# Research Papers — 2025-11 · bundle page 115 of 197 > Full-text markdown of papers #5701–5750 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/115 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/114.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/116.md) ### ERMoE: Eigen-Reparameterized Mixture-of-Experts for Stable Routing and Interpretable Specialization Authors: Anzhe Cheng, Shukai Duan, Shixuan Li, Chenzhong Yin, Mingxi Cheng, Heng Ping, Tamoghna Chattopadhyay, Sophia I Thomopoulos, Shahin Nazarian, Paul Thompson, Paul Bogdan Published: 2025-11-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10971v2 Mixture-of-Experts (MoE) architectures expand model capacity by sparsely activating experts but face two core challenges: misalignment between router logits and each expert's internal structure leads to unstable routing and expert underutilization, and load imbalances create straggler bottlenecks. Standard solutions, such as auxiliary load-balancing losses, can reduce load disparities but often weaken expert specialization and hurt downstream performance. To address these issues, we propose ERMoE, a sparse MoE transformer that reparameterizes each expert in a learned orthonormal eigenbasis and replaces learned gating logits with an "Eigenbasis Score", defined as the cosine similarity between input features and an expert's basis. This content-aware routing ties token assignments directly to experts' representation spaces, stabilizing utilization and promoting interpretable specialization without sacrificing sparsity. Crucially, ERMoE removes the need for explicit balancing losses and avoids the interfering gradients they introduce. We show that ERMoE achieves state-of-the-art accuracy on ImageNet classification and cross-modal image-text retrieval benchmarks (e.g., COCO, Flickr30K), while naturally producing flatter expert load distributions. Moreover, a 3D MRI variant (ERMoE-ba) improves brain age prediction accuracy by more than 7\% and yields anatomically interpretable expert specializations. ERMoE thus introduces a new architectural principle for sparse expert models that directly addresses routing instabilities and enables improved performance with scalable, interpretable specialization. --- ### How Data Quality Affects Machine Learning Models for Credit Risk Assessment Authors: Andrea Maurino Published: 2025-11-14 Categories: cs.LG, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2511.10964v1 Machine Learning (ML) models are being increasingly employed for credit risk evaluation, with their effectiveness largely hinging on the quality of the input data. In this paper we investigate the impact of several data quality issues, including missing values, noisy attributes, outliers, and label errors, on the predictive accuracy of the machine learning model used in credit risk assessment. Utilizing an open-source dataset, we introduce controlled data corruption using the Pucktrick library to assess the robustness of 10 frequently used models like Random Forest, SVM, and Logistic Regression and so on. Our experiments show significant differences in model robustness based on the nature and severity of the data degradation. Moreover, the proposed methodology and accompanying tools offer practical support for practitioners seeking to enhance data pipeline robustness, and provide researchers with a flexible framework for further experimentation in data-centric AI contexts. --- ### Text-guided Weakly Supervised Framework for Dynamic Facial Expression Recognition Authors: Gunho Jung, Heejo Kong, Seong-Whan Lee Published: 2025-11-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.10958v1 Dynamic facial expression recognition (DFER) aims to identify emotional states by modeling the temporal changes in facial movements across video sequences. A key challenge in DFER is the many-to-one labeling problem, where a video composed of numerous frames is assigned a single emotion label. A common strategy to mitigate this issue is to formulate DFER as a Multiple Instance Learning (MIL) problem. However, MIL-based approaches inherently suffer from the visual diversity of emotional expressions and the complexity of temporal dynamics. To address this challenge, we propose TG-DFER, a text-guided weakly supervised framework that enhances MIL-based DFER by incorporating semantic guidance and coherent temporal modeling. We incorporate a vision-language pre-trained (VLP) model is integrated to provide semantic guidance through fine-grained textual descriptions of emotional context. Furthermore, we introduce visual prompts, which align enriched textual emotion labels with visual instance features, enabling fine-grained reasoning and frame-level relevance estimation. In addition, a multi-grained temporal network is designed to jointly capture short-term facial dynamics and long-range emotional flow, ensuring coherent affective understanding across time. Extensive results demonstrate that TG-DFER achieves improved generalization, interpretability, and temporal sensitivity under weak supervision. --- ### Language-Guided Graph Representation Learning for Video Summarization Authors: Wenrui Li, Wei Han, Hengyu Man, Wangmeng Zuo, Xiaopeng Fan, Yonghong Tian Published: 2025-11-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10953v1 With the rapid growth of video content on social media, video summarization has become a crucial task in multimedia processing. However, existing methods face challenges in capturing global dependencies in video content and accommodating multimodal user customization. Moreover, temporal proximity between video frames does not always correspond to semantic proximity. To tackle these challenges, we propose a novel Language-guided Graph Representation Learning Network (LGRLN) for video summarization. Specifically, we introduce a video graph generator that converts video frames into a structured graph to preserve temporal order and contextual dependencies. By constructing forward, backward and undirected graphs, the video graph generator effectively preserves the sequentiality and contextual relationships of video content. We designed an intra-graph relational reasoning module with a dual-threshold graph convolution mechanism, which distinguishes semantically relevant frames from irrelevant ones between nodes. Additionally, our proposed language-guided cross-modal embedding module generates video summaries with specific textual descriptions. We model the summary generation output as a mixture of Bernoulli distribution and solve it with the EM algorithm. Experimental results show that our method outperforms existing approaches across multiple benchmarks. Moreover, we proposed LGRLN reduces inference time and model parameters by 87.8% and 91.7%, respectively. Our codes and pre-trained models are available at https://github.com/liwrui/LGRLN. --- ### Requirements for Aligned, Dynamic Resolution of Conflicts in Operational Constraints Authors: Steven J. Jones, Robert E. Wray, John E. Laird Published: 2025-11-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.10952v2 Deployed, autonomous AI systems must often evaluate multiple plausible courses of action (extended sequences of behavior) in novel or under-specified contexts. Despite extensive training, these systems will inevitably encounter scenarios where no available course of action fully satisfies all operational constraints (e.g., operating procedures, rules, laws, norms, and goals). To achieve goals in accordance with human expectations and values, agents must go beyond their trained policies and instead construct, evaluate, and justify candidate courses of action. These processes require contextual "knowledge" that may lie outside prior (policy) training. This paper characterizes requirements for agent decision making in these contexts. It also identifies the types of knowledge agents require to make decisions robust to agent goals and aligned with human expectations. Drawing on both analysis and empirical case studies, we examine how agents need to integrate normative, pragmatic, and situational understanding to select and then to pursue more aligned courses of action in complex, real-world environments. --- ### Exposing Weak Links in Multi-Agent Systems under Adversarial Prompting Authors: Nirmit Arora, Sathvik Joel, Ishan Kavathekar, Palak, Rohan Gandhi, Yash Pandya, Tanuja Ganu, Aditya Kanade, Akshay Nambi Published: 2025-11-14 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2511.10949v1 LLM-based agents are increasingly deployed in multi-agent systems (MAS). As these systems move toward real-world applications, their security becomes paramount. Existing research largely evaluates single-agent security, leaving a critical gap in understanding the vulnerabilities introduced by multi-agent design. However, existing systems fall short due to lack of unified frameworks and metrics focusing on unique rejection modes in MAS. We present SafeAgents, a unified and extensible framework for fine-grained security assessment of MAS. SafeAgents systematically exposes how design choices such as plan construction strategies, inter-agent context sharing, and fallback behaviors affect susceptibility to adversarial prompting. We introduce Dharma, a diagnostic measure that helps identify weak links within multi-agent pipelines. Using SafeAgents, we conduct a comprehensive study across five widely adopted multi-agent architectures (centralized, decentralized, and hybrid variants) on four datasets spanning web tasks, tool use, and code generation. Our findings reveal that common design patterns carry significant vulnerabilities. For example, centralized systems that delegate only atomic instructions to sub-agents obscure harmful objectives, reducing robustness. Our results highlight the need for security-aware design in MAS. Link to code is https://github.com/microsoft/SafeAgents --- ### DEFT-LLM: Disentangled Expert Feature Tuning for Micro-Expression Recognition Authors: Ren Zhang, Huilai Li, Chao qi, Guoliang Xu, Tianyu Zhou, Wei wei, Jianqin Yin Published: 2025-11-14 Categories: cs.CV, cs.HC arXiv: https://arxiv.org/abs/2511.10948v1 Micro expression recognition (MER) is crucial for inferring genuine emotion. Applying a multimodal large language model (MLLM) to this task enables spatio-temporal analysis of facial motion and provides interpretable descriptions. However, there are still two core challenges: (1) The entanglement of static appearance and dynamic motion cues prevents the model from focusing on subtle motion; (2) Textual labels in existing MER datasets do not fully correspond to underlying facial muscle movements, creating a semantic gap between text supervision and physical motion. To address these issues, we propose DEFT-LLM, which achieves motion semantic alignment by multi-expert disentanglement. We first introduce Uni-MER, a motion-driven instruction dataset designed to align text with local facial motion. Its construction leverages dual constraints from optical flow and Action Unit (AU) labels to ensure spatio-temporal consistency and reasonable correspondence to the movements. We then design an architecture with three experts to decouple facial dynamics into independent and interpretable representations (structure, dynamic textures, and motion-semantics). By integrating the instruction-aligned knowledge from Uni-MER into DEFT-LLM, our method injects effective physical priors for micro expressions while also leveraging the cross modal reasoning ability of large language models, thus enabling precise capture of subtle emotional cues. Experiments on multiple challenging MER benchmarks demonstrate state-of-the-art performance, as well as a particular advantage in interpretable modeling of local facial motion. --- ### Abstract 3D Perception for Spatial Intelligence in Vision-Language Models Authors: Yifan Liu, Fangneng Zhan, Kaichen Zhou, Yilun Du, Paul Pu Liang, Hanspeter Pfister Published: 2025-11-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10946v3 Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding, which are crucial for real-world applications like robotics and embodied agents. We attribute this to a modality gap between the 3D tasks and the 2D training of VLM, which led to inefficient retrieval of 3D information from 2D input. To bridge this gap, we introduce SandboxVLM, a simple yet effective framework that leverages abstract bounding boxes to encode geometric structure and physical kinematics for VLM. Specifically, we design a 3D Sandbox reconstruction and perception pipeline comprising four stages: generating multi-view priors with abstract control, proxy elevation, multi-view voting and clustering, and 3D-aware reasoning. Evaluated in zero-shot settings across multiple benchmarks and VLM backbones, our approach consistently improves spatial intelligence, achieving an 8.3\% gain on SAT Real compared with baseline methods for instance. These results demonstrate that equipping VLMs with a 3D abstraction substantially enhances their 3D reasoning ability without additional training, suggesting new possibilities for general-purpose embodied intelligence. --- ### Divide, Conquer and Unite: Hierarchical Style-Recalibrated Prototype Alignment for Federated Medical Segmentation Authors: Xingyue Zhao, Wenke Huang, Xingguang Wang, Haoyu Zhao, Linghao Zhuang, Anwen Jiang, Guancheng Wan, Mang Ye Published: 2025-11-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10945v2 Federated learning enables multiple medical institutions to train a global model without sharing data, yet feature heterogeneity from diverse scanners or protocols remains a major challenge. Many existing works attempt to address this issue by leveraging model representations (e.g., mean feature vectors) to correct local training; however, they often face two key limitations: 1) Incomplete Contextual Representation Learning: Current approaches primarily focus on final-layer features, overlooking critical multi-level cues and thus diluting essential context for accurate segmentation. 2) Layerwise Style Bias Accumulation: Although utilizing representations can partially align global features, these methods neglect domain-specific biases within intermediate layers, allowing style discrepancies to build up and reduce model robustness. To address these challenges, we propose FedBCS to bridge feature representation gaps via domain-invariant contextual prototypes alignment. Specifically, we introduce a frequency-domain adaptive style recalibration into prototype construction that not only decouples content-style representations but also learns optimal style parameters, enabling more robust domain-invariant prototypes. Furthermore, we design a context-aware dual-level prototype alignment method that extracts domain-invariant prototypes from different layers of both encoder and decoder and fuses them with contextual information for finer-grained representation alignment. Extensive experiments on two public datasets demonstrate that our method exhibits remarkable performance. --- ### From Parameter to Representation: A Closed-Form Approach for Controllable Model Merging Authors: Jialin Wu, Jian Yang, Handing Wang, Jiajun Wen, Zhiyong Yu Published: 2025-11-14 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.10943v1 Model merging combines expert models for multitask performance but faces challenges from parameter interference. This has sparked recent interest in controllable model merging, giving users the ability to explicitly balance performance trade-offs. Existing approaches employ a compile-then-query paradigm, performing a costly offline multi-objective optimization to enable fast, preference-aware model generation. This offline stage typically involves iterative search or dedicated training, with complexity that grows exponentially with the number of tasks. To overcome these limitations, we shift the perspective from parameter-space optimization to a direct correction of the model's final representation. Our approach models this correction as an optimal linear transformation, yielding a closed-form solution that replaces the entire offline optimization process with a single-step, architecture-agnostic computation. This solution directly incorporates user preferences, allowing a Pareto-optimal model to be generated on-the-fly with complexity that scales linearly with the number of tasks. Experimental results show our method generates a superior Pareto front with more precise preference alignment and drastically reduced computational cost. --- ### Heterogeneous Complementary Distillation Authors: Liuchi Xu, Hao Zheng, Lu Wang, Lisheng Xu, Jun Cheng Published: 2025-11-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10942v2 Knowledge distillation (KD)transfers the dark knowledge from a complex teacher to a compact student. However, heterogeneous architecture distillation, such as Vision Transformer (ViT) to ResNet18, faces challenges due to differences in spatial feature representations.Traditional KD methods are mostly designed for homogeneous architectures and hence struggle to effectively address the disparity. Although heterogeneous KD approaches have been developed recently to solve these issues, they often incur high computational costs and complex designs, or overly rely on logit alignment, which limits their ability to leverage the complementary features. To overcome these limitations, we propose Heterogeneous Complementary Distillation (HCD),a simple yet effective framework that integrates complementary teacher and student features to align representations in shared logits.These logits are decomposed and constrained to facilitate diverse knowledge transfer to the student. Specifically, HCD processes the student's intermediate features through convolutional projector and adaptive pooling, concatenates them with teacher's feature from the penultimate layer and then maps them via the Complementary Feature Mapper (CFM) module, comprising fully connected layer,to produce shared logits.We further introduce Sub-logit Decoupled Distillation (SDD) that partitions the shared logits into n sub-logits, which are fused with teacher's logits to rectify classification.To ensure sub-logit diversity and reduce redundant knowledge transfer, we propose an Orthogonality Loss (OL).By preserving student-specific strengths and leveraging teacher knowledge,HCD enhances robustness and generalization in students.Extensive experiments on the CIFAR-100, Fine-grained (e.g., CUB200)and ImageNet-1K datasets demonstrate that HCD outperforms state-of-the-art KD methods,establishing it as an effective solution for heterogeneous KD. --- ### Flow matching-based generative models for MIMO channel estimation Authors: Wenkai Liu, Nan Ma, Jianqiao Chen, Xiaoxuan Qi, Yuhang Ma Published: 2025-11-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.10941v1 Diffusion model (DM)-based channel estimation, which generates channel samples via a posteriori sampling stepwise with denoising process, has shown potential in high-precision channel state information (CSI) acquisition. However, slow sampling speed is an essential challenge for recent developed DM-based schemes. To alleviate this problem, we propose a novel flow matching (FM)-based generative model for multiple-input multiple-output (MIMO) channel estimation. We first formulate the channel estimation problem within FM framework, where the conditional probability path is constructed from the noisy channel distribution to the true channel distribution. In this case, the path evolves along the straight-line trajectory at a constant speed. Then, guided by this, we derive the velocity field that depends solely on the noise statistics to guide generative models training. Furthermore, during the sampling phase, we utilize the trained velocity field as prior information for channel estimation, which allows for quick and reliable noise channel enhancement via ordinary differential equation (ODE) Euler solver. Finally, numerical results demonstrate that the proposed FM-based channel estimation scheme can significantly reduce the sampling overhead compared to other popular DM-based schemes, such as the score matching (SM)-based scheme. Meanwhile, it achieves superior channel estimation accuracy under different channel conditions. --- ### Facial Expression Recognition with YOLOv11 and YOLOv12: A Comparative Study Authors: Umma Aymon, Nur Shazwani Kamarudin, Ahmad Fakhri Ab. Nasir Published: 2025-11-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10940v1 Facial Expression Recognition remains a challenging task, especially in unconstrained, real-world environments. This study investigates the performance of two lightweight models, YOLOv11n and YOLOv12n, which are the nano variants of the latest official YOLO series, within a unified detection and classification framework for FER. Two benchmark classification datasets, FER2013 and KDEF, are converted into object detection format and model performance is evaluated using mAP 0.5, precision, recall, and confusion matrices. Results show that YOLOv12n achieves the highest overall performance on the clean KDEF dataset with a mAP 0.5 of 95.6, and also outperforms YOLOv11n on the FER2013 dataset in terms of mAP 63.8, reflecting stronger sensitivity to varied expressions. In contrast, YOLOv11n demonstrates higher precision 65.2 on FER2013, indicating fewer false positives and better reliability in noisy, real-world conditions. On FER2013, both models show more confusion between visually similar expressions, while clearer class separation is observed on the cleaner KDEF dataset. These findings underscore the trade-off between sensitivity and precision, illustrating how lightweight YOLO models can effectively balance performance and efficiency. The results demonstrate adaptability across both controlled and real-world conditions, establishing these models as strong candidates for real-time, resource-constrained emotion-aware AI applications. --- ### Cascading Bandits With Feedback Authors: R Sri Prakash, Nikhil Karamchandani, Sharayu Moharir Published: 2025-11-14 Categories: cs.LG, cs.DC arXiv: https://arxiv.org/abs/2511.10938v2 Motivated by the challenges of edge inference, we study a variant of the cascade bandit model in which each arm corresponds to an inference model with an associated accuracy and error probability. We analyse four decision-making policies-Explore-then-Commit, Action Elimination, Lower Confidence Bound (LCB), and Thompson Sampling-and provide sharp theoretical regret guarantees for each. Unlike in classical bandit settings, Explore-then-Commit and Action Elimination incur suboptimal regret because they commit to a fixed ordering after the exploration phase, limiting their ability to adapt. In contrast, LCB and Thompson Sampling continuously update their decisions based on observed feedback, achieving constant O(1) regret. Simulations corroborate these theoretical findings, highlighting the crucial role of adaptivity for efficient edge inference under uncertainty. --- ### GraphToxin: Reconstructing Full Unlearned Graphs from Graph Unlearning Authors: Ying Song, Balaji Palanisamy Published: 2025-11-14 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2511.10936v3 Graph unlearning (GU) has emerged as a promising solution to comply with "the right to be forgotten" regulations by enabling the removal of sensitive information upon request. However, this solution is not foolproof. The involvement of multiple parties creates new attack surfaces, and residual traces of deleted data can persist within the unlearned graph neural networks (GNNs). These vulnerabilities can be exploited by attackers to recover the supposedly erased samples, undermining the intended functionality of GU. In this work, we propose GraphToxin, the first full graph reconstruction attack against GU. We show that GraphToxin can recover not only a deleted individual's information and personal links but also sensitive content of their neighbors, thereby posing substantially more detrimental threats than prior membership inference attacks (MIAs). Specifically, we introduce a novel curvature matching module to provide fine-grained guidance for full unlearned graph recovery. We further extend GraphToxin to multiple-node removal under both white-box and black-box settings, showcasing its practical feasibility and potential to cause considerable harm. We highlight the necessity of worst-case analysis and propose a systematic evaluation framework to assess attack performance under both random and worst-case node removal scenarios. Our extensive experiments demonstrate the effectiveness and flexibility of GraphToxin. Notably, current defense mechanisms are largely ineffective against this attack. Additionally, our findings reveal that existing GU verification standards based on MIAs can be misleading: they achieve membership-level protection, while the full unlearned graph remains recoverable through GraphToxin. --- ### CAT-Net: A Cross-Attention Tone Network for Cross-Subject EEG-EMG Fusion Tone Decoding Authors: Yifan Zhuang, Calvin Huang, Zepeng Yu, Yongjie Zou, Jiawei Ju Published: 2025-11-14 Categories: cs.SD, cs.LG, q-bio.NC arXiv: https://arxiv.org/abs/2511.10935v1 Brain-computer interface (BCI) speech decoding has emerged as a promising tool for assisting individuals with speech impairments. In this context, the integration of electroencephalography (EEG) and electromyography (EMG) signals offers strong potential for enhancing decoding performance. Mandarin tone classification presents particular challenges, as tonal variations convey distinct meanings even when phonemes remain identical. In this study, we propose a novel cross-subject multimodal BCI decoding framework that fuses EEG and EMG signals to classify four Mandarin tones under both audible and silent speech conditions. Inspired by the cooperative mechanisms of neural and muscular systems in speech production, our neural decoding architecture combines spatial-temporal feature extraction branches with a cross-attention fusion mechanism, enabling informative interaction between modalities. We further incorporate domain-adversarial training to improve cross-subject generalization. We collected 4,800 EEG trials and 4,800 EMG trials from 10 participants using only twenty EEG and five EMG channels, demonstrating the feasibility of minimal-channel decoding. Despite employing lightweight modules, our model outperforms state-of-the-art baselines across all conditions, achieving average classification accuracies of 87.83% for audible speech and 88.08% for silent speech. In cross-subject evaluations, it still maintains strong performance with accuracies of 83.27% and 85.10% for audible and silent speech, respectively. We further conduct ablation studies to validate the effectiveness of each component. Our findings suggest that tone-level decoding with minimal EEG-EMG channels is feasible and potentially generalizable across subjects, contributing to the development of practical BCI applications. --- ### CardioEmbed: Domain-Specialized Text Embeddings for Clinical Cardiology Authors: Richard J. Young, Alice M. Matthews Published: 2025-11-14 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.10930v1 Biomedical text embeddings have primarily been developed using research literature from PubMed, yet clinical cardiology practice relies heavily on procedural knowledge and specialized terminology found in comprehensive textbooks rather than research abstracts. This research practice gap limits the effectiveness of existing embedding models for clinical applications incardiology. This study trained CardioEmbed, a domain-specialized embedding model based on Qwen3-Embedding-8B, using contrastive learning on a curated corpus of seven comprehensive cardiology textbooks totaling approximately 150,000 sentences after deduplication. The model employs InfoNCE loss with in-batch negatives and achieves 99.60% retrieval accuracy on cardiac-specific semantic retrieval tasks, a +15.94 percentage point improvement over MedTE, the current state-of-the-art medical embedding model. On MTEB medical benchmarks, the model obtained BIOSSES 0.77 Spearman and SciFact 0.61 NDCG@10, indicating competitive performance on related biomedical domains. Domain-specialized training on comprehensive clinical textbooks yields near-perfect cardiology retrieval (99.60% Acc@1), improving over MedTE by +15.94 percentage points. --- ### Multi-Agent Legal Verifier Systems for Data Transfer Planning Authors: Ha-Thanh Nguyen, Wachara Fungwacharakorn, Ken Satoh Published: 2025-11-14 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.10925v1 Legal compliance in AI-driven data transfer planning is becoming increasingly critical under stringent privacy regulations such as the Japanese Act on the Protection of Personal Information (APPI). We propose a multi-agent legal verifier that decomposes compliance checking into specialized agents for statutory interpretation, business context evaluation, and risk assessment, coordinated through a structured synthesis protocol. Evaluated on a stratified dataset of 200 Amended APPI Article 16 cases with clearly defined ground truth labels and multiple performance metrics, the system achieves 72% accuracy, which is 21 percentage points higher than a single-agent baseline, including 90% accuracy on clear compliance cases (vs. 16% for the baseline) while maintaining perfect detection of clear violations. While challenges remain in ambiguous scenarios, these results show that domain specialization and coordinated reasoning can meaningfully improve legal AI performance, providing a scalable and regulation-aware framework for trustworthy and interpretable automated compliance verification. --- ### Out-of-Distribution Detection with Positive and Negative Prompt Supervision Using Large Language Models Authors: Zhixia He, Chen Zhao, Minglai Shao, Xintao Wu, Xujiang Zhao, Dong Li, Qin Tian, Linlin Yu Published: 2025-11-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10923v1 Out-of-distribution (OOD) detection is committed to delineating the classification boundaries between in-distribution (ID) and OOD images. Recent advances in vision-language models (VLMs) have demonstrated remarkable OOD detection performance by integrating both visual and textual modalities. In this context, negative prompts are introduced to emphasize the dissimilarity between image features and prompt content. However, these prompts often include a broad range of non-ID features, which may result in suboptimal outcomes due to the capture of overlapping or misleading information. To address this issue, we propose Positive and Negative Prompt Supervision, which encourages negative prompts to capture inter-class features and transfers this semantic knowledge to the visual modality to enhance OOD detection performance. Our method begins with class-specific positive and negative prompts initialized by large language models (LLMs). These prompts are subsequently optimized, with positive prompts focusing on features within each class, while negative prompts highlight features around category boundaries. Additionally, a graph-based architecture is employed to aggregate semantic-aware supervision from the optimized prompt representations and propagate it to the visual branch, thereby enhancing the performance of the energy-based OOD detector. Extensive experiments on two benchmarks, CIFAR-100 and ImageNet-1K, across eight OOD datasets and five different LLMs, demonstrate that our method outperforms state-of-the-art baselines. --- ### Heterogeneous Multisource Transfer Learning via Model Averaging for Positive-Unlabeled Data Authors: Jialei Liu, Jun Liao, Kuangnan Fang Published: 2025-11-14 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.10919v1 Positive-Unlabeled (PU) learning presents unique challenges due to the lack of explicitly labeled negative samples, particularly in high-stakes domains such as fraud detection and medical diagnosis. To address data scarcity and privacy constraints, we propose a novel transfer learning with model averaging framework that integrates information from heterogeneous data sources - including fully binary labeled, semi-supervised, and PU data sets - without direct data sharing. For each source domain type, a tailored logistic regression model is conducted, and knowledge is transferred to the PU target domain through model averaging. Optimal weights for combining source models are determined via a cross-validation criterion that minimizes the Kullback-Leibler divergence. We establish theoretical guarantees for weight optimality and convergence, covering both misspecified and correctly specified target models, with further extensions to high-dimensional settings using sparsity-penalized estimators. Extensive simulations and real-world credit risk data analyses demonstrate that our method outperforms other comparative methods in terms of predictive accuracy and robustness, especially under limited labeled data and heterogeneous environments. --- ### Towards Federated Clustering: A Client-wise Private Graph Aggregation Framework Authors: Guanxiong He, Jie Wang, Liaoyuan Tang, Zheng Wang, Rong Wang, Feiping Nie Published: 2025-11-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.10915v1 Federated clustering addresses the critical challenge of extracting patterns from decentralized, unlabeled data. However, it is hampered by the flaw that current approaches are forced to accept a compromise between performance and privacy: \textit{transmitting embedding representations risks sensitive data leakage, while sharing only abstract cluster prototypes leads to diminished model accuracy}. To resolve this dilemma, we propose Structural Privacy-Preserving Federated Graph Clustering (SPP-FGC), a novel algorithm that innovatively leverages local structural graphs as the primary medium for privacy-preserving knowledge sharing, thus moving beyond the limitations of conventional techniques. Our framework operates on a clear client-server logic; on the client-side, each participant constructs a private structural graph that captures intrinsic data relationships, which the server then securely aggregates and aligns to form a comprehensive global graph from which a unified clustering structure is derived. The framework offers two distinct modes to suit different needs. SPP-FGC is designed as an efficient one-shot method that completes its task in a single communication round, ideal for rapid analysis. For more complex, unstructured data like images, SPP-FGC+ employs an iterative process where clients and the server collaboratively refine feature representations to achieve superior downstream performance. Extensive experiments demonstrate that our framework achieves state-of-the-art performance, improving clustering accuracy by up to 10\% (NMI) over federated baselines while maintaining provable privacy guarantees. --- ### PhaseWin Search Framework Enable Efficient Object-Level Interpretation Authors: Zihan Gu, Ruoyu Chen, Junchi Zhang, Yue Hu, Hua Zhang, Xiaochun Cao Published: 2025-11-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10914v1 Attribution is essential for interpreting object-level foundation models. Recent methods based on submodular subset selection have achieved high faithfulness, but their efficiency limitations hinder practical deployment in real-world scenarios. To address this, we propose PhaseWin, a novel phase-window search algorithm that enables faithful region attribution with near-linear complexity. PhaseWin replaces traditional quadratic-cost greedy selection with a phased coarse-to-fine search, combining adaptive pruning, windowed fine-grained selection, and dynamic supervision mechanisms to closely approximate greedy behavior while dramatically reducing model evaluations. Theoretically, PhaseWin retains near-greedy approximation guarantees under mild monotone submodular assumptions. Empirically, PhaseWin achieves over 95% of greedy attribution faithfulness using only 20% of the computational budget, and consistently outperforms other attribution baselines across object detection and visual grounding tasks with Grounding DINO and Florence-2. PhaseWin establishes a new state of the art in scalable, high-faithfulness attribution for object-level multimodal models. --- ### Synthetic Voices, Real Threats: Evaluating Large Text-to-Speech Models in Generating Harmful Audio Authors: Guangke Chen, Yuhui Wang, Shouling Ji, Xiapu Luo, Ting Wang Published: 2025-11-14 Categories: cs.SD, cs.AI, cs.CR, cs.MM, eess.AS arXiv: https://arxiv.org/abs/2511.10913v1 Modern text-to-speech (TTS) systems, particularly those built on Large Audio-Language Models (LALMs), generate high-fidelity speech that faithfully reproduces input text and mimics specified speaker identities. While prior misuse studies have focused on speaker impersonation, this work explores a distinct content-centric threat: exploiting TTS systems to produce speech containing harmful content. Realizing such threats poses two core challenges: (1) LALM safety alignment frequently rejects harmful prompts, yet existing jailbreak attacks are ill-suited for TTS because these systems are designed to faithfully vocalize any input text, and (2) real-world deployment pipelines often employ input/output filters that block harmful text and audio. We present HARMGEN, a suite of five attacks organized into two families that address these challenges. The first family employs semantic obfuscation techniques (Concat, Shuffle) that conceal harmful content within text. The second leverages audio-modality exploits (Read, Spell, Phoneme) that inject harmful content through auxiliary audio channels while maintaining benign textual prompts. Through evaluation across five commercial LALMs-based TTS systems and three datasets spanning two languages, we demonstrate that our attacks substantially reduce refusal rates and increase the toxicity of generated speech. We further assess both reactive countermeasures deployed by audio-streaming platforms and proactive defenses implemented by TTS providers. Our analysis reveals critical vulnerabilities: deepfake detectors underperform on high-fidelity audio; reactive moderation can be circumvented by adversarial perturbations; while proactive moderation detects 57-93% of attacks. Our work highlights a previously underexplored content-centric misuse vector for TTS and underscore the need for robust cross-modal safeguards throughout training and deployment. --- ### Evaluating Large Language Models on Rare Disease Diagnosis: A Case Study using House M.D Authors: Arsh Gupta, Ajay Narayanan Sridhar, Bonam Mingole, Amulya Yadav Published: 2025-11-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.10912v1 Large language models (LLMs) have demonstrated capabilities across diverse domains, yet their performance on rare disease diagnosis from narrative medical cases remains underexplored. We introduce a novel dataset of 176 symptom-diagnosis pairs extracted from House M.D., a medical television series validated for teaching rare disease recognition in medical education. We evaluate four state-of-the-art LLMs such as GPT 4o mini, GPT 5 mini, Gemini 2.5 Flash, and Gemini 2.5 Pro on narrative-based diagnostic reasoning tasks. Results show significant variation in performance, ranging from 16.48% to 38.64% accuracy, with newer model generations demonstrating a 2.3 times improvement. While all models face substantial challenges with rare disease diagnosis, the observed improvement across architectures suggests promising directions for future development. Our educationally validated benchmark establishes baseline performance metrics for narrative medical reasoning and provides a publicly accessible evaluation framework for advancing AI-assisted diagnosis research. --- ### Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy Authors: Peichen Xie, Shuotao Xu, Yang Wang, Fan Yang, Mao Yang Published: 2025-11-14 Categories: cs.AR, cs.LG, math.NA arXiv: https://arxiv.org/abs/2511.10909v3 Modern AI accelerators rely on matrix multiply-accumulate units (MMAUs), such as NVIDIA Tensor Cores and AMD Matrix Cores, to accelerate deep neural network workloads. MMAUs expose only instruction-level or API-level interfaces of matrix multiply-accumulate (MMA) operations, while leaving internal floating-point arithmetic behavior undocumented. Consequently, MMAUs across vendors and architectural generations often produce numerical discrepancies for identical inputs, and sometimes exhibit reduced numerical accuracy that can cause training instability. Diagnosing and understanding the root causes of these effects is challenging without white-box models of their arithmetic behavior. This paper proposes closed-loop feature probing (CLFP), a generic and systematic framework for constructing bit-accurate arithmetic behavior models of MMA operations. Based on this framework, we analyze all MMA instructions on ten GPU architectures spanning NVIDIA Volta through RTX Blackwell and AMD CDNA1 through CDNA3, and derive the first bit-accurate arithmetic models for these MMAUs. Our models explain previously observed cross-platform numerical discrepancies and accuracy issues, enable white-box numerical error analysis, reveal four types of precision bottlenecks and one type of numerical asymmetry, and inform software workarounds as well as design suggestions for future MMAUs. This work is open-source at https://github.com/microsoft/MMA-Sim --- ### YOLO-Drone: An Efficient Object Detection Approach Using the GhostHead Network for Drone Images Authors: Hyun-Ki Jung Published: 2025-11-14 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.10905v1 Object detection using images or videos captured by drones is a promising technology with significant potential across various industries. However, a major challenge is that drone images are typically taken from high altitudes, making object identification difficult. This paper proposes an effective solution to address this issue. The base model used in the experiments is YOLOv11, the latest object detection model, with a specific implementation based on YOLOv11n. The experimental data were sourced from the widely used and reliable VisDrone dataset, a standard benchmark in drone-based object detection. This paper introduces an enhancement to the Head network of the YOLOv11 algorithm, called the GhostHead Network. The model incorporating this improvement is named YOLO-Drone. Experimental results demonstrate that YOLO-Drone achieves significant improvements in key detection accuracy metrics, including Precision, Recall, F1-Score, and mAP (0.5), compared to the original YOLOv11. Specifically, the proposed model recorded a 0.4% increase in Precision, a 0.6% increase in Recall, a 0.5% increase in F1-Score, and a 0.5% increase in mAP (0.5). Additionally, the Inference Speed metric, which measures image processing speed, also showed a notable improvement. These results indicate that YOLO-Drone is a high-performance model with enhanced accuracy and speed compared to YOLOv11. To further validate its reliability, comparative experiments were conducted against other high-performance object detection models, including YOLOv8, YOLOv9, and YOLOv10. The results confirmed that the proposed model outperformed YOLOv8 by 0.1% in mAP (0.5) and surpassed YOLOv9 and YOLOv10 by 0.3% and 0.6%, respectively. --- ### Automated Analysis of Learning Outcomes and Exam Questions Based on Bloom's Taxonomy Authors: Ramya Kumar, Dhruv Gulwani, Sonit Singh Published: 2025-11-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.10903v1 This paper explores the automatic classification of exam questions and learning outcomes according to Bloom's Taxonomy. A small dataset of 600 sentences labeled with six cognitive categories - Knowledge, Comprehension, Application, Analysis, Synthesis, and Evaluation - was processed using traditional machine learning (ML) models (Naive Bayes, Logistic Regression, Support Vector Machines), recurrent neural network architectures (LSTM, BiLSTM, GRU, BiGRU), transformer-based models (BERT and RoBERTa), and large language models (OpenAI, Gemini, Ollama, Anthropic). Each model was evaluated under different preprocessing and augmentation strategies (for example, synonym replacement, word embeddings, etc.). Among traditional ML approaches, Support Vector Machines (SVM) with data augmentation achieved the best overall performance, reaching 94 percent accuracy, recall, and F1 scores with minimal overfitting. In contrast, the RNN models and BERT suffered from severe overfitting, while RoBERTa initially overcame it but began to show signs as training progressed. Finally, zero-shot evaluations of large language models (LLMs) indicated that OpenAI and Gemini performed best among the tested LLMs, achieving approximately 0.72-0.73 accuracy and comparable F1 scores. These findings highlight the challenges of training complex deep models on limited data and underscore the value of careful data augmentation and simpler algorithms (such as augmented SVM) for Bloom's Taxonomy classification. --- ### Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions Authors: Mengze Hong, Di Jiang, Weiwei Zhao, Yawen Li, Yihang Wang, Xinyuan Luo, Yanjie Sun, Chen Jason Zhang Published: 2025-11-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.10902v2 While large language models (LLMs) offer promising capabilities for automating academic workflows, existing systems for academic peer review remain constrained by text-only inputs, limited contextual grounding, and a lack of actionable feedback. In this work, we present an interactive web-based system for multimodal, community-aware peer review simulation to enable effective manuscript revisions before paper submission. Our framework integrates textual and visual information through multimodal LLMs, enhances review quality via retrieval-augmented generation (RAG) grounded in web-scale OpenReview data, and converts generated reviews into actionable to-do lists using the proposed Action:Objective(\#) format, providing structured and traceable guidance. The system integrates seamlessly into existing academic writing platforms, providing interactive interfaces for real-time feedback and revision tracking. Experimental results highlight the effectiveness of the proposed system in generating more comprehensive and useful reviews aligned with expert standards, surpassing ablated baselines and advancing transparent, human-centered scholarly assistance. --- ### Expert-Guided Prompting and Retrieval-Augmented Generation for Emergency Medical Service Question Answering Authors: Xueren Ge, Sahil Murtaza, Anthony Cortez, Homa Alemzadeh Published: 2025-11-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.10900v2 Large language models (LLMs) have shown promise in medical question answering, yet they often overlook the domain-specific expertise that professionals depend on, such as the clinical subject areas (e.g., trauma, airway) and the certification level (e.g., EMT, Paramedic). Existing approaches typically apply general-purpose prompting or retrieval strategies without leveraging this structured context, limiting performance in high-stakes settings. We address this gap with EMSQA, an 24.3K-question multiple-choice dataset spanning 10 clinical subject areas and 4 certification levels, accompanied by curated, subject area-aligned knowledge bases (40K documents and 2M tokens). Building on EMSQA, we introduce (i) Expert-CoT, a prompting strategy that conditions chain-of-thought (CoT) reasoning on specific clinical subject area and certification level, and (ii) ExpertRAG, a retrieval-augmented generation pipeline that grounds responses in subject area-aligned documents and real-world patient data. Experiments on 4 LLMs show that Expert-CoT improves up to 2.05% over vanilla CoT prompting. Additionally, combining Expert-CoT with ExpertRAG yields up to a 4.59% accuracy gain over standard RAG baselines. Notably, the 32B expertise-augmented LLMs pass all the computer-adaptive EMS certification simulation exams. --- ### From Proof to Program: Characterizing Tool-Induced Reasoning Hallucinations in Large Language Models Authors: Farima Fatahi Bayat, Pouya Pezeshkpour, Estevam Hruschka Published: 2025-11-14 Categories: cs.CL, cs.LO, cs.SE arXiv: https://arxiv.org/abs/2511.10899v2 Tool-augmented Language Models (TaLMs) can invoke external tools to solve problems beyond their parametric capacity. However, it remains unclear whether these tool-enabled gains reflect trustworthy reasoning. Focusing on the Code Interpreter tool, we show that even when tools are selected and executed correctly, TaLMs treat tool outputs as substitutes for reasoning, producing solutions that appear correct but lack coherent justification. We term this failure mode Tool-Induced Myopia (TIM), and study it using PYMATH, a benchmark of 1,679 competition-level mathematical problems for which Python code is helpful but not sufficient. We further develop a multi-dimensional evaluation suite to quantify reasoning degradation in TaLMs relative to their non-tool counterparts. Our findings reveal that while TaLMs achieve up to a 19.3 percentage point gain in final-answer accuracy, their reasoning behavior consistently deteriorates (e.g., non-tool LLMs win up to 41.5% more often in pairwise comparisons of the reasoning process). This degradation intensifies with tool use; the more frequently a model invokes tools, the less coherent its reasoning becomes. Moreover, tool use shifts errors from arithmetic mistakes toward global reasoning failures (logic, assumption, creativity); with TIM present in ~55% of high-risk cases. Finally, we propose a preference-optimization-based framework that realigns TaLMs to use tools as assistive evidence, improving both final-answer accuracy and reasoning depth under tool use. Codes and data are available at: https://github.com/megagonlabs/TIM. --- ### Graph Attention Network for Predicting Duration of Large-Scale Power Outages Induced by Natural Disasters Authors: Chenghao Duan, Chuanyi Ji Published: 2025-11-14 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.10898v1 Natural disasters such as hurricanes, wildfires, and winter storms have induced large-scale power outages in the U.S., resulting in tremendous economic and societal impacts. Accurately predicting power outage recovery and impact is key to resilience of power grid. Recent advances in machine learning offer viable frameworks for estimating power outage duration from geospatial and weather data. However, three major challenges are inherent to the task in a real world setting: spatial dependency of the data, spatial heterogeneity of the impact, and moderate event data. We propose a novel approach to estimate the duration of severe weather-induced power outages through Graph Attention Networks (GAT). Our network uses a simple structure from unsupervised pre-training, followed by semi-supervised learning. We use field data from four major hurricanes affecting $501$ counties in eight Southeastern U.S. states. The model exhibits an excellent performance ($>93\%$ accuracy) and outperforms the existing methods XGBoost, Random Forest, GCN and simple GAT by $2\% - 15\%$ in both the overall performance and class-wise accuracy. --- ### CLIPPan: Adapting CLIP as A Supervisor for Unsupervised Pansharpening Authors: Lihua Jian, Jiabo Liu, Shaowu Wu, Lihui Chen Published: 2025-11-14 Categories: eess.IV, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.10896v1 Despite remarkable advancements in supervised pansharpening neural networks, these methods face domain adaptation challenges of resolution due to the intrinsic disparity between simulated reduced-resolution training data and real-world full-resolution scenarios.To bridge this gap, we propose an unsupervised pansharpening framework, CLIPPan, that enables model training at full resolution directly by taking CLIP, a visual-language model, as a supervisor. However, directly applying CLIP to supervise pansharpening remains challenging due to its inherent bias toward natural images and limited understanding of pansharpening tasks. Therefore, we first introduce a lightweight fine-tuning pipeline that adapts CLIP to recognize low-resolution multispectral, panchromatic, and high-resolution multispectral images, as well as to understand the pansharpening process. Then, building on the adapted CLIP, we formulate a novel \textit{loss integrating semantic language constraints}, which aligns image-level fusion transitions with protocol-aligned textual prompts (e.g., Wald's or Khan's descriptions), thus enabling CLIPPan to use language as a powerful supervisory signal and guide fusion learning without ground truth. Extensive experiments demonstrate that CLIPPan consistently improves spectral and spatial fidelity across various pansharpening backbones on real-world datasets, setting a new state of the art for unsupervised full-resolution pansharpening. --- ### DINOv3 as a Frozen Encoder for CRPS-Oriented Probabilistic Rainfall Nowcasting Authors: Luciano Araujo Dourado Filho, Almir Moreira da Silva Neto, Anthony Miyaguchi, Rodrigo Pereira David, Rodrigo Tripodi Calumby, Lukáš Picek Published: 2025-11-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.10894v2 This paper proposes a competitive and computationally efficient approach to probabilistic rainfall nowcasting. A video projector (V-JEPA Vision Transformer) associated to a lightweight probabilistic head is attached to a pre-trained satellite vision encoder (DINOv3-SAT493M) to map encoder tokens into a discrete empirical CDF (eCDF) over 4-hour accumulated rainfall. The projector-head is optimized end-to-end over the Ranked Probability Score (RPS). As an alternative, 3D-UNET baselines trained with an aggregate Rank Probability Score and a per-pixel Gamma-Hurdle objective are used. On the Weather4Cast 2025 benchmark, the proposed method achieved a promising performance, with a CRPS of 3.5102, which represents $\approx$ 26% in effectiveness gain against the best 3D-UNET. --- ### Multi-View Polymer Representations for the Open Polymer Prediction Authors: Wonjin Jung, Yongseok Choi Published: 2025-11-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.10893v2 We address polymer property prediction with a multi-view design that exploits complementary representations. Our system integrates four families: (i) tabular RDKit/Morgan descriptors, (ii) graph neural networks, (iii) 3D-informed representations, and (iv) pretrained SMILES language models, and averages per-property predictions via a uniform ensemble. Models are trained with 10-fold splits and evaluated with SMILES test-time augmentation. The approach ranks 9th of 2241 teams in the Open Polymer Prediction Challenge at NeurIPS 2025. The submitted ensemble achieves a public MAE of 0.057 and a private MAE of 0.082. --- ### MCN-CL: Multimodal Cross-Attention Network and Contrastive Learning for Multimodal Emotion Recognition Authors: Feng Li, Ke Wu, Yongwei Li Published: 2025-11-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.10892v1 Multimodal emotion recognition plays a key role in many domains, including mental health monitoring, educational interaction, and human-computer interaction. However, existing methods often face three major challenges: unbalanced category distribution, the complexity of dynamic facial action unit time modeling, and the difficulty of feature fusion due to modal heterogeneity. With the explosive growth of multimodal data in social media scenarios, the need for building an efficient cross-modal fusion framework for emotion recognition is becoming increasingly urgent. To this end, this paper proposes Multimodal Cross-Attention Network and Contrastive Learning (MCN-CL) for multimodal emotion recognition. It uses a triple query mechanism and hard negative mining strategy to remove feature redundancy while preserving important emotional cues, effectively addressing the issues of modal heterogeneity and category imbalance. Experiment results on the IEMOCAP and MELD datasets show that our proposed method outperforms state-of-the-art approaches, with Weighted F1 scores improving by 3.42% and 5.73%, respectively. --- ### LLM enhanced graph inference for long-term disease progression modelling Authors: Tiantian He, An Zhao, Elinor Thompson, Anna Schroder, Ahmed Abdulaal, Frederik Barkhof, Daniel C. Alexander Published: 2025-11-14 Categories: cs.AI, stat.ML arXiv: https://arxiv.org/abs/2511.10890v1 Understanding the interactions between biomarkers among brain regions during neurodegenerative disease is essential for unravelling the mechanisms underlying disease progression. For example, pathophysiological models of Alzheimer's Disease (AD) typically describe how variables, such as regional levels of toxic proteins, interact spatiotemporally within a dynamical system driven by an underlying biological substrate, often based on brain connectivity. However, current methods grossly oversimplify the complex relationship between brain connectivity by assuming a single-modality brain connectome as the disease-spreading substrate. This leads to inaccurate predictions of pathology spread, especially during the long-term progression period. Meanhwile, other methods of learning such a graph in a purely data-driven way face the identifiability issue due to lack of proper constraint. We thus present a novel framework that uses Large Language Models (LLMs) as expert guides on the interaction of regional variables to enhance learning of disease progression from irregularly sampled longitudinal patient data. By leveraging LLMs' ability to synthesize multi-modal relationships and incorporate diverse disease-driving mechanisms, our method simultaneously optimizes 1) the construction of long-term disease trajectories from individual-level observations and 2) the biologically-constrained graph structure that captures interactions among brain regions with better identifiability. We demonstrate the new approach by estimating the pathology propagation using tau-PET imaging data from an Alzheimer's disease cohort. The new framework demonstrates superior prediction accuracy and interpretability compared to traditional approaches while revealing additional disease-driving factors beyond conventional connectivity measures. --- ### MedPath: Multi-Domain Cross-Vocabulary Hierarchical Paths for Biomedical Entity Linking Authors: Nishant Mishra, Wilker Aziz, Iacer Calixto Published: 2025-11-14 Categories: cs.CL, cs.DB arXiv: https://arxiv.org/abs/2511.10887v2 Progress in biomedical Named Entity Recognition (NER) and Entity Linking (EL) is currently hindered by a fragmented data landscape, a lack of resources for building explainable models, and the limitations of semantically-blind evaluation metrics. To address these challenges, we present MedPath, a large-scale and multi-domain biomedical EL dataset that builds upon nine existing expert-annotated EL datasets. In MedPath, all entities are 1) normalized using the latest version of the Unified Medical Language System (UMLS), 2) augmented with mappings to 62 other biomedical vocabularies and, crucially, 3) enriched with full ontological paths -- i.e., from general to specific -- in up to 11 biomedical vocabularies. MedPath directly enables new research frontiers in biomedical NLP, facilitating training and evaluation of semantic-rich and interpretable EL systems, and the development of the next generation of interoperable and explainable clinical NLP models. --- ### A Multifaceted Analysis of Negative Bias in Large Language Models through the Lens of Parametric Knowledge Authors: Jongyoon Song, Sangwon Yu, Sungroh Yoon Published: 2025-11-14 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.10881v1 Negative bias refers to the tendency of large language models (LLMs) to excessively generate negative responses in binary decision tasks (e.g., yes-no question answering). Previous research has focused on detecting and addressing negative attention heads that induce negative bias. However, the underlying detailed factors influencing negative bias remain underexplored. In this paper, we demonstrate that LLMs exhibit format-level negative bias, meaning the prompt format more influences their responses than the semantics of the negative response. For the fine-grained study of the negative bias, we introduce a pipeline for constructing the evaluation set, which systematically categorizes the dataset into three subsets based on the model's parametric knowledge: correct, incorrect, and insufficient relevant knowledge. Through analysis of this evaluation set, we identify a shortcut behavior in which models tend to generate negative responses when they lack sufficient knowledge to answer a yes-no question, leading to negative bias. We further examine how negative bias changes under various prompting scenarios related to parametric knowledge. We observe that providing relevant context and offering an "I don't know" option generally reduces negative bias, whereas chain-of-thought prompting tends to amplify the bias. Finally, we demonstrate that the degree of negative bias can vary depending on the type of prompt, which influences the direction of the response. Our work reveals the various factors that influence negative bias, providing critical insights for mitigating it in LLMs. --- ### ICX360: In-Context eXplainability 360 Toolkit Authors: Dennis Wei, Ronny Luss, Xiaomeng Hu, Lucas Monteiro Paes, Pin-Yu Chen, Karthikeyan Natesan Ramamurthy, Erik Miehling, Inge Vejsbjerg, Hendrik Strobelt Published: 2025-11-14 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.10879v1 Large Language Models (LLMs) have become ubiquitous in everyday life and are entering higher-stakes applications ranging from summarizing meeting transcripts to answering doctors' questions. As was the case with earlier predictive models, it is crucial that we develop tools for explaining the output of LLMs, be it a summary, list, response to a question, etc. With these needs in mind, we introduce In-Context Explainability 360 (ICX360), an open-source Python toolkit for explaining LLMs with a focus on the user-provided context (or prompts in general) that are fed to the LLMs. ICX360 contains implementations for three recent tools that explain LLMs using both black-box and white-box methods (via perturbations and gradients respectively). The toolkit, available at https://github.com/IBM/ICX360, contains quick-start guidance materials as well as detailed tutorials covering use cases such as retrieval augmented generation, natural language generation, and jailbreaking. --- ### Multi-Joint Physics-Informed Deep Learning Framework for Time-Efficient Inverse Dynamics Authors: Shuhao Ma, Zeyi Huang, Yu Cao, Wesley Doorsamy, Chaoyang Shi, Jun Li, Zhi-Qiang Zhang Published: 2025-11-14 Categories: cs.LG, cs.HC, eess.SP arXiv: https://arxiv.org/abs/2511.10878v1 Time-efficient estimation of muscle activations and forces across multi-joint systems is critical for clinical assessment and assistive device control. However, conventional approaches are computationally expensive and lack a high-quality labeled dataset for multi-joint applications. To address these challenges, we propose a physics-informed deep learning framework that estimates muscle activations and forces directly from kinematics. The framework employs a novel Multi-Joint Cross-Attention (MJCA) module with Bidirectional Gated Recurrent Unit (BiGRU) layers to capture inter-joint coordination, enabling each joint to adaptively integrate motion information from others. By embedding multi-joint dynamics, inter-joint coupling, and external force interactions into the loss function, our Physics-Informed MJCA-BiGRU (PI-MJCA-BiGRU) delivers physiologically consistent predictions without labeled data while enabling time-efficient inference. Experimental validation on two datasets demonstrates that PI-MJCA-BiGRU achieves performance comparable to conventional supervised methods without requiring ground-truth labels, while the MJCA module significantly enhances inter-joint coordination modeling compared to other baseline architectures. --- ### Architecting software monitors for control-flow anomaly detection through large language models and conformance checking Authors: Francesco Vitale, Francesco Flammini, Mauro Caporuscio, Nicola Mazzocca Published: 2025-11-14 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2511.10876v2 Context: Ensuring high levels of dependability in modern computer-based systems has become increasingly challenging due to their complexity. Although systems are validated at design time, their behavior can be different at runtime, possibly showing control-flow anomalies due to ``unknown unknowns''. Objective: We aim to detect control-flow anomalies through software monitoring, which verifies runtime behavior by logging software execution and detecting deviations from expected control flow. Methods: We propose a methodology to develop software monitors for control-flow anomaly detection through Large Language Models (LLMs) and conformance checking. The methodology builds on existing software development practices to maintain traditional V\&V while providing an additional level of robustness and trustworthiness. It leverages LLMs to link design-time models and implementation code, automating source-code instrumentation. The resulting event logs are analyzed via conformance checking, an explainable and effective technique for control-flow anomaly detection. Results: We test the methodology on a case-study scenario from the European Railway Traffic Management System / European Train Control System (ERTMS/ETCS), which is a railway standard for modern interoperable railways. The results obtained from the ERTMS/ETCS case study demonstrate that LLM-based source-code instrumentation can achieve up to 82.849% control-flow coverage of the reference design-time process model, while the subsequent conformance checking-based anomaly detection reaches a peak performance of 95.957% F1-score and 93.669% AUC. Conclusion: Incorporating domain-specific knowledge to guide LLMs in source-code instrumentation significantly allowed obtaining reliable and quality software logs and enabled effective control-flow anomaly detection through conformance checking. --- ### Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations Authors: Shuyuan Zhang, Zihan Wang, Xiao-Wen Chang, Doina Precup Published: 2025-11-14 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.10872v1 The integration of graphs with Goal-conditioned Hierarchical Reinforcement Learning (GCHRL) has recently gained attention, as intermediate goals (subgoals) can be effectively sampled from graphs that naturally represent the overall task structure in most RL tasks. However, existing approaches typically rely on domain-specific knowledge to construct these graphs, limiting their applicability to new tasks. Other graph-based approaches create graphs dynamically during exploration but struggle to fully utilize them, because they have problems passing the information in the graphs to newly visited states. Additionally, current GCHRL methods face challenges such as sample inefficiency and poor subgoal representation. This paper proposes a solution to these issues by developing a graph encoder-decoder to evaluate unseen states. Our proposed method, Graph-Guided sub-Goal representation Generation RL (G4RL), can be incorporated into any existing GCHRL method when operating in environments with primarily symmetric and reversible transitions to enhance performance across this class of problems. We show that the graph encoder-decoder can be effectively implemented using a network trained on the state graph generated during exploration. Empirical results indicate that leveraging high and low-level intrinsic rewards from the graph encoder-decoder significantly enhances the performance of state-of-the-art GCHRL approaches with an extra small computational cost in dense and sparse reward environments. --- ### From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems Authors: Parisa Rabbani, Nimet Beyza Bozdag, Dilek Hakkani-Tür Published: 2025-11-14 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.10871v2 LLMs are increasingly employed as judges across a variety of tasks, including those involving everyday social interactions. Yet, it remains unclear whether such LLM-judges can reliably assess tasks that require social or conversational judgment. We investigate how an LLM's conviction is changed when a task is reframed from a direct factual query to a Conversational Judgment Task. Our evaluation framework contrasts the model's performance on direct factual queries with its assessment of a speaker's correctness when the same information is presented within a minimal dialogue, effectively shifting the query from "Is this statement correct?" to "Is this speaker correct?". Furthermore, we apply pressure in the form of a simple rebuttal ("The previous answer is incorrect.") to both conditions. This perturbation allows us to measure how firmly the model maintains its position under conversational pressure. Our findings show that while some models like GPT-4o-mini reveal sycophantic tendencies under social framing tasks, others like Llama-8B-Instruct become overly-critical. We observe an average performance change of 9.24% across all models, demonstrating that even minimal dialogue context can significantly alter model judgment, underscoring conversational framing as a key factor in LLM-based evaluation. The proposed framework offers a reproducible methodology for diagnosing model conviction and contributes to the development of more trustworthy dialogue systems. --- ### Go-UT-Bench: A Fine-Tuning Dataset for LLM-Based Unit Test Generation in Go Authors: Yashshi Pipalani, Hritik Raj, Rajat Ghosh, Vaishnavi Bhargava, Debojyoti Dutta Published: 2025-11-14 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.10868v2 Training data imbalance poses a major challenge for code LLMs. Most available data heavily over represents raw opensource code while underrepresenting broader software engineering tasks, especially in low resource languages like Golang. As a result, models excel at code autocompletion but struggle with real world developer workflows such as unit test generation. To address this gap, we introduce GO UT Bench, a benchmark dataset of 5264 pairs of code and unit tests, drawn from 10 permissively licensed Golang repositories spanning diverse domain. We evaluate its effectiveness as a fine tuning dataset across two LLM families i.e. mixture of experts and dense decoders. Our results show that finetuned models outperform their base counterparts on more than 75% of benchmark tasks. --- ### Short-Window Sliding Learning for Real-Time Violence Detection via LLM-based Auto-Labeling Authors: Seoik Jung, Taekyung Song, Yangro Lee, Sungjun Lee Published: 2025-11-14 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.10866v2 This paper proposes a Short-Window Sliding Learning framework for real-time violence detection in CCTV footages. Unlike conventional long-video training approaches, the proposed method divides videos into 1-2 second clips and applies Large Language Model (LLM)-based auto-caption labeling to construct fine-grained datasets. Each short clip fully utilizes all frames to preserve temporal continuity, enabling precise recognition of rapid violent events. Experiments demonstrate that the proposed method achieves 95.25\% accuracy on RWF-2000 and significantly improves performance on long videos (UCF-Crime: 83.25\%), confirming its strong generalization and real-time applicability in intelligent surveillance systems. --- ### Generative Artificial Intelligence Adoption Among Bangladeshi Journalists: Exploring Journalists' Awareness, Acceptance, Usage, and Organizational Stance on Generative AI Authors: H. M. Murtuza, Md Oliullah Published: 2025-11-14 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.10862v1 Newsrooms and journalists across the world are adopting Generative AI (GenAI). Drawing on in-depth interviews with 23 journalists, this study identifies Bangladeshi journalists' awareness, acceptance, usage patterns, and their media organizations' stance toward GenAI. This study finds Bangladeshi journalists' high reliance on GenAI like their Western colleagues despite limited institutional support and the near absence of AI policy. Despite this contrast, concerns over GenAI's implications in journalism between the West and non-West were mostly identical. Moreover, this study contributes to the Unified Theory of Acceptance and Use of Technology (UTAUT) by proposing two changes regarding GenAI adoption among journalists in non-Western settings. First, this study identifies the non-contribution of facilitating conditions in shaping behavioral intent in GenAI adoption in non-Western contexts. Second, social influence works in a horizontal order through informal peer pressure or professional motivation in the absence of formal institutional hierarchical pressure. Voluntariness in the context of Bangladeshi journalists is underpinned by their professional compulsion. Therefore, this study contributes to understanding how contextual factors shape technology adoption trajectories in non-Western journalism. --- ### Documenting SME Processes with Conversational AI: From Tacit Knowledge to BPMN Authors: Unnikrishnan Radhakrishnan Published: 2025-11-13 Categories: cs.AI arXiv: https://arxiv.org/abs/2512.05122v1 Small and medium-sized enterprises (SMEs) still depend heavily on tacit, experience-based know-how that rarely makes its way into formal documentation. This paper introduces a large-language-model (LLM)-driven conversational assistant that captures such knowledge on the shop floor and converts it incrementally and interactively into standards-compliant Business Process Model and Notation (BPMN) 2.0 diagrams. Powered by Gemini 2.5 Pro and delivered through a lightweight Gradio front-end with client-side bpmn-js visualisation, the assistant conducts an interview-style dialogue: it elicits process details, supports clarifying dialogue and on-demand analysis, and renders live diagrams that users can refine in real time. A proof-of-concept evaluation in an equipment-maintenance scenario shows that the chatbot produced an accurate "AS-IS" model, flagged issues via on-diagram annotations, and generated an improved "TO-BE" variant, all within about 12-minutes, while keeping API costs within an SME-friendly budget. The study analyses latency sources, model-selection trade-offs, and the challenges of enforcing strict XML schemas, then outlines a roadmap toward agentic and multimodal deployments. The results demonstrate that conversational LLMs can potentially be used to lower the skill and cost barriers to rigorous process documentation, helping SMEs preserve institutional knowledge, enhance operational transparency, and accelerate continuous-improvement efforts. --- ### LM4Opt-RA: A Multi-Candidate LLM Framework with Structured Ranking for Automating Network Resource Allocation Authors: Tasnim Ahmed, Siana Rizwan, Naveed Ejaz, Salimur Choudhury Published: 2025-11-13 Categories: cs.NI, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2512.00039v1 Building on advancements in Large Language Models (LLMs), we can tackle complex analytical and mathematical reasoning tasks requiring nuanced contextual understanding. A prime example of such complex tasks is modelling resource allocation optimization in networks, which extends beyond translating natural language inputs into mathematical equations or Linear Programming (LP), Integer Linear Programming (ILP), and Mixed-Integer Linear Programming (MILP) models. However, existing benchmarks and datasets cannot address the complexities of such problems with dynamic environments, interdependent variables, and heterogeneous constraints. To address this gap, we introduce NL4RA, a curated dataset comprising 50 resource allocation optimization problems formulated as LP, ILP, and MILP. We then evaluate the performance of well-known open-source LLMs with varying parameter counts. To enhance existing LLM based methods, we introduce LM4Opt RA, a multi candidate framework that applies diverse prompting strategies such as direct, few shot, and chain of thought, combined with a structured ranking mechanism to improve accuracy. We identified discrepancies between human judgments and automated scoring such as ROUGE, BLEU, or BERT scores. However, human evaluation is time-consuming and requires specialized expertise, making it impractical for a fully automated end-to-end framework. To quantify the difference between LLM-generated responses and ground truth, we introduce LLM-Assisted Mathematical Evaluation (LAME), an automated metric designed for mathematical formulations. Using LM4Opt-RA, Llama-3.1-70B achieved a LAME score of 0.8007, outperforming other models by a significant margin, followed closely by Llama-3.1-8B. While baseline LLMs demonstrate considerable promise, they still lag behind human expertise; our proposed method surpasses these baselines regarding LAME and other metrics. --- ### ICD-Net: Inertial Covariance Displacement Network for Drone Visual-Inertial SLAM Authors: Tali Orlev Shapira, Itzik Klein Published: 2025-11-13 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2512.00037v1 Visual-inertial SLAM systems often exhibit suboptimal performance due to multiple confounding factors including imperfect sensor calibration, noisy measurements, rapid motion dynamics, low illumination, and the inherent limitations of traditional inertial navigation integration methods. These issues are particularly problematic in drone applications where robust and accurate state estimation is critical for safe autonomous operation. In this work, we present ICD-Net, a novel framework that enhances visual-inertial SLAM performance by learning to process raw inertial measurements and generating displacement estimates with associated uncertainty quantification. Rather than relying on analytical inertial sensor models that struggle with real-world sensor imperfections, our method directly extracts displacement maps from sensor data while simultaneously predicting measurement covariances that reflect estimation confidence. We integrate ICD-Net outputs as additional residual constraints into the VINS-Fusion optimization framework, where the predicted uncertainties appropriately weight the neural network contributions relative to traditional visual and inertial terms. The learned displacement constraints provide complementary information that compensates for various error sources in the SLAM pipeline. Our approach can be used under both normal operating conditions and in situations of camera inconsistency or visual degradation. Experimental evaluation on challenging high-speed drone sequences demonstrated that our approach significantly improved trajectory estimation accuracy compared to standard VINS-Fusion, with more than 38% improvement in mean APE and uncertainty estimates proving crucial for maintaining system robustness. Our method shows that neural network enhancement can effectively address multiple sources of SLAM degradation while maintaining real-time performance requirements. --- ### Classification of Transient Astronomical Object Light Curves Using LSTM Neural Networks Authors: Guilherme Grancho D. Fernandes, Marco A. Barroca, Mateus dos Santos, Rafael S. Oliveira Published: 2025-11-13 Categories: cs.LG, astro-ph.IM, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.17564v1 This study presents a bidirectional Long Short-Term Memory (LSTM) neural network for classifying transient astronomical object light curves from the Photometric LSST Astronomical Time-series Classification Challenge (PLAsTiCC) dataset. The original fourteen object classes were reorganized into five generalized categories (S-Like, Fast, Long, Periodic, and Non-Periodic) to address class imbalance. After preprocessing with padding, temporal rescaling, and flux normalization, a bidirectional LSTM network with masking layers was trained and evaluated on a test set of 19,920 objects. The model achieved strong performance for S-Like and Periodic classes, with ROC area under the curve (AUC) values of 0.95 and 0.99, and Precision-Recall AUC values of 0.98 and 0.89, respectively. However, performance was significantly lower for Fast and Long classes (ROC AUC of 0.68 for Long class), and the model exhibited difficulty distinguishing between Periodic and Non-Periodic objects. Evaluation on partial light curve data (5, 10,and 20 days from detection) revealed substantial performance degradation, with increased misclassification toward the S-Like class. These findings indicate that class imbalance and limited temporal information are primary limitations, suggesting that class balancing strategies and preprocessing techniques focusing on detection moments could improve performance. ---