along with a self distillation mechanism to train fine-grained GranViT on Gran-29M. We sufficiently exploit the fine-grained annotations from Gran-29M to resort to bounding-box-to-caption regression to enhance localized visual representation of the vision encoder in the pretraining and caption-to-bounding-box regression to improve vision feature utilization and localization for LLM in the adaptation. We further incorporate a self distillation mechanism that imposes explicit localization constraints on the vision encoder to strengthen its regional reasoning capability. Extensive experiments show that GranViT surpasses existing vision encoders and attains strong transferability to varying LLMs. Remarkably, it achieves state-of-the-art results on fine-grained recognition, multimodal VQA, and OCR understanding. --- ### Online Multi-Class Selection with Group Fairness Guarantee Authors: Faraz Zargari, Hossein Nekouyan, Lyndon Hallett, Bo Sun, Xiaoqi Tan Published: 2025-10-23 Categories: cs.LG, cs.DS arXiv: https://arxiv.org/abs/2510.21055v1 We study the online multi-class selection problem with group fairness guarantees, where limited resources must be allocated to sequentially arriving agents. Our work addresses two key limitations in the existing literature. First, we introduce a novel lossless rounding scheme that ensures the integral algorithm achieves the same expected performance as any fractional solution. Second, we explicitly address the challenges introduced by agents who belong to multiple classes. To this end, we develop a randomized algorithm based on a relax-and-round framework. The algorithm first computes a fractional solution using a resource reservation approach -- referred to as the set-aside mechanism -- to enforce fairness across classes. The subsequent rounding step preserves these fairness guarantees without degrading performance. Additionally, we propose a learning-augmented variant that incorporates untrusted machine-learned predictions to better balance fairness and efficiency in practical settings. --- ### Amortized Active Generation of Pareto Sets Authors: Daniel M. Steinberg, Asiri Wijesinghe, Rafael Oliveira, Piotr Koniusz, Cheng Soon Ong, Edwin V. Bonilla Published: 2025-10-23 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.21052v3 We introduce active generation of Pareto sets (A-GPS), a new framework for online discrete black-box multi-objective optimization (MOO). A-GPS learns a generative model of the Pareto set that supports a-posteriori conditioning on user preferences. The method employs a class probability estimator (CPE) to predict non-dominance relations and to condition the generative model toward high-performing regions of the search space. We also show that this non-dominance CPE implicitly estimates the probability of hypervolume improvement (PHVI). To incorporate subjective trade-offs, A-GPS introduces preference direction vectors that encode user-specified preferences in objective space. At each iteration, the model is updated using both Pareto membership and alignment with these preference directions, producing an amortized generative model capable of sampling across the Pareto front without retraining. The result is a simple yet powerful approach that achieves high-quality Pareto set approximations, avoids explicit hypervolume computation, and flexibly captures user preferences. Empirical results on synthetic benchmarks and protein design tasks demonstrate strong sample efficiency and effective preference incorporation. --- ### Amortized Active Generation of Pareto Sets Authors: Daniel M. Steinberg, Asiri Wijesinghe, Rafael Oliveira, Piotr Koniusz, Cheng Soon Ong, Edwin V. Bonilla Published: 2025-10-23 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.21052v1 We introduce active generation of Pareto sets (A-GPS), a new framework for online discrete black-box multi-objective optimization (MOO). A-GPS learns a generative model of the Pareto set that supports a-posteriori conditioning on user preferences. The method employs a class probability estimator (CPE) to predict non-dominance relations and to condition the generative model toward high-performing regions of the search space. We also show that this non-dominance CPE implicitly estimates the probability of hypervolume improvement (PHVI). To incorporate subjective trade-offs, A-GPS introduces preference direction vectors that encode user-specified preferences in objective space. At each iteration, the model is updated using both Pareto membership and alignment with these preference directions, producing an amortized generative model capable of sampling across the Pareto front without retraining. The result is a simple yet powerful approach that achieves high-quality Pareto set approximations, avoids explicit hypervolume computation, and flexibly captures user preferences. Empirical results on synthetic benchmarks and protein design tasks demonstrate strong sample efficiency and effective preference incorporation. --- ### Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection Authors: Atoosa Chegini, Hamid Kazemi, Garrett Souza, Maria Safi, Yang Song, Samy Bengio, Sinead Williamson, Mehrdad Farajtabar Published: 2025-10-23 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.21049v1 Reasoning has become a central paradigm for large language models (LLMs), consistently boosting accuracy across diverse benchmarks. Yet its suitability for precision-sensitive tasks remains unclear. We present the first systematic study of reasoning for classification tasks under strict low false positive rate (FPR) regimes. Our analysis covers two tasks--safety detection and hallucination detection--evaluated in both fine-tuned and zero-shot settings, using standard LLMs and Large Reasoning Models (LRMs). Our results reveal a clear trade-off: Think On (reasoning-augmented) generation improves overall accuracy, but underperforms at the low-FPR thresholds essential for practical use. In contrast, Think Off (no reasoning during inference) dominates in these precision-sensitive regimes, with Think On surpassing only when higher FPRs are acceptable. In addition, we find token-based scoring substantially outperforms self-verbalized confidence for precision-sensitive deployments. Finally, a simple ensemble of the two modes recovers the strengths of each. Taken together, our findings position reasoning as a double-edged tool: beneficial for average accuracy, but often ill-suited for applications requiring strict precision. --- ### xMem: A CPU-Based Approach for Accurate Estimation of GPU Memory in Deep Learning Training Workloads Authors: Jiabo Shi, Dimitrios Pezaros, Yehia Elkhatib Published: 2025-10-23 Categories: cs.PF, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2510.21048v1 The global scarcity of GPUs necessitates more sophisticated strategies for Deep Learning jobs in shared cluster environments. Accurate estimation of how much GPU memory a job will require is fundamental to enabling advanced scheduling and GPU sharing, which helps prevent out-of-memory (OOM) errors and resource underutilization. However, existing estimation methods have limitations. Approaches relying on static analysis or historical data with machine learning often fail to accurately capture runtime dynamics. Furthermore, direct GPU analysis consumes scarce resources, and some techniques require intrusive code modifications. Thus, the key challenge lies in precisely estimating dynamic memory requirements, including memory allocator nuances, without consuming GPU resources and non-intrusive code changes. To address this challenge, we propose xMem, a novel framework that leverages CPU-only dynamic analysis to accurately estimate peak GPU memory requirements a priori. We conducted a thorough evaluation of xMem against state-of-the-art solutions using workloads from 25 different models, including architectures like Convolutional Neural Networks and Transformers. The analysis of 5209 runs, which includes ANOVA and Monte Carlo results, highlights xMem's benefits: it decreases the median relative error by 91% and significantly reduces the probability of estimation failure as safe OOM thresholds by 75%, meaning that the estimated value can often be used directly without causing OOM. Ultimately, these improvements lead to a 368% increase in memory conservation potential over current solutions. --- ### From Questions to Queries: An AI-powered Multi-Agent Framework for Spatial Text-to-SQL Authors: Ali Khosravi Kazazi, Zhenlong Li, M. Naser Lessani, Guido Cervone Published: 2025-10-23 Categories: cs.AI, cs.DB, cs.IR arXiv: https://arxiv.org/abs/2510.21045v3 The complexity of SQL and the spatial semantics of PostGIS create barriers for non-experts working with spatial data. Although large language models can translate natural language into SQL, spatial Text-to-SQL is more error-prone than general Text-to-SQL because it must resolve geographic intent, schema ambiguity, geometry-bearing tables and columns, spatial function choice, and coordinate reference system and measurement assumptions. We introduce a multi-agent framework that addresses these coupled challenges through staged interpretation, schema grounding, logical planning, SQL generation, and execution-based review. The framework is supported by a knowledge base with programmatic schema profiling, semantic enrichment, and embedding-based retrieval. We evaluated the framework on the non-spatial KaggleDBQA benchmark and on SpatialQueryQA, a new multi-level and coverage-oriented benchmark with diverse geometry types, workload categories, and spatial operations. On KaggleDBQA, the system reached 81.2% accuracy, 221 of 272 questions, after reviewer corrections. On SpatialQueryQA, the system achieved 87.7% accuracy, 79 of 90, compared with 76.7% without the review stage. These results show that decomposing the task into specialized but tightly coupled agents improves robustness, especially for spatially sensitive queries. The study improves access to spatial analysis and provides a practical step toward more reliable spatial Text-to-SQL systems and autonomous GIS. --- ### From Questions to Queries: An AI-powered Multi-Agent Framework for Spatial Text-to-SQL Authors: Ali Khosravi Kazazi, Zhenlong Li, M. Naser Lessani, Guido Cervone Published: 2025-10-23 Categories: cs.AI, cs.DB, cs.IR arXiv: https://arxiv.org/abs/2510.21045v1 The complexity of Structured Query Language (SQL) and the specialized nature of geospatial functions in tools like PostGIS present significant barriers to non-experts seeking to analyze spatial data. While Large Language Models (LLMs) offer promise for translating natural language into SQL (Text-to-SQL), single-agent approaches often struggle with the semantic and syntactic complexities of spatial queries. To address this, we propose a multi-agent framework designed to accurately translate natural language questions into spatial SQL queries. The framework integrates several innovative components, including a knowledge base with programmatic schema profiling and semantic enrichment, embeddings for context retrieval, and a collaborative multi-agent pipeline as its core. This pipeline comprises specialized agents for entity extraction, metadata retrieval, query logic formulation, SQL generation, and a review agent that performs programmatic and semantic validation of the generated SQL to ensure correctness (self-verification). We evaluate our system using both the non-spatial KaggleDBQA benchmark and a new, comprehensive SpatialQueryQA benchmark that includes diverse geometry types, predicates, and three levels of query complexity. On KaggleDBQA, the system achieved an overall accuracy of 81.2% (221 out of 272 questions) after the review agent's review and corrections. For spatial queries, the system achieved an overall accuracy of 87.7% (79 out of 90 questions), compared with 76.7% without the review agent. Beyond accuracy, results also show that in some instances the system generates queries that are more semantically aligned with user intent than those in the benchmarks. This work makes spatial analysis more accessible, and provides a robust, generalizable foundation for spatial Text-to-SQL systems, advancing the development of autonomous GIS. --- ### Epistemic Deference to AI Authors: Benjamin Lange Published: 2025-10-23 Categories: cs.AI, cs.CY arXiv: https://arxiv.org/abs/2510.21043v1 When should we defer to AI outputs over human expert judgment? Drawing on recent work in social epistemology, I motivate the idea that some AI systems qualify as Artificial Epistemic Authorities (AEAs) due to their demonstrated reliability and epistemic superiority. I then introduce AI Preemptionism, the view that AEA outputs should replace rather than supplement a user's independent epistemic reasons. I show that classic objections to preemptionism - such as uncritical deference, epistemic entrenchment, and unhinging epistemic bases - apply in amplified form to AEAs, given their opacity, self-reinforcing authority, and lack of epistemic failure markers. Against this, I develop a more promising alternative: a total evidence view of AI deference. According to this view, AEA outputs should function as contributory reasons rather than outright replacements for a user's independent epistemic considerations. This approach has three key advantages: (i) it mitigates expertise atrophy by keeping human users engaged, (ii) it provides an epistemic case for meaningful human oversight and control, and (iii) it explains the justified mistrust of AI when reliability conditions are unmet. While demanding in practice, this account offers a principled way to determine when AI deference is justified, particularly in high-stakes contexts requiring rigorous reliability. --- ### Efficient Meningioma Tumor Segmentation Using Ensemble Learning Authors: Mohammad Mahdi Danesh Pajouh, Sara Saeedi Published: 2025-10-23 Categories: eess.IV, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2510.21040v1 Meningiomas represent the most prevalent form of primary brain tumors, comprising nearly one-third of all diagnosed cases. Accurate delineation of these tumors from MRI scans is crucial for guiding treatment strategies, yet remains a challenging and time-consuming task in clinical practice. Recent developments in deep learning have accelerated progress in automated tumor segmentation; however, many advanced techniques are hindered by heavy computational demands and long training schedules, making them less accessible for researchers and clinicians working with limited hardware. In this work, we propose a novel ensemble-based segmentation approach that combines three distinct architectures: (1) a baseline SegResNet model, (2) an attention-augmented SegResNet with concatenative skip connections, and (3) a dual-decoder U-Net enhanced with attention-gated skip connections (DDUNet). The ensemble aims to leverage architectural diversity to improve robustness and accuracy while significantly reducing training demands. Each baseline model was trained for only 20 epochs and Evaluated on the BraTS-MEN 2025 dataset. The proposed ensemble model achieved competitive performance, with average Lesion-Wise Dice scores of 77.30%, 76.37% and 73.9% on test dataset for Enhancing Tumor (ET), Tumor Core (TC) and Whole Tumor (WT) respectively. These results highlight the effectiveness of ensemble learning for brain tumor segmentation, even under limited hardware constraints. Our proposed method provides a practical and accessible tool for aiding the diagnosis of meningioma, with potential impact in both clinical and research settings. --- ### Elementary, My Dear Watson: Non-Invasive Neural Keyword Spotting in the LibriBrain Dataset Authors: Gereon Elvers, Gilad Landau, Oiwi Parker Jones Published: 2025-10-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.21038v2 Non-invasive brain-computer interfaces (BCIs) are beginning to benefit from large, public benchmarks. However, current benchmarks target relatively simple, foundational tasks like Speech Detection and Phoneme Classification, while application-ready results on tasks like Brain-to-Text remain elusive. We propose Keyword Spotting (KWS) as a practically applicable, privacy-aware intermediate task. Using the deep 52-hour, within-subject LibriBrain corpus, we provide standardized train/validation/test splits for reproducible benchmarking, and adopt an evaluation protocol tailored to extreme class imbalance. Concretely, we use area under the precision-recall curve (AUPRC) as a robust evaluation metric, complemented by false alarms per hour (FA/h) at fixed recall to capture user-facing trade-offs. To simplify deployment and further experimentation within the research community, we are releasing an updated version of the pnpl library with word-level dataloaders and Colab-ready tutorials. As an initial reference model, we present a compact 1-D Conv/ResNet baseline with focal loss and top-k pooling that is trainable on a single consumer-class GPU. The reference model achieves approximately 13x the permutation baseline AUPRC on held-out sessions, demonstrating the viability of the task. Exploratory analyses reveal: (i) predictable within-subject scaling - performance improves log-linearly with more training hours - and (ii) the existence of word-level factors (frequency and duration) that systematically modulate detectability. --- ### Input Matters: Evaluating Input Structure's Impact on LLM Summaries of Sports Play-by-Play Authors: Barkavi Sundararajan, Somayajulu Sripada, Ehud Reiter Published: 2025-10-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.21034v2 A major concern when deploying LLMs in accuracy-critical domains such as sports reporting is that the generated text may not faithfully reflect the input data. We quantify how input structure affects hallucinations and other factual errors in LLM-generated summaries of NBA play-by-play data, across three formats: row-structured, JSON and unstructured. We manually annotated 3,312 factual errors across 180 game summaries produced by two models, Llama-3.1-70B and Qwen2.5-72B. Input structure has a strong effect: JSON input reduces error rates by 69% for Llama and 65% for Qwen compared to unstructured input, while row-structured input reduces errors by 54% for Llama and 51% for Qwen. A two-way repeated measures ANOVA shows that input structure accounts for over 80% of the variance in error rates, with Tukey HSD post hoc tests confirming statistically significant differences between all input formats. --- ### Iso-Riemannian Optimization on Learned Data Manifolds Authors: Willem Diepeveen, Melanie Weber Published: 2025-10-23 Categories: math.OC, cs.LG, math.DG arXiv: https://arxiv.org/abs/2510.21033v3 We develop a theory of iso-Riemannian optimization for problems constrained to learned data manifolds, a setting in which classical Riemannian optimization - and Riemannian gradient descent in particular - can be poorly suited. That is, favorable Euclidean properties of an objective need not translate into geodesic convexity or L-smoothness, and the Riemannian gradient may provide an unsuitable search direction. We instead combine the manifold mappings induced by the iso-connection, whose geodesics have constant Euclidean speed, with the l2-projected Euclidean gradient, resulting in l2-projected gradient iso-Riemannian descent, in an attempt to alleviate these issues. We analyze this scheme from two complementary perspectives. First, we introduce iso-g-convexity and iso-L-smoothness, relate strong iso-g-convexity to a Polyak-Lojasiewicz-type condition, and establish general convergence guarantees. This function-based theory addresses the conditioning and search-direction issues that motivate our approach. Second, we introduce iso-monotonicity and iso-Lipschitzness for vector fields. However, while these notions yield analogous convergence results in one dimension and enable applications such as the computation of iso-Riemannian barycentres, the resulting theory need not extend meaningfully to higher dimensions. So unlike in the classical Levi-Civita setting, these function- and vector field-based perspectives need not be equivalent in the iso-Riemannian setting. Consequently, distinct extensions of classical Riemannian optimization lead to different assumptions and convergence guarantees. The theory developed here suggests that, for function optimization, the function-based perspective provides the more general, tractable and overall suitable framework, whereas the vector field perspective is naturally reserved for problems without a direct function-based formulation. --- ### Iso-Riemannian Optimization on Learned Data Manifolds Authors: Willem Diepeveen, Melanie Weber Published: 2025-10-23 Categories: math.OC, cs.LG, math.DG, 90C26, 68T07, 53Z50 arXiv: https://arxiv.org/abs/2510.21033v1 High-dimensional data that exhibit an intrinsic low-dimensional structure are ubiquitous in machine learning and data science. While various approaches allow for learning the corresponding data manifold from finite samples, performing downstream tasks such as optimization directly on these learned manifolds presents a significant challenge. This work introduces a principled framework for optimization on learned data manifolds using iso-Riemannian geometry. Our approach addresses key limitations of classical Riemannian optimization in this setting, specifically, that the Levi-Civita connection fails to yield constant-speed geodesics, and that geodesic convexity assumptions break down under the learned pullback constructions commonly used in practice. To overcome these challenges, we propose new notions of monotonicity and Lipschitz continuity tailored to the iso-Riemannian setting and propose iso-Riemannian descent algorithms for which we provide a detailed convergence analysis. We demonstrate the practical effectiveness of those algorithms on both synthetic and real datasets, including MNIST under a learned pullback structure. Our approach yields interpretable barycentres, improved clustering, and provably efficient solutions to inverse problems, even in high-dimensional settings. These results establish that optimization under iso-Riemannian geometry can overcome distortions inherent to learned manifold mappings. --- ### AgentArcEval: An Architecture Evaluation Method for Foundation Model based Agents Authors: Qinghua Lu, Dehai Zhao, Yue Liu, Hao Zhang, Liming Zhu, Xiwei Xu, Angela Shi, Tristan Tan, Rick Kazman Published: 2025-10-23 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2510.21031v1 The emergence of foundation models (FMs) has enabled the development of highly capable and autonomous agents, unlocking new application opportunities across a wide range of domains. Evaluating the architecture of agents is particularly important as the architectural decisions significantly impact the quality attributes of agents given their unique characteristics, including compound architecture, autonomous and non-deterministic behaviour, and continuous evolution. However, these traditional methods fall short in addressing the evaluation needs of agent architecture due to the unique characteristics of these agents. Therefore, in this paper, we present AgentArcEval, a novel agent architecture evaluation method designed specially to address the complexities of FM-based agent architecture and its evaluation. Moreover, we present a catalogue of agent-specific general scenarios, which serves as a guide for generating concrete scenarios to design and evaluate the agent architecture. We demonstrate the usefulness of AgentArcEval and the catalogue through a case study on the architecture evaluation of a real-world tax copilot, named Luna. --- ### Customizing Open Source LLMs for Quantitative Medication Attribute Extraction across Heterogeneous EHR Systems Authors: Zhe Fei, Mehmet Yigit Turali, Shreyas Rajesh, Xinyang Dai, Huyen Pham, Pavan Holur, Yuhui Zhu, Larissa Mooney, Yih-Ing Hser, Vwani Roychowdhury Published: 2025-10-23 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2510.21027v1 Harmonizing medication data across Electronic Health Record (EHR) systems is a persistent barrier to monitoring medications for opioid use disorder (MOUD). In heterogeneous EHR systems, key prescription attributes are scattered across differently formatted fields and freetext notes. We present a practical framework that customizes open source large language models (LLMs), including Llama, Qwen, Gemma, and MedGemma, to extract a unified set of MOUD prescription attributes (prescription date, drug name, duration, total quantity, daily quantity, and refills) from heterogeneous, site specific data and compute a standardized metric of medication coverage, \emph{MOUD days}, per patient. Our pipeline processes records directly in a fixed JSON schema, followed by lightweight normalization and cross-field consistency checks. We evaluate the system on prescription level EHR data from five clinics in a national OUD study (25{,}605 records from 1{,}257 patients), using a previously annotated benchmark of 10{,}369 records (776 patients) as the ground truth. Performance is reported as coverage (share of records with a valid, matchable output) and record-level exact-match accuracy. Larger models perform best overall: Qwen2.5-32B achieves \textbf{93.4\%} coverage with \textbf{93.0\%} exact-match accuracy across clinics, and MedGemma-27B attains \textbf{93.1\%}/\textbf{92.2\%}. A brief error review highlights three common issues and fixes: imputing missing dosage fields using within-drug norms, handling monthly/weekly injectables (e.g., Vivitrol) by setting duration from the documented schedule, and adding unit checks to prevent mass units (e.g., ``250 g'') from being misread as daily counts. By removing brittle, site-specific ETL and supporting local, privacy-preserving deployment, this approach enables consistent cross-site analyses of MOUD exposure, adherence, and retention in real-world settings. --- ### JSTprove: Pioneering Verifiable AI for a Trustless Future Authors: Jonathan Gold, Tristan Freiberg, Haruna Isah, Shirin Shahabi Published: 2025-10-23 Categories: cs.CR, cs.AI, cs.DC, cs.LG arXiv: https://arxiv.org/abs/2510.21024v1 The integration of machine learning (ML) systems into critical industries such as healthcare, finance, and cybersecurity has transformed decision-making processes, but it also brings new challenges around trust, security, and accountability. As AI systems become more ubiquitous, ensuring the transparency and correctness of AI-driven decisions is crucial, especially when they have direct consequences on privacy, security, or fairness. Verifiable AI, powered by Zero-Knowledge Machine Learning (zkML), offers a robust solution to these challenges. zkML enables the verification of AI model inferences without exposing sensitive data, providing an essential layer of trust and privacy. However, traditional zkML systems typically require deep cryptographic expertise, placing them beyond the reach of most ML engineers. In this paper, we introduce JSTprove, a specialized zkML toolkit, built on Polyhedra Network's Expander backend, to enable AI developers and ML engineers to generate and verify proofs of AI inference. JSTprove provides an end-to-end verifiable AI inference pipeline that hides cryptographic complexity behind a simple command-line interface while exposing auditable artifacts for reproducibility. We present the design, innovations, and real-world use cases of JSTprove as well as our blueprints and tooling to encourage community review and extension. JSTprove therefore serves both as a usable zkML product for current engineering needs and as a reproducible foundation for future research and production deployments of verifiable AI. --- ### Physically consistent and uncertainty-aware learning of spatiotemporal dynamics Authors: Qingsong Xu, Jonathan L Bamber, Nils Thuerey, Niklas Boers, Paul Bates, Gustau Camps-Valls, Yilei Shi, Xiao Xiang Zhu Published: 2025-10-23 Categories: cs.LG, cs.AI, physics.comp-ph arXiv: https://arxiv.org/abs/2510.21023v1 Accurate long-term forecasting of spatiotemporal dynamics remains a fundamental challenge across scientific and engineering domains. Existing machine learning methods often neglect governing physical laws and fail to quantify inherent uncertainties in spatiotemporal predictions. To address these challenges, we introduce a physics-consistent neural operator (PCNO) that enforces physical constraints by projecting surrogate model outputs onto function spaces satisfying predefined laws. A physics-consistent projection layer within PCNO efficiently computes mass and momentum conservation in Fourier space. Building upon deterministic predictions, we further propose a diffusion model-enhanced PCNO (DiffPCNO), which leverages a consistency model to quantify and mitigate uncertainties, thereby improving the accuracy and reliability of forecasts. PCNO and DiffPCNO achieve high-fidelity spatiotemporal predictions while preserving physical consistency and uncertainty across diverse systems and spatial resolutions, ranging from turbulent flow modeling to real-world flood/atmospheric forecasting. Our two-stage framework provides a robust and versatile approach for accurate, physically grounded, and uncertainty-aware spatiotemporal forecasting. --- ### CIPHER: Scalable Time Series Analysis for Physical Sciences with Application to Solar Wind Phenomena Authors: Jasmine R. Kobayashi, Daniela Martin, Valmir P Moraes Filho, Connor O'Brien, Jinsu Hong, Sudeshna Boro Saikia, Hala Lamdouar, Nathan D. Miles, Marcella Scoczynski, Mavis Stone, Sairam Sundaresan, Anna Jungbluth et al. Published: 2025-10-23 Categories: cs.LG, astro-ph.SR arXiv: https://arxiv.org/abs/2510.21022v1 Labeling or classifying time series is a persistent challenge in the physical sciences, where expert annotations are scarce, costly, and often inconsistent. Yet robust labeling is essential to enable machine learning models for understanding, prediction, and forecasting. We present the \textit{Clustering and Indexation Pipeline with Human Evaluation for Recognition} (CIPHER), a framework designed to accelerate large-scale labeling of complex time series in physics. CIPHER integrates \textit{indexable Symbolic Aggregate approXimation} (iSAX) for interpretable compression and indexing, density-based clustering (HDBSCAN) to group recurring phenomena, and a human-in-the-loop step for efficient expert validation. Representative samples are labeled by domain scientists, and these annotations are propagated across clusters to yield systematic, scalable classifications. We evaluate CIPHER on the task of classifying solar wind phenomena in OMNI data, a central challenge in space weather research, showing that the framework recovers meaningful phenomena such as coronal mass ejections and stream interaction regions. Beyond this case study, CIPHER highlights a general strategy for combining symbolic representations, unsupervised learning, and expert knowledge to address label scarcity in time series across the physical sciences. The code and configuration files used in this study are publicly available to support reproducibility. --- ### From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD Authors: Konstantinos Christopher Tsiolis, Alireza Mousavi-Hosseini, Murat A. Erdogdu Published: 2025-10-23 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2510.21020v1 To understand feature learning dynamics in neural networks, recent theoretical works have focused on gradient-based learning of Gaussian single-index models, where the label is a nonlinear function of a latent one-dimensional projection of the input. While the sample complexity of online SGD is determined by the information exponent of the link function, recent works improved this by performing multiple gradient steps on the same sample with different learning rates -- yielding a non-correlational update rule -- and instead are limited by the (potentially much smaller) generative exponent. However, this picture is only valid when these learning rates are sufficiently large. In this paper, we characterize the relationship between learning rate(s) and sample complexity for a broad class of gradient-based algorithms that encapsulates both correlational and non-correlational updates. We demonstrate that, in certain cases, there is a phase transition from an "information exponent regime" with small learning rate to a "generative exponent regime" with large learning rate. Our framework covers prior analyses of one-pass SGD and SGD with batch reuse, while also introducing a new layer-wise training algorithm that leverages a two-timescales approach (via different learning rates for each layer) to go beyond correlational queries without reusing samples or modifying the loss from squared error. Our theoretical study demonstrates that the choice of learning rate is as important as the design of the algorithm in achieving statistical and computational efficiency. --- ### More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning Authors: Wanhao Yu, Zheng Wang, Shuteng Niu, Sen Lin, Li Yang Published: 2025-10-23 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2510.21019v3 Zeroth-order (ZO) optimization has gained attention as a memory-efficient alternative to first-order (FO) methods, particularly in settings where gradient computation is expensive or even impractical. Beyond its memory efficiency, in this work, we investigate ZO optimization for continual learning (CL) as a novel approach to address the plasticity-stability-efficiency trilemma. Through theoretical analysis and empirical evidence, we show that ZO optimization naturally leads to flatter loss landscapes, which in turn reduce forgetting in CL. However, this stability comes at a cost of plasticity: due to its imprecise gradient estimates and slower convergence, ZO optimization tends to be less effective than FO in acquiring new task-specific knowledge, particularly under constrained training budgets. To better understand this trade-off, we conduct a holistic evaluation of ZO optimization applied to various existing CL methods. Our findings reveal that ZO optimization enhances stability but often undermines plasticity, particularly when used with learnable classifiers. Motivated by this insight, we propose ZO-FC, a simple but effective approach that applies ZO optimization to a single adapter-based PEFT module with FO optimized classifier. This design leverages the stability benefits of ZO while preserving the adaptability of FO updates with negligible memory overhead. Experiments demonstrate that ZO-FC achieves an effective balance between stability and plasticity, offering a practical and memory-efficient solution for on-device CL. --- ### More Than Memory Savings: Zeroth-Order Optimization Mitigates Forgetting in Continual Learning Authors: Wanhao Yu, Zheng Wang, Shuteng Niu, Sen Lin, Li Yang Published: 2025-10-23 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2510.21019v1 Zeroth-order (ZO) optimization has gained attention as a memory-efficient alternative to first-order (FO) methods, particularly in settings where gradient computation is expensive or even impractical. Beyond its memory efficiency, in this work, we investigate ZO optimization for continual learning (CL) as a novel approach to address the plasticity-stability-efficiency trilemma. Through theoretical analysis and empirical evidence, we show that ZO optimization naturally leads to flatter loss landscapes, which in turn reduce forgetting in CL. However, this stability comes at a cost of plasticity: due to its imprecise gradient estimates and slower convergence, ZO optimization tends to be less effective than FO in acquiring new task-specific knowledge, particularly under constrained training budgets. To better understand this trade-off, we conduct a holistic evaluation of ZO optimization applied to various existing CL methods. Our findings reveal that ZO optimization enhances stability but often undermines plasticity, particularly when used with learnable classifiers. Motivated by this insight, we propose ZO-FC, a simple but effective approach that applies ZO optimization to a single adapter-based PEFT module with FO optimized classifier. This design leverages the stability benefits of ZO while preserving the adaptability of FO updates with negligible memory overhead. Experiments demonstrate that ZO-FC achieves an effective balance between stability and plasticity, offering a practical and memory-efficient solution for on-device CL. --- ### Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference Authors: Yuhong Luo, Austin Hoag, Xintong Wang, Philip S. Thomas, Przemyslaw A. Grabowicz Published: 2025-10-23 Categories: cs.LG arXiv: https://arxiv.org/abs/2510.21017v1 Representation learning is increasingly applied to generate representations that generalize well across multiple downstream tasks. Ensuring fairness guarantees in representation learning is crucial to prevent unfairness toward specific demographic groups in downstream tasks. In this work, we formally introduce the task of learning representations that achieve high-confidence fairness. We aim to guarantee that demographic disparity in every downstream prediction remains bounded by a *user-defined* error threshold $ε$, with *controllable* high probability. To this end, we propose the ***F**air **R**epresentation learning with high-confidence **G**uarantees (FRG)* framework, which provides these high-confidence fairness guarantees by leveraging an optimized adversarial model. We empirically evaluate FRG on three real-world datasets, comparing its performance to six state-of-the-art fair representation learning methods. Our results demonstrate that FRG consistently bounds unfairness across a range of downstream models and tasks. --- ### Graph Neural Regularizers for PDE Inverse Problems Authors: William Lauga, James Rowbottom, Alexander Denker, Željko Kereta, Moshe Eliasof, Carola-Bibiane Schönlieb Published: 2025-10-23 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2510.21012v1 We present a framework for solving a broad class of ill-posed inverse problems governed by partial differential equations (PDEs), where the target coefficients of the forward operator are recovered through an iterative regularization scheme that alternates between FEM-based inversion and learned graph neural regularization. The forward problem is numerically solved using the finite element method (FEM), enabling applicability to a wide range of geometries and PDEs. By leveraging the graph structure inherent to FEM discretizations, we employ physics-inspired graph neural networks as learned regularizers, providing a robust, interpretable, and generalizable alternative to standard approaches. Numerical experiments demonstrate that our framework outperforms classical regularization techniques and achieves accurate reconstructions even in highly ill-posed scenarios. --- ### Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations Authors: Ilona van der Linden, Sahana Kumar, Arnav Dixit, Aadi Sudan, Smruthi Danda, David C. Anastasiu, Kai Lukoff Published: 2025-10-23 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2510.21011v3 As generative AI tools are increasingly used to portray people in professional roles, understanding their racial and gender representational biases is critical. We audit over 1.5 million occupational personas generated by four major large language models (GPT-4, Gemini 2.5, DeepSeek V3.1, and Mistral-medium) across 41 U.S. occupations. Comparing these personas against U.S. Bureau of Labor Statistics (BLS) data, we find that models generate demographics with less variation than real-world data, functionally compressing each occupation toward a dominant demographic profile rather than representing population-level variation. A shift/exaggeration decomposition reveals the structure of these distortions: White (-31 percentage points) and Black (-9 pp) workers are consistently underrepresented, while Hispanic (+17 pp) and Asian (+12 pp) workers are overrepresented, with stereotype exaggeration amplifying existing occupational segregation. These distortions are often extreme, including near-total portrayals of housekeepers as Hispanic and the near-erasure of Black workers from many occupations. Because these patterns recur across models with different institutional and cultural origins, they suggest shared structural sources of bias rather than model-specific artifacts. We argue that auditing generative AI requires evaluation frameworks that examine how synthetic populations systematically reshape demographic visibility across social roles. --- ### Race and Gender in LLM-Generated Personas: A Large-Scale Audit of 41 Occupations Authors: Ilona van der Linden, Sahana Kumar, Arnav Dixit, Aadi Sudan, Smruthi Danda, David C. Anastasiu, Kai Lukoff Published: 2025-10-23 Categories: cs.HC, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2510.21011v1 Generative AI tools are increasingly used to create portrayals of people in occupations, raising concerns about how race and gender are represented. We conducted a large-scale audit of over 1.5 million occupational personas across 41 U.S. occupations, generated by four large language models with different AI safety commitments and countries of origin (U.S., China, France). Compared with Bureau of Labor Statistics data, we find two recurring patterns: systematic shifts, where some groups are consistently under- or overrepresented, and stereotype exaggeration, where existing demographic skews are amplified. On average, White (--31pp) and Black (--9pp) workers are underrepresented, while Hispanic (+17pp) and Asian (+12pp) workers are overrepresented. These distortions can be extreme: for example, across all four models, Housekeepers are portrayed as nearly 100\% Hispanic, while Black workers are erased from many occupations. For HCI, these findings show provider choice materially changes who is visible, motivating model-specific audits and accountable design practices. --- ### Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs? Authors: Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras Published: 2025-10-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.21007v3 Chain-of-thought (CoT) prompting is a common technique for improving the reasoning abilities of large language models (LLMs). However, extended reasoning is often unnecessary and substantially increases token usage. As such, a key question becomes how to optimally allocate compute to when reasoning is actually needed. We study this through confidence-gated CoT, where a model produces a direct answer and a confidence estimate to decide whether to invoke CoT. We present an evaluation framework together with the first systematic study of confidence signals for this decision. We evaluate four representative confidence measures and compare them with random gating and an oracle upper bound. Experiments across two model families and diverse reasoning tasks show that existing training-free confidence measures can reduce redundant reasoning. However, we also find that the utility of individual confidence measures is inconsistent across settings. Through our evaluation framework and analysis, our study provides practical guidance toward developing and evaluating models that selectively use CoT. --- ### Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs? Authors: Samuel Lewis-Lim, Xingwei Tan, Zhixue Zhao, Nikolaos Aletras Published: 2025-10-23 Categories: cs.CL arXiv: https://arxiv.org/abs/2510.21007v2 Chain-of-thought (CoT) prompting has emerged as a common technique for enhancing the reasoning abilities of large language models (LLMs). While extended reasoning can boost accuracy on complex tasks, it is often unnecessary and substantially increases token usage, limiting the practicality of reasoning models in many scenarios. Recent models, such as GPT-OSS and Qwen3, expose controls that enable users to adjust the length of CoT or determine whether it is used at all. Yet, it remains unclear when CoT should be used: on some tasks it improves performance, while on others it provides little benefit or even harms performance. We address this challenge with confidence-gated CoT, where a model invokes reasoning only when confidence in its direct answer is low. To this end, we present the first systematic study of training-free confidence estimation methods for CoT gating. Specifically, we evaluate four training-free confidence estimation methods and compare them to a random baseline and an oracle that always knows when CoT is needed. Through extensive experiments, we show that existing training-free confidence measures can reduce redundant CoT and outperform randomly invoked CoT. However, the utility of individual confidence measures is inconsistent, varying with both the dataset and the model, underscoring the difficulty of deploying confidence-gated CoT in practice. By analysing both strengths and failure modes, our study highlights the potential and limitations of current methods and paves the way toward more reliable adaptive gating of CoT. --- ### Can Current Detectors Catch Face-to-Voice Deepfake Attacks? Authors: Nguyen Linh Bao Nguyen, Alsharif Abuadbba, Kristen Moore, Tingmin Wu Published: 2025-10-23 Categories: cs.CR, cs.LG, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2510.21004v2 The rapid advancement of generative models has enabled the creation of increasingly stealthy synthetic voices, commonly referred to as audio deepfakes. A recent technique, FOICE (USENIX'24), demonstrates a particularly alarming capability: generating a victim's voice from a single facial image, without requiring any voice sample. By exploiting correlations between facial and vocal features, FOICE produces synthetic voices realistic enough to bypass industry-standard authentication systems, including WeChat Voiceprint and Microsoft Azure. This raises serious security concerns, as facial images are far easier for adversaries to obtain than voice samples, dramatically lowering the barrier to large-scale attacks. In this work, we investigate two core research questions: (RQ1) can state-of-the-art audio deepfake detectors reliably detect FOICE-generated speech under clean and noisy conditions, and (RQ2) whether fine-tuning these detectors on FOICE data improves detection without overfitting, thereby preserving robustness to unseen voice generators such as SpeechT5. Our study makes three contributions. First, we present the first systematic evaluation of FOICE detection, showing that leading detectors consistently fail under both standard and noisy conditions. Second, we introduce targeted fine-tuning strategies that capture FOICE-specific artifacts, yielding significant accuracy improvements. Third, we assess generalization after fine-tuning, revealing trade-offs between specialization to FOICE and robustness to unseen synthesis pipelines. These findings expose fundamental weaknesses in today's defenses and motivate new architectures and training protocols for next-generation audio deepfake detection. --- ### Can Current Detectors Catch Face-to-Voice Deepfake Attacks? Authors: Nguyen Linh Bao Nguyen, Alsharif Abuadbba, Kristen Moore, Tingming Wu Published: 2025-10-23 Categories: cs.CR, cs.LG, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2510.21004v1 The rapid advancement of generative models has enabled the creation of increasingly stealthy synthetic voices, commonly referred to as audio deepfakes. A recent technique, FOICE (USENIX'24), demonstrates a particularly alarming capability: generating a victim's voice from a single facial image, without requiring any voice sample. By exploiting correlations between facial and vocal features, FOICE produces synthetic voices realistic enough to bypass industry-standard authentication systems, including WeChat Voiceprint and Microsoft Azure. This raises serious security concerns, as facial images are far easier for adversaries to obtain than voice samples, dramatically lowering the barrier to large-scale attacks. In this work, we investigate two core research questions: (RQ1) can state-of-the-art audio deepfake detectors reliably detect FOICE-generated speech under clean and noisy conditions, and (RQ2) whether fine-tuning these detectors on FOICE data improves detection without overfitting, thereby preserving robustness to unseen voice generators such as SpeechT5. Our study makes three contributions. First, we present the first systematic evaluation of FOICE detection, showing that leading detectors consistently fail under both standard and noisy conditions. Second, we introduce targeted fine-tuning strategies that capture FOICE-specific artifacts, yielding significant accuracy improvements. Third, we assess generalization after fine-tuning, revealing trade-offs between specialization to FOICE and robustness to unseen synthesis pipelines. These findings expose fundamental weaknesses in today's defenses and motivate new architectures and training protocols for next-generation audio deepfake detection. ---