# Research Papers — 2025-11 · bundle page 160 of 197 > Full-text markdown of papers #7951–8000 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/160 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/159.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/161.md) ### Self-adaptive weighting and sampling for physics-informed neural networks Authors: Wenqian Chen, Amanda Howard, Panos Stinis Published: 2025-11-07 Categories: stat.ML, cs.AI, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2511.05452v2 Physics-informed deep learning has emerged as a promising framework for solving partial differential equations (PDEs). Nevertheless, training these models on complex problems remains challenging, often leading to limited accuracy and efficiency. In this work, we introduce a hybrid adaptive sampling and weighting method to enhance the performance of physics-informed neural networks (PINNs). The adaptive sampling component identifies training points in regions where the solution exhibits rapid variation, while the adaptive weighting component balances the convergence rate across training points. Numerical experiments show that applying only adaptive sampling or only adaptive weighting is insufficient to consistently achieve accurate predictions, particularly when training points are scarce. Since each method emphasizes different aspects of the solution, their effectiveness is problem dependent. By combining both strategies, the proposed framework consistently improves prediction accuracy and training efficiency, offering a more robust approach for solving PDEs with PINNs. --- ### Self-adaptive weighting and sampling for physics-informed neural networks Authors: Wenqian Chen, Amanda Howard, Panos Stinis Published: 2025-11-07 Categories: stat.ML, cs.AI, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2511.05452v1 Physics-informed deep learning has emerged as a promising framework for solving partial differential equations (PDEs). Nevertheless, training these models on complex problems remains challenging, often leading to limited accuracy and efficiency. In this work, we introduce a hybrid adaptive sampling and weighting method to enhance the performance of physics-informed neural networks (PINNs). The adaptive sampling component identifies training points in regions where the solution exhibits rapid variation, while the adaptive weighting component balances the convergence rate across training points. Numerical experiments show that applying only adaptive sampling or only adaptive weighting is insufficient to consistently achieve accurate predictions, particularly when training points are scarce. Since each method emphasizes different aspects of the solution, their effectiveness is problem dependent. By combining both strategies, the proposed framework consistently improves prediction accuracy and training efficiency, offering a more robust approach for solving PDEs with PINNs. --- ### How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need? Authors: Tuan Anh Tran, Duy M. H. Nguyen, Hoai-Chau Tran, Michael Barz, Khoa D. Doan, Roger Wattenhofer, Ngo Anh Vien, Mathias Niepert, Daniel Sonntag, Paul Swoboda Published: 2025-11-07 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.05449v1 Recent advances in 3D point cloud transformers have led to state-of-the-art results in tasks such as semantic segmentation and reconstruction. However, these models typically rely on dense token representations, incurring high computational and memory costs during training and inference. In this work, we present the finding that tokens are remarkably redundant, leading to substantial inefficiency. We introduce gitmerge3D, a globally informed graph token merging method that can reduce the token count by up to 90-95% while maintaining competitive performance. This finding challenges the prevailing assumption that more tokens inherently yield better performance and highlights that many current models are over-tokenized and under-optimized for scalability. We validate our method across multiple 3D vision tasks and show consistent improvements in computational efficiency. This work is the first to assess redundancy in large-scale 3D transformer models, providing insights into the development of more efficient 3D foundation architectures. Our code and checkpoints are publicly available at https://gitmerge3d.github.io --- ### Adversarially Robust Multitask Adaptive Control Authors: Kasra Fallah, Leonardo F. Toso, James Anderson Published: 2025-11-07 Categories: cs.LG, eess.SY, math.OC arXiv: https://arxiv.org/abs/2511.05444v1 We study adversarially robust multitask adaptive linear quadratic control; a setting where multiple systems collaboratively learn control policies under model uncertainty and adversarial corruption. We propose a clustered multitask approach that integrates clustering and system identification with resilient aggregation to mitigate corrupted model updates. Our analysis characterizes how clustering accuracy, intra-cluster heterogeneity, and adversarial behavior affect the expected regret of certainty-equivalent (CE) control across LQR tasks. We establish non-asymptotic bounds demonstrating that the regret decreases inversely with the number of honest systems per cluster and that this reduction is preserved under a bounded fraction of adversarial systems within each cluster. --- ### APP: Accelerated Path Patching with Task-Specific Pruning Authors: Frauke Andersen, William Rudman, Ruochen Zhang, Carsten Eickhoff Published: 2025-11-07 Categories: cs.LG, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.05442v1 Circuit discovery is a key step in many mechanistic interpretability pipelines. Current methods, such as Path Patching, are computationally expensive and have limited in-depth circuit analysis for smaller models. In this study, we propose Accelerated Path Patching (APP), a hybrid approach leveraging our novel contrastive attention head pruning method to drastically reduce the search space of circuit discovery methods. Our Contrastive-FLAP pruning algorithm uses techniques from causal mediation analysis to assign higher pruning scores to task-specific attention heads, leading to higher performing sparse models compared to traditional pruning techniques. Although Contrastive-FLAP is successful at preserving task-specific heads that existing pruning algorithms remove at low sparsity ratios, the circuits found by Contrastive-FLAP alone are too large to satisfy the minimality constraint required in circuit analysis. APP first applies Contrastive-FLAP to reduce the search space on required for circuit discovery algorithms by, on average, 56\%. Next, APP, applies traditional Path Patching on the remaining attention heads, leading to a speed up of 59.63\%-93.27\% compared to Path Patching applied to the dense model. Despite the substantial computational saving that APP provides, circuits obtained from APP exhibit substantial overlap and similar performance to previously established Path Patching circuits --- ### Shared Latent Representation for Joint Text-to-Audio-Visual Synthesis Authors: Dogucan Yaman, Seymanur Akti, Fevziye Irem Eyiokur, Alexander Waibel Published: 2025-11-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05432v1 We propose a text-to-talking-face synthesis framework leveraging latent speech representations from HierSpeech++. A Text-to-Vec module generates Wav2Vec2 embeddings from text, which jointly condition speech and face generation. To handle distribution shifts between clean and TTS-predicted features, we adopt a two-stage training: pretraining on Wav2Vec2 embeddings and finetuning on TTS outputs. This enables tight audio-visual alignment, preserves speaker identity, and produces natural, expressive speech and synchronized facial motion without ground-truth audio at inference. Experiments show that conditioning on TTS-predicted latent features outperforms cascaded pipelines, improving both lip-sync and visual realism. --- ### "I Like That You Have to Poke Around": Instructors on How Experiential Approaches to AI Literacy Spark Inquiry and Critical Thinking Authors: Aparna Maya Warrier, Arav Agarwal, Jaromir Savelka, Christopher Bogart, Heather Burte Published: 2025-11-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.05430v1 As artificial intelligence (AI) increasingly shapes decision-making across domains, there is a growing need to support AI literacy among learners beyond computer science. However, many current approaches rely on programming-heavy tools or abstract lecture-based content, limiting accessibility for non-STEM audiences. This paper presents findings from a study of AI User, a modular, web-based curriculum that teaches core AI concepts through interactive, no-code projects grounded in real-world scenarios. The curriculum includes eight projects; this study focuses on instructor feedback on Projects 5-8, which address applied topics such as natural language processing, computer vision, decision support, and responsible AI. Fifteen community college instructors participated in structured focus groups, completing the projects as learners and providing feedback through individual reflection and group discussion. Using thematic analysis, we examined how instructors evaluated the design, instructional value, and classroom applicability of these experiential activities. Findings highlight instructors' appreciation for exploratory tasks, role-based simulations, and real-world relevance, while also surfacing design trade-offs around cognitive load, guidance, and adaptability for diverse learners. This work extends prior research on AI literacy by centering instructor perspectives on teaching complex AI topics without code. It offers actionable insights for designing inclusive, experiential AI learning resources that scale across disciplines and learner backgrounds. --- ### Sharing the Learned Knowledge-base to Estimate Convolutional Filter Parameters for Continual Image Restoration Authors: Aupendu Kar, Krishnendu Ghosh, Prabir Kumar Biswas Published: 2025-11-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05421v2 Continual learning is an emerging topic in the field of deep learning, where a model is expected to learn continuously for new upcoming tasks without forgetting previous experiences. This field has witnessed numerous advancements, but few works have been attempted in the direction of image restoration. Handling large image sizes and the divergent nature of various degradation poses a unique challenge in the restoration domain. However, existing works require heavily engineered architectural modifications for new task adaptation, resulting in significant computational overhead. Regularization-based methods are unsuitable for restoration, as different restoration challenges require different kinds of feature processing. In this direction, we propose a simple modification of the convolution layer to adapt the knowledge from previous restoration tasks without touching the main backbone architecture. Therefore, it can be seamlessly applied to any deep architecture without any structural modifications. Unlike other approaches, we demonstrate that our model can increase the number of trainable parameters without significantly increasing computational overhead or inference time. Experimental validation demonstrates that new restoration tasks can be introduced without compromising the performance of existing tasks. We also show that performance on new restoration tasks improves by adapting the knowledge from the knowledge base created by previous restoration tasks. The code is available at https://github.com/aupendu/continual-restore. --- ### Sharing the Learned Knowledge-base to Estimate Convolutional Filter Parameters for Continual Image Restoration Authors: Aupendu Kar, Krishnendu Ghosh, Prabir Kumar Biswas Published: 2025-11-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05421v1 Continual learning is an emerging topic in the field of deep learning, where a model is expected to learn continuously for new upcoming tasks without forgetting previous experiences. This field has witnessed numerous advancements, but few works have been attempted in the direction of image restoration. Handling large image sizes and the divergent nature of various degradation poses a unique challenge in the restoration domain. However, existing works require heavily engineered architectural modifications for new task adaptation, resulting in significant computational overhead. Regularization-based methods are unsuitable for restoration, as different restoration challenges require different kinds of feature processing. In this direction, we propose a simple modification of the convolution layer to adapt the knowledge from previous restoration tasks without touching the main backbone architecture. Therefore, it can be seamlessly applied to any deep architecture without any structural modifications. Unlike other approaches, we demonstrate that our model can increase the number of trainable parameters without significantly increasing computational overhead or inference time. Experimental validation demonstrates that new restoration tasks can be introduced without compromising the performance of existing tasks. We also show that performance on new restoration tasks improves by adapting the knowledge from the knowledge base created by previous restoration tasks. The code is available at https://github.com/aupendu/continual-restore. --- ### ProDER: A Continual Learning Approach for Fault Classification and Localization in Evolving Smart Grids Authors: Emad Efatinasab, Nahal Azadi, Davide Dalle Pezze, Gian Antonio Susto, Chuadhry Mujeeb Ahmed, Mirco Rampazzo Published: 2025-11-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.05420v4 Data-driven fault diagnosis models for smart grids are usually trained once on a fixed dataset, whereas in operation new fault types appear and monitoring is extended to new grid zones. Retraining from scratch on all accumulated data is costly, while naively updating the model on new data causes catastrophic forgetting. To address this problem, we formulate fault type classification and fault zone localization as continual learning (CL) problems and design four evaluation scenarios on the IEEE 13-node test feeder, three class-incremental and one domain-incremental. We then propose Prototype-based Dark Experience Replay (ProDER), which extends DER++ with prototype attraction and prototype-level repulsion losses that stabilize the feature space, temperature-scaled logit distillation, and a prototype-aware replay memory that retains both core and boundary samples of each class. ProDER achieves the highest accuracy among the tested CL methods in all scenarios, with an average accuracy of 58.2%, 6.6 points above the strongest competing method (DPDMR, 51.6%) and only 3.2 points below joint training (61.4%). Per scenario, it improves over the strongest competitor by 4.2 to 7.4 points and closes the gap to joint training to as little as 1.0 point in fault type classification, while matching it in fault zone localization. Moreover, it remains the best method when the replay buffer is substantially reduced. These results show that prototype-guided replay is an effective, memory-bounded way to keep fault diagnosis models up to date as the grid evolves, while validation on field measurements remains a necessary next step. --- ### ProDER: A Continual Learning Approach for Fault Prediction in Evolving Smart Grids Authors: Emad Efatinasab, Nahal Azadi, Davide Dalle Pezze, Gian Antonio Susto, Chuadhry Mujeeb Ahmed, Mirco Rampazzo Published: 2025-11-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.05420v1 As smart grids evolve to meet growing energy demands and modern operational challenges, the ability to accurately predict faults becomes increasingly critical. However, existing AI-based fault prediction models struggle to ensure reliability in evolving environments where they are required to adapt to new fault types and operational zones. In this paper, we propose a continual learning (CL) framework in the smart grid context to evolve the model together with the environment. We design four realistic evaluation scenarios grounded in class-incremental and domain-incremental learning to emulate evolving grid conditions. We further introduce Prototype-based Dark Experience Replay (ProDER), a unified replay-based approach that integrates prototype-based feature regularization, logit distillation, and a prototype-guided replay memory. ProDER achieves the best performance among tested CL techniques, with only a 0.045 accuracy drop for fault type prediction and 0.015 for fault zone prediction. These results demonstrate the practicality of CL for scalable, real-world fault prediction in smart grids. --- ### Steering Language Models with Weight Arithmetic Authors: Constanza Fierro, Fabien Roger Published: 2025-11-07 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.05408v2 Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizations. To better leverage narrow training data, we propose contrastive weight steering, a simple post-training method that edits the model parameters using weight arithmetic. We isolate a behavior direction in weight-space by subtracting the weight deltas from two small fine-tunes -- one that induces the desired behavior and another that induces its opposite -- and then add or remove this direction to modify the model's weights. We apply this technique to mitigate sycophancy and induce misalignment, and find that weight steering often generalizes further than activation steering, achieving stronger out-of-distribution behavioral control before degrading general capabilities. We also show that, in the context of task-specific fine-tuning, weight steering can partially mitigate undesired behavioral drift: it can reduce sycophancy and under-refusals introduced during fine-tuning while preserving task performance gains. Finally, we provide preliminary evidence that emergent misalignment can be detected by measuring the similarity between fine-tuning updates and an "evil" weight direction, suggesting that it may be possible to monitor the evolution of weights during training and detect rare misaligned behaviors that never manifest during training or evaluations. --- ### Steering Language Models with Weight Arithmetic Authors: Constanza Fierro, Fabien Roger Published: 2025-11-07 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.05408v1 Providing high-quality feedback to Large Language Models (LLMs) on a diverse training distribution can be difficult and expensive, and providing feedback only on a narrow distribution can result in unintended generalizations. To better leverage narrow training data, we propose contrastive weight steering, a simple post-training method that edits the model parameters using weight arithmetic. We isolate a behavior direction in weight-space by subtracting the weight deltas from two small fine-tunes -- one that induces the desired behavior and another that induces its opposite -- and then add or remove this direction to modify the model's weights. We apply this technique to mitigate sycophancy and induce misalignment, and find that weight steering often generalizes further than activation steering, achieving stronger out-of-distribution behavioral control before degrading general capabilities. We also show that, in the context of task-specific fine-tuning, weight steering can partially mitigate undesired behavioral drift: it can reduce sycophancy and under-refusals introduced during fine-tuning while preserving task performance gains. Finally, we provide preliminary evidence that emergent misalignment can be detected by measuring the similarity between fine-tuning updates and an "evil" weight direction, suggesting that it may be possible to monitor the evolution of weights during training and detect rare misaligned behaviors that never manifest during training or evaluations. --- ### Minority-Aware Satisfaction Estimation in Dialogue Systems via Preference-Adaptive Reinforcement Learning Authors: Yahui Fu, Zi Haur Pang, Tatsuya Kawahara Published: 2025-11-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.05407v1 User satisfaction in dialogue systems is inherently subjective. When the same response strategy is applied across users, minority users may assign different satisfaction ratings than majority users due to variations in individual intents and preferences. However, existing alignment methods typically train one-size-fits-all models that aim for broad consensus, often overlooking minority perspectives and user-specific adaptation. We propose a unified framework that models both individual- and group-level preferences for user satisfaction estimation. First, we introduce Chain-of-Personalized-Reasoning (CoPeR) to capture individual preferences through interpretable reasoning chains. Second, we propose an expectation-maximization-based Majority-Minority Preference-Aware Clustering (M2PC) algorithm that discovers distinct user groups in an unsupervised manner to learn group-level preferences. Finally, we integrate these components into a preference-adaptive reinforcement learning framework (PAda-PPO) that jointly optimizes alignment with both individual and group preferences. Experiments on the Emotional Support Conversation dataset demonstrate consistent improvements in user satisfaction estimation, particularly for underrepresented user groups. --- ### Large Language Models for Explainable Threat Intelligence Authors: Tiago Dinis, Miguel Correia, Roger Tavares Published: 2025-11-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.05406v1 As cyber threats continue to grow in complexity, traditional security mechanisms struggle to keep up. Large language models (LLMs) offer significant potential in cybersecurity due to their advanced capabilities in text processing and generation. This paper explores the use of LLMs with retrieval-augmented generation (RAG) to obtain threat intelligence by combining real-time information retrieval with domain-specific data. The proposed system, RAGRecon, uses a LLM with RAG to answer questions about cybersecurity threats. Moreover, it makes this form of Artificial Intelligence (AI) explainable by generating and visually presenting to the user a knowledge graph for every reply. This increases the transparency and interpretability of the reasoning of the model, allowing analysts to better understand the connections made by the system based on the context recovered by the RAG system. We evaluated RAGRecon experimentally with two datasets and seven different LLMs and the responses matched the reference responses more than 91% of the time for the best combinations. --- ### Multi-modal Loop Closure Detection with Foundation Models in Severely Unstructured Environments Authors: Laura Alejandra Encinar Gonzalez, John Folkesson, Rudolph Triebel, Riccardo Giubilato Published: 2025-11-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.05404v1 Robust loop closure detection is a critical component of Simultaneous Localization and Mapping (SLAM) algorithms in GNSS-denied environments, such as in the context of planetary exploration. In these settings, visual place recognition often fails due to aliasing and weak textures, while LiDAR-based methods suffer from sparsity and ambiguity. This paper presents MPRF, a multimodal pipeline that leverages transformer-based foundation models for both vision and LiDAR modalities to achieve robust loop closure in severely unstructured environments. Unlike prior work limited to retrieval, MPRF integrates a two-stage visual retrieval strategy with explicit 6-DoF pose estimation, combining DINOv2 features with SALAD aggregation for efficient candidate screening and SONATA-based LiDAR descriptors for geometric verification. Experiments on the S3LI dataset and S3LI Vulcano dataset show that MPRF outperforms state-of-the-art retrieval methods in precision while enhancing pose estimation robustness in low-texture regions. By providing interpretable correspondences suitable for SLAM back-ends, MPRF achieves a favorable trade-off between accuracy, efficiency, and reliability, demonstrating the potential of foundation models to unify place recognition and pose estimation. Code and models will be released at github.com/DLR-RM/MPRF. --- ### PALM: A Dataset and Baseline for Learning Multi-subject Hand Prior Authors: Zicong Fan, Edoardo Remelli, David Dimond, Fadime Sener, Liuhao Ge, Bugra Tekin, Cem Keskin, Shreyas Hampali Published: 2025-11-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05403v3 The ability to grasp objects, signal with gestures, and share emotion through touch all stem from the unique capabilities of human hands. Yet creating high-quality personalized hand avatars from images remains challenging due to complex geometry, appearance, and articulation, particularly under unconstrained lighting and limited views. Progress has also been limited by the lack of datasets that jointly provide accurate 3D geometry, high-resolution multiview imagery, and a diverse population of subjects. To address this, we present PALM, a large-scale dataset comprising 13k high-quality hand scans from 263 subjects and 90k multi-view images, capturing rich variation in skin tone, age, and geometry. To show its utility, we present a baseline PALM-Net, a multi-subject prior over hand geometry and material properties learned via physically based inverse rendering, enabling realistic, relightable single-image hand avatar personalization. PALM's scale and diversity make it a valuable real-world resource for hand modeling and related research. --- ### PALM: A Dataset and Baseline for Learning Multi-subject Hand Prior Authors: Zicong Fan, Edoardo Remelli, David Dimond, Fadime Sener, Liuhao Ge, Bugra Tekin, Cem Keskin, Shreyas Hampali Published: 2025-11-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05403v1 The ability to grasp objects, signal with gestures, and share emotion through touch all stem from the unique capabilities of human hands. Yet creating high-quality personalized hand avatars from images remains challenging due to complex geometry, appearance, and articulation, particularly under unconstrained lighting and limited views. Progress has also been limited by the lack of datasets that jointly provide accurate 3D geometry, high-resolution multiview imagery, and a diverse population of subjects. To address this, we present PALM, a large-scale dataset comprising 13k high-quality hand scans from 263 subjects and 90k multi-view images, capturing rich variation in skin tone, age, and geometry. To show its utility, we present a baseline PALM-Net, a multi-subject prior over hand geometry and material properties learned via physically based inverse rendering, enabling realistic, relightable single-image hand avatar personalization. PALM's scale and diversity make it a valuable real-world resource for hand modeling and related research. --- ### Robust Neural Audio Fingerprinting using Music Foundation Models Authors: Shubhr Singh, Kiran Bhat, Xavier Riley, Benjamin Resnick, John Thickstun, Walter De Brouwer Published: 2025-11-07 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2511.05399v1 The proliferation of distorted, compressed, and manipulated music on modern media platforms like TikTok motivates the development of more robust audio fingerprinting techniques to identify the sources of musical recordings. In this paper, we develop and evaluate new neural audio fingerprinting techniques with the aim of improving their robustness. We make two contributions to neural fingerprinting methodology: (1) we use a pretrained music foundation model as the backbone of the neural architecture and (2) we expand the use of data augmentation to train fingerprinting models under a wide variety of audio manipulations, including time streching, pitch modulation, compression, and filtering. We systematically evaluate our methods in comparison to two state-of-the-art neural fingerprinting models: NAFP and GraFPrint. Results show that fingerprints extracted with music foundation models (e.g., MuQ, MERT) consistently outperform models trained from scratch or pretrained on non-musical audio. Segment-level evaluation further reveals their capability to accurately localize fingerprint matches, an important practical feature for catalog management. --- ### EveryDayVLA: A Vision-Language-Action Model for Affordable Robotic Manipulation Authors: Samarth Chopra, Alex McMoil, Ben Carnovale, Evan Sokolson, Rajkumar Kubendran, Samuel Dickerson Published: 2025-11-07 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.05397v1 While Vision-Language-Action (VLA) models map visual inputs and language instructions directly to robot actions, they often rely on costly hardware and struggle in novel or cluttered scenes. We introduce EverydayVLA, a 6-DOF manipulator that can be assembled for under $300, capable of modest payloads and workspace. A single unified model jointly outputs discrete and continuous actions, and our adaptive-horizon ensemble monitors motion uncertainty to trigger on-the-fly re-planning for safe, reliable operation. On LIBERO, EverydayVLA matches state-of-the-art success rates, and in real-world tests it outperforms prior methods by 49% in-distribution and 34.9% out-of-distribution. By combining a state-of-the-art VLA with cost-effective hardware, EverydayVLA democratizes access to a robotic foundation model and paves the way for economical use in homes and research labs alike. Experiment videos and details: https://everydayvla.github.io/ --- ### Sample Complexity of Distributionally Robust Off-Dynamics Reinforcement Learning with Online Interaction Authors: Yiting He, Zhishuai Liu, Weixin Wang, Pan Xu Published: 2025-11-07 Categories: cs.LG, cs.AI, cs.RO, stat.ML arXiv: https://arxiv.org/abs/2511.05396v1 Off-dynamics reinforcement learning (RL), where training and deployment transition dynamics are different, can be formulated as learning in a robust Markov decision process (RMDP) where uncertainties in transition dynamics are imposed. Existing literature mostly assumes access to generative models allowing arbitrary state-action queries or pre-collected datasets with a good state coverage of the deployment environment, bypassing the challenge of exploration. In this work, we study a more realistic and challenging setting where the agent is limited to online interaction with the training environment. To capture the intrinsic difficulty of exploration in online RMDPs, we introduce the supremal visitation ratio, a novel quantity that measures the mismatch between the training dynamics and the deployment dynamics. We show that if this ratio is unbounded, online learning becomes exponentially hard. We propose the first computationally efficient algorithm that achieves sublinear regret in online RMDPs with $f$-divergence based transition uncertainties. We also establish matching regret lower bounds, demonstrating that our algorithm achieves optimal dependence on both the supremal visitation ratio and the number of interaction episodes. Finally, we validate our theoretical results through comprehensive numerical experiments. --- ### AI Assisted AR Assembly: Object Recognition and Computer Vision for Augmented Reality Assisted Assembly Authors: Alexander Htet Kyaw, Haotian Ma, Sasa Zivkovic, Jenny Sabin Published: 2025-11-07 Categories: cs.CV, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.05394v2 We present an AI-assisted Augmented Reality assembly workflow that uses deep learning-based object recognition to identify different assembly components and display step-by-step instructions. For each assembly step, the system displays a bounding box around the corresponding components in the physical space, and where the component should be placed. By connecting assembly instructions with the real-time location of relevant components, the system eliminates the need for manual searching, sorting, or labeling of different components before each assembly. To demonstrate the feasibility of using object recognition for AR-assisted assembly, we highlight a case study involving the assembly of LEGO sculptures. --- ### AI Assisted AR Assembly: Object Recognition and Computer Vision for Augmented Reality Assisted Assembly Authors: Alexander Htet Kyaw, Haotian Ma, Sasa Zivkovic, Jenny Sabin Published: 2025-11-07 Categories: cs.CV, cs.AI, cs.HC, H.5.2; H.5.1; I.4.8; I.2.6 arXiv: https://arxiv.org/abs/2511.05394v1 We present an AI-assisted Augmented Reality assembly workflow that uses deep learning-based object recognition to identify different assembly components and display step-by-step instructions. For each assembly step, the system displays a bounding box around the corresponding components in the physical space, and where the component should be placed. By connecting assembly instructions with the real-time location of relevant components, the system eliminates the need for manual searching, sorting, or labeling of different components before each assembly. To demonstrate the feasibility of using object recognition for AR-assisted assembly, we highlight a case study involving the assembly of LEGO sculptures. --- ### PreResQ-R1: Response-Preference Disentangled Ranking-and-Scoring Reinforcement Optimization for Robust Visual Quality Assessment Authors: Zehui Feng, Weichuan Wang, Xiaohan Chen, Ting Han Published: 2025-11-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05393v2 Visual Quality Assessment (QA) seeks to predict human perceptual judgments of visual fidelity. While recent multimodal large language models (MLLMs) show promise in reasoning about image and video quality, existing approaches mainly rely on supervised fine-tuning or rank-only objectives, resulting in shallow reasoning, poor score calibration, and limited cross-domain generalization. We propose PreResQ-R1, a Preference-Response Disentangled Reinforcement Learning framework that unifies absolute score regression and relative ranking consistency within a single reasoning-driven optimization scheme. Unlike prior QA methods, PreResQ-R1 introduces a dual-branch reward formulation that separately models intra-sample response coherence and inter-sample preference alignment, optimized via Group Relative Policy Optimization (GRPO). This design encourages fine-grained, stable, and interpretable chain-of-thought reasoning about perceptual quality. To extend beyond static imagery, we further design a global-temporal and local-spatial data flow strategy for Video Quality Assessment. Remarkably, with reinforcement fine-tuning on only 6K images and 28K videos, PreResQ-R1 achieves state-of-the-art results across 10 IQA and 5 VQA benchmarks under both SRCC and PLCC metrics, surpassing by margins of 5.30% and textbf2.15% in IQA task, respectively. Beyond quantitative gains, it produces human-aligned reasoning traces that reveal the perceptual cues underlying quality judgments. --- ### PreResQ-R1: Towards Fine-Grained Rank-and-Score Reinforcement Learning for Visual Quality Assessment via Preference-Response Disentangled Policy Optimization Authors: Zehui Feng, Tian Qiu, Tong Wu, Junxuan Li, Huayuan Xu, Ting Han Published: 2025-11-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05393v1 Visual Quality Assessment (QA) seeks to predict human perceptual judgments of visual fidelity. While recent multimodal large language models (MLLMs) show promise in reasoning about image and video quality, existing approaches mainly rely on supervised fine-tuning or rank-only objectives, resulting in shallow reasoning, poor score calibration, and limited cross-domain generalization. We propose PreResQ-R1, a Preference-Response Disentangled Reinforcement Learning framework that unifies absolute score regression and relative ranking consistency within a single reasoning-driven optimization scheme. Unlike prior QA methods, PreResQ-R1 introduces a dual-branch reward formulation that separately models intra-sample response coherence and inter-sample preference alignment, optimized via Group Relative Policy Optimization (GRPO). This design encourages fine-grained, stable, and interpretable chain-of-thought reasoning about perceptual quality. To extend beyond static imagery, we further design a global-temporal and local-spatial data flow strategy for Video Quality Assessment. Remarkably, with reinforcement fine-tuning on only 6K images and 28K videos, PreResQ-R1 achieves state-of-the-art results across 10 IQA and 5 VQA benchmarks under both SRCC and PLCC metrics, surpassing by margins of 5.30% and textbf2.15% in IQA task, respectively. Beyond quantitative gains, it produces human-aligned reasoning traces that reveal the perceptual cues underlying quality judgments. Code and model are available. --- ### TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework Authors: Chao Zhang, Yuhao Wang, Derong Xu, Haoxin Zhang, Yuanjie Lyu, Yuhao Chen, Shuochen Liu, Tong Xu, Xiangyu Zhao, Yan Gao, Yao Hu, Enhong Chen Published: 2025-11-07 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2511.05385v2 Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent agentic RAG has improved via reinforcement learning, they often incur substantial token overhead from search and reasoning processes. This trade-off prioritizes accuracy over efficiency. To address this issue, this work proposes TeaRAG, a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps. 1) First, the retrieved content is compressed by augmenting chunk-based semantic retrieval with a graph retrieval using concise triplets. A knowledge association graph is then built from semantic similarity and co-occurrence. Finally, Personalized PageRank is leveraged to highlight key knowledge within this graph, reducing the number of tokens per retrieval. 2) Besides, to reduce reasoning steps, Iterative Process-aware Direct Preference Optimization (IP-DPO) is proposed. Specifically, our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps. This design can produce high-quality preference-pair datasets, supporting iterative DPO to improve reasoning conciseness. Across six datasets, TeaRAG improves the average Exact Match by 4% and 2% while reducing output tokens by 61% and 59% on Llama3-8B-Instruct and Qwen2.5-14B-Instruct, respectively. Code is available at https://github.com/Applied-Machine-Learning-Lab/TeaRAG. --- ### TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework Authors: Chao Zhang, Yuhao Wang, Derong Xu, Haoxin Zhang, Yuanjie Lyu, Yuhao Chen, Shuochen Liu, Tong Xu, Xiangyu Zhao, Yan Gao, Yao Hu, Enhong Chen Published: 2025-11-07 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2511.05385v1 Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent agentic RAG has improved via reinforcement learning, they often incur substantial token overhead from search and reasoning processes. This trade-off prioritizes accuracy over efficiency. To address this issue, this work proposes TeaRAG, a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps. 1) First, the retrieved content is compressed by augmenting chunk-based semantic retrieval with a graph retrieval using concise triplets. A knowledge association graph is then built from semantic similarity and co-occurrence. Finally, Personalized PageRank is leveraged to highlight key knowledge within this graph, reducing the number of tokens per retrieval. 2) Besides, to reduce reasoning steps, Iterative Process-aware Direct Preference Optimization (IP-DPO) is proposed. Specifically, our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps. This design can produce high-quality preference-pair datasets, supporting iterative DPO to improve reasoning conciseness. Across six datasets, TeaRAG improves the average Exact Match by 4% and 2% while reducing output tokens by 61% and 59% on Llama3-8B-Instruct and Qwen2.5-14B-Instruct, respectively. Code is available at https://github.com/Applied-Machine-Learning-Lab/TeaRAG. --- ### Reasoning Is All You Need for Urban Planning AI Authors: Sijie Yang, Jiatong Li, Filip Biljecki Published: 2025-11-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.05375v1 AI has proven highly successful at urban planning analysis -- learning patterns from data to predict future conditions. The next frontier is AI-assisted decision-making: agents that recommend sites, allocate resources, and evaluate trade-offs while reasoning transparently about constraints and stakeholder values. Recent breakthroughs in reasoning AI -- CoT prompting, ReAct, and multi-agent collaboration frameworks -- now make this vision achievable. This position paper presents the Agentic Urban Planning AI Framework for reasoning-capable planning agents that integrates three cognitive layers (Perception, Foundation, Reasoning) with six logic components (Analysis, Generation, Verification, Evaluation, Collaboration, Decision) through a multi-agents collaboration framework. We demonstrate why planning decisions require explicit reasoning capabilities that are value-based (applying normative principles), rule-grounded (guaranteeing constraint satisfaction), and explainable (generating transparent justifications) -- requirements that statistical learning alone cannot fulfill. We compare reasoning agents with statistical learning, present a comprehensive architecture with benchmark evaluation metrics, and outline critical research challenges. This framework shows how AI agents can augment human planners by systematically exploring solution spaces, verifying regulatory compliance, and deliberating over trade-offs transparently -- not replacing human judgment but amplifying it with computational reasoning capabilities. --- ### Dense Motion Captioning Authors: Shiyao Xu, Benedetta Liberatori, Gül Varol, Paolo Rota Published: 2025-11-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05369v1 Recent advances in 3D human motion and language integration have primarily focused on text-to-motion generation, leaving the task of motion understanding relatively unexplored. We introduce Dense Motion Captioning, a novel task that aims to temporally localize and caption actions within 3D human motion sequences. Current datasets fall short in providing detailed temporal annotations and predominantly consist of short sequences featuring few actions. To overcome these limitations, we present the Complex Motion Dataset (CompMo), the first large-scale dataset featuring richly annotated, complex motion sequences with precise temporal boundaries. Built through a carefully designed data generation pipeline, CompMo includes 60,000 motion sequences, each composed of multiple actions ranging from at least two to ten, accurately annotated with their temporal extents. We further present DEMO, a model that integrates a large language model with a simple motion adapter, trained to generate dense, temporally grounded captions. Our experiments show that DEMO substantially outperforms existing methods on CompMo as well as on adapted benchmarks, establishing a robust baseline for future research in 3D motion understanding and captioning. --- ### Near-Efficient and Non-Asymptotic Multiway Inference Authors: Oscar López, Arvind Prasadan, Carlos Llosa-Vite, Richard B. Lehoucq, Daniel M. Dunlavy Published: 2025-11-07 Categories: math.ST, math.NA, stat.ML arXiv: https://arxiv.org/abs/2511.05368v1 We establish non-asymptotic efficiency guarantees for tensor decomposition-based inference in count data models. Under a Poisson framework, we consider two related goals: (i) parametric inference, the estimation of the full distributional parameter tensor, and (ii) multiway analysis, the recovery of its canonical polyadic (CP) decomposition factors. Our main result shows that in the rank-one setting, a rank-constrained maximum-likelihood estimator achieves multiway analysis with variance matching the Cramér-Rao Lower Bound (CRLB) up to absolute constants and logarithmic factors. This provides a general framework for studying "near-efficient" multiway estimators in finite-sample settings. For higher ranks, we illustrate that our multiway estimator may not attain the CRLB; nevertheless, CP-based parametric inference remains nearly minimax optimal, with error bounds that improve on prior work by offering more favorable dependence on the CP rank. Numerical experiments corroborate near-efficiency in the rank-one case and highlight the efficiency gap in higher-rank scenarios. --- ### AI Literacy for Community Colleges: Instructors' Perspectives on Scenario-Based and Interactive Approaches to Teaching AI Authors: Aparna Maya Warrier, Arav Agarwal, Jaromir Savelka, Christopher A Bogart, Heather Burte Published: 2025-11-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.05363v1 This research category full paper investigates how community college instructors evaluate interactive, no-code AI literacy resources designed for non-STEM learners. As artificial intelligence becomes increasingly integrated into everyday technologies, AI literacy - the ability to evaluate AI systems, communicate with them, and understand their broader impacts - has emerged as a critical skill across disciplines. Yet effective, scalable approaches for teaching these concepts in higher education remain limited, particularly for students outside STEM fields. To address this gap, we developed AI User, an interactive online curriculum that introduces core AI concepts through scenario - based activities set in real - world contexts. This study presents findings from four focus groups with instructors who engaged with AI User materials and participated in structured feedback activities. Thematic analysis revealed that instructors valued exploratory tasks that simulated real - world AI use cases and fostered experimentation, while also identifying challenges related to scaffolding, accessibility, and multi-modal support. A ranking task for instructional support materials showed a strong preference for interactive demonstrations over traditional educational materials like conceptual guides or lecture slides. These findings offer insights into instructor perspectives on making AI concepts more accessible and relevant for broad learner audiences. They also inform the design of AI literacy tools that align with diverse teaching contexts and support critical engagement with AI in higher education. --- ### A multimodal multiplex of the mental lexicon for multilingual individuals Authors: Maria Huynh, Wilder C. Rodrigues Published: 2025-11-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.05361v1 Historically, bilingualism was often perceived as an additional cognitive load that could hinder linguistic and intellectual development. However, over the last three decades, this view has changed considerably. Numerous studies have aimed to model and understand the architecture of the bilingual word recognition system Dijkstra and van Heuven (2002), investigating how parallel activation operates in the brain and how one language influences another Kroll et al. (2015). Increasingly, evidence suggests that multilinguals, individuals who speak three or more languages, can perform better than monolinguals in various linguistic and cognitive tasks, such as learning an additional language Abu-Rabia and Sanitsky (2010). This research proposal focuses on the study of the mental lexicon and how it may be structured in individuals who speak multiple languages. Building on the work of Stella et al. (2018), who investigated explosive learning in humans using a multiplex model of the mental lexicon, and the Bilingual Interactive Activation (BIA+) framework proposed by Dijkstra and van Heuven (2002), the present study applies the same multilayer network principles introduced by Kivela et al. (2014). Our experimental design extends previous research by incorporating multimodality into the multiplex model, introducing an additional layer that connects visual inputs to their corresponding lexical representations across the multilingual layers of the mental lexicon. In this research, we aim to explore how a heritage language influences the acquisition of another language. Specifically, we ask: Does the presence of visual input in a translation task influence participants' proficiency and accuracy compared to text-only conditions? --- ### Neural Image Abstraction Using Long Smoothing B-Splines Authors: Daniel Berio, Michael Stroh, Sylvain Calinon, Frederic Fol Leymarie, Oliver Deussen, Ariel Shamir Published: 2025-11-07 Categories: cs.GR, cs.CV arXiv: https://arxiv.org/abs/2511.05360v1 We integrate smoothing B-splines into a standard differentiable vector graphics (DiffVG) pipeline through linear mapping, and show how this can be used to generate smooth and arbitrarily long paths within image-based deep learning systems. We take advantage of derivative-based smoothing costs for parametric control of fidelity vs. simplicity tradeoffs, while also enabling stylization control in geometric and image spaces. The proposed pipeline is compatible with recent vector graphics generation and vectorization methods. We demonstrate the versatility of our approach with four applications aimed at the generation of stylized vector graphics: stylized space-filling path generation, stroke-based image abstraction, closed-area image abstraction, and stylized text generation. --- ### ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations Authors: Amr Gomaa, Ahmed Salem, Sahar Abdelnabi Published: 2025-11-07 Categories: cs.CR, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2511.05359v1 As language models evolve into autonomous agents that act and communicate on behalf of users, ensuring safety in multi-agent ecosystems becomes a central challenge. Interactions between personal assistants and external service providers expose a core tension between utility and protection: effective collaboration requires information sharing, yet every exchange creates new attack surfaces. We introduce ConVerse, a dynamic benchmark for evaluating privacy and security risks in agent-agent interactions. ConVerse spans three practical domains (travel, real estate, insurance) with 12 user personas and over 864 contextually grounded attacks (611 privacy, 253 security). Unlike prior single-agent settings, it models autonomous, multi-turn agent-to-agent conversations where malicious requests are embedded within plausible discourse. Privacy is tested through a three-tier taxonomy assessing abstraction quality, while security attacks target tool use and preference manipulation. Evaluating seven state-of-the-art models reveals persistent vulnerabilities; privacy attacks succeed in up to 88% of cases and security breaches in up to 60%, with stronger models leaking more. By unifying privacy and security within interactive multi-agent contexts, ConVerse reframes safety as an emergent property of communication. --- ### Diffusion-Based Electromagnetic Inverse Design of Scattering Structured Media Authors: Mikhail Tsukerman, Konstantin Grotov, Pavel Ginzburg Published: 2025-11-07 Categories: cs.LG, physics.app-ph, physics.comp-ph arXiv: https://arxiv.org/abs/2511.05357v1 We present a conditional diffusion model for electromagnetic inverse design that generates structured media geometries directly from target differential scattering cross-section profiles, bypassing expensive iterative optimization. Our 1D U-Net architecture with Feature-wise Linear Modulation learns to map desired angular scattering patterns to 2x2 dielectric sphere structure, naturally handling the non-uniqueness of inverse problems by sampling diverse valid designs. Trained on 11,000 simulated metasurfaces, the model achieves median MPE below 19% on unseen targets (best: 1.39%), outperforming CMA-ES evolutionary optimization while reducing design time from hours to seconds. These results demonstrate that employing diffusion models is promising for advancing electromagnetic inverse design research, potentially enabling rapid exploration of complex metasurface architectures and accelerating the development of next-generation photonic and wireless communication systems. The code is publicly available at https://github.com/mikzuker/inverse_design_metasurface_generation. --- ### Canonical Space Representation for 4D Panoptic Segmentation of Articulated Objects Authors: Manuel Gomes, Bogdan Raducanu, Miguel Oliveira Published: 2025-11-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.05356v1 Articulated object perception presents significant challenges in computer vision, particularly because most existing methods ignore temporal dynamics despite the inherently dynamic nature of such objects. The use of 4D temporal data has not been thoroughly explored in articulated object perception and remains unexamined for panoptic segmentation. The lack of a benchmark dataset further hurt this field. To this end, we introduce Artic4D as a new dataset derived from PartNet Mobility and augmented with synthetic sensor data, featuring 4D panoptic annotations and articulation parameters. Building on this dataset, we propose CanonSeg4D, a novel 4D panoptic segmentation framework. This approach explicitly estimates per-frame offsets mapping observed object parts to a learned canonical space, thereby enhancing part-level segmentation. The framework employs this canonical representation to achieve consistent alignment of object parts across sequential frames. Comprehensive experiments on Artic4D demonstrate that the proposed CanonSeg4D outperforms state of the art approaches in panoptic segmentation accuracy in more complex scenarios. These findings highlight the effectiveness of temporal modeling and canonical alignment in dynamic object understanding, and pave the way for future advances in 4D articulated object perception. --- ### SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning Authors: Tzu-Yuan Huang, Armin Lederer, Dai-Jie Wu, Xiaobing Dai, Sihua Zhang, Hsiu-Chin Lin, Shao-Hua Sun, Stefan Sosnowski, Sandra Hirche Published: 2025-11-07 Categories: cs.LG, cs.RO, eess.SY arXiv: https://arxiv.org/abs/2511.05355v3 Flow matching (FM) has shown promising results in data-driven planning. However, it inherently lacks formal guarantees for ensuring state and action constraints, whose satisfaction is a fundamental and crucial requirement for the safety and admissibility of planned trajectories on various systems. Moreover, existing FM planners do not ensure the dynamical consistency, which potentially renders trajectories inexecutable. We address these shortcomings by proposing SAD-Flower, a novel framework for generating Safe, Admissible, and Dynamically consistent trajectories. Our approach relies on an augmentation of the flow with a virtual control input. Thereby, principled guidance can be derived using techniques from nonlinear control theory, providing formal guarantees for state constraints, action constraints, and dynamic consistency. Crucially, SAD-Flower operates without retraining, enabling test-time satisfaction of unseen constraints. Through extensive experiments across several tasks, we demonstrate that SAD-Flower outperforms various generative-model-based baselines in ensuring constraint satisfaction. --- ### SAD-Flower: Flow Matching for Safe, Admissible, and Dynamically Consistent Planning Authors: Tzu-Yuan Huang, Armin Lederer, Dai-Jie Wu, Xiaobing Dai, Sihua Zhang, Stefan Sosnowski, Shao-Hua Sun, Sandra Hirche Published: 2025-11-07 Categories: cs.LG, cs.RO, cs.SY, eess.SY arXiv: https://arxiv.org/abs/2511.05355v1 Flow matching (FM) has shown promising results in data-driven planning. However, it inherently lacks formal guarantees for ensuring state and action constraints, whose satisfaction is a fundamental and crucial requirement for the safety and admissibility of planned trajectories on various systems. Moreover, existing FM planners do not ensure the dynamical consistency, which potentially renders trajectories inexecutable. We address these shortcomings by proposing SAD-Flower, a novel framework for generating Safe, Admissible, and Dynamically consistent trajectories. Our approach relies on an augmentation of the flow with a virtual control input. Thereby, principled guidance can be derived using techniques from nonlinear control theory, providing formal guarantees for state constraints, action constraints, and dynamic consistency. Crucially, SAD-Flower operates without retraining, enabling test-time satisfaction of unseen constraints. Through extensive experiments across several tasks, we demonstrate that SAD-Flower outperforms various generative-model-based baselines in ensuring constraint satisfaction. --- ### A Latent-Variable Formulation of the Poisson Canonical Polyadic Tensor Model: Maximum Likelihood Estimation and Fisher Information Authors: Carlos Llosa-Vite, Daniel M. Dunlavy, Richard B. Lehoucq, Oscar López, Arvind Prasadan Published: 2025-11-07 Categories: math.ST, math.NA, stat.ML arXiv: https://arxiv.org/abs/2511.05352v2 We establish parameter inference for the Poisson canonical polyadic (PCP) model of tensor count data through a latent-variable formulation. Our approach exploits the property that any random tensor that follows the PCP model can be derived by marginalizing an unobservable random tensor of one dimension larger. The loglikelihood of this larger dimensional tensor, referred to as the "complete" loglikelihood, is comprised of multiple loglikelihoods corresponding to rank one PCP models. Using this methodology, we first demonstrate that several existing algorithms for fitting non-negative matrix and tensor factorizations are Expectation-Maximization algorithms. Next, we derive the observed and expected Fisher information matrices for the PCP model by leveraging its latent-variable formulation. The Fisher information provides us crucial insights into the well-posedness of the tensor model, such as the role that the rank of parameter tensor plays in identifiability and indeterminacy. For the special case of PCP models with rank one parameter tensors, we demonstrate that these results are greatly simplified. --- ### A Latent-Variable Formulation of the Poisson Canonical Polyadic Tensor Model: Maximum Likelihood Estimation and Fisher Information Authors: Carlos Llosa-Vite, Daniel M. Dunlavy, Richard B. Lehoucq, Oscar López, Arvind Prasadan Published: 2025-11-07 Categories: math.ST, cs.NA, math.NA, stat.ML, stat.TH, 62F99 (Primary) 15A69 (Secondary) arXiv: https://arxiv.org/abs/2511.05352v1 We establish parameter inference for the Poisson canonical polyadic (PCP) tensor model through a latent-variable formulation. Our approach exploits the observation that any random PCP tensor can be derived by marginalizing an unobservable random tensor of one dimension larger. The loglikelihood of this larger dimensional tensor, referred to as the "complete" loglikelihood, is comprised of multiple rank one PCP loglikelihoods. Using this methodology, we first derive non-iterative maximum likelihood estimators for the PCP model and demonstrate that several existing algorithms for fitting non-negative matrix and tensor factorizations are Expectation-Maximization algorithms. Next, we derive the observed and expected Fisher information matrices for the PCP model. The Fisher information provides us crucial insights into the well-posedness of the tensor model, such as the role that tensor rank plays in identifiability and indeterminacy. For the special case of rank one PCP models, we demonstrate that these results are greatly simplified. --- ### Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders Authors: Mathias Rose Bjare, Giorgia Cantisani, Marco Pasini, Stefan Lattner, Gerhard Widmer Published: 2025-11-07 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2511.05350v3 We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptually motivated losses, yields encodings that are structured according to a perceptual hierarchy. We demonstrate the emergence of this hierarchy by showing that, after training an audio autoencoder in this manner, perceptually salient information is captured in coarser representation structures than with conventional training. Furthermore, we show that such perceptual hierarchies improve latent diffusion decoding in the context of estimating pitch surprisal in music and predicting EEG-brain responses to music listening. In both cases, our results surpass those of previous methods. Pretrained weights are available on github.com/CPJKU/pa-audioic. --- ### Perceptually Aligning Representations of Music via Noise-Augmented Autoencoders Authors: Mathias Rose Bjare, Giorgia Cantisani, Marco Pasini, Stefan Lattner, Gerhard Widmer Published: 2025-11-07 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2511.05350v1 We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptual losses, yields encodings that are structured according to a perceptual hierarchy. We demonstrate the emergence of this hierarchical structure by showing that, after training an audio autoencoder in this manner, perceptually salient information is captured in coarser representation structures than with conventional training. Furthermore, we show that such perceptual hierarchies improve latent diffusion decoding in the context of estimating surprisal in music pitches and predicting EEG-brain responses to music listening. Pretrained weights are available on github.com/CPJKU/pa-audioic. --- ### Learning Dynamics from Input-Output Data with Hamiltonian Gaussian Processes Authors: Jan-Hendrik Ewering, Robin E. Herrmann, Niklas Wahlström, Thomas B. Schön, Thomas Seel Published: 2025-11-07 Categories: cs.LG, eess.SY arXiv: https://arxiv.org/abs/2511.05330v2 Embedding non-restrictive prior knowledge, such as energy conservation laws, into learning methods is a key motive to construct physically consistent dynamics models from limited data, relevant for, e.g., model-based control. Recent work incorporates Hamiltonian dynamics into Gaussian Processes (GPs) to obtain uncertainty-quantifying, energy-consistent models, but these methods rely on -- rarely available -- velocity or momentum data. In this paper, we study dynamics learning using Hamiltonian GPs and focus on learning solely from input-output data, without relying on velocity or momentum measurements. Adopting a non-conservative formulation, energy exchange with the environment, e.g., through external forces or dissipation, can be captured. We provide a fully Bayesian scheme for estimating probability densities of unknown hidden states, GP hyperparameters, as well as structural hyperparameters, such as damping coefficients. The proposed method is evaluated in a nonlinear simulation case study and compared to a state-of-the-art approach that relies on momentum measurements. --- ### Learning Dynamics from Input-Output Data with Hamiltonian Gaussian Processes Authors: Jan-Hendrik Ewering, Robin E. Herrmann, Niklas Wahlström, Thomas B. Schön, Thomas Seel Published: 2025-11-07 Categories: cs.LG, cs.SY, eess.SY arXiv: https://arxiv.org/abs/2511.05330v1 Embedding non-restrictive prior knowledge, such as energy conservation laws, in learning-based approaches is a key motive to construct physically consistent models from limited data, relevant for, e.g., model-based control. Recent work incorporates Hamiltonian dynamics into Gaussian Process (GP) regression to obtain uncertainty-quantifying models that adhere to the underlying physical principles. However, these works rely on velocity or momentum data, which is rarely available in practice. In this paper, we consider dynamics learning with non-conservative Hamiltonian GPs, and address the more realistic problem setting of learning from input-output data. We provide a fully Bayesian scheme for estimating probability densities of unknown hidden states, of GP hyperparameters, as well as of structural hyperparameters, such as damping coefficients. Considering the computational complexity of GPs, we take advantage of a reduced-rank GP approximation and leverage its properties for computationally efficient prediction and training. The proposed method is evaluated in a nonlinear simulation case study and compared to a state-of-the-art approach that relies on momentum measurements. --- ### Turning Adversaries into Allies: Reversing Typographic Attacks for Multimodal E-Commerce Product Retrieval Authors: Janet Jenq, Hongda Shen Published: 2025-11-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.05325v1 Multimodal product retrieval systems in e-commerce platforms rely on effectively combining visual and textual signals to improve search relevance and user experience. However, vision-language models such as CLIP are vulnerable to typographic attacks, where misleading or irrelevant text embedded in images skews model predictions. In this work, we propose a novel method that reverses the logic of typographic attacks by rendering relevant textual content (e.g., titles, descriptions) directly onto product images to perform vision-text compression, thereby strengthening image-text alignment and boosting multimodal product retrieval performance. We evaluate our method on three vertical-specific e-commerce datasets (sneakers, handbags, and trading cards) using six state-of-the-art vision foundation models. Our experiments demonstrate consistent improvements in unimodal and multimodal retrieval accuracy across categories and model families. Our findings suggest that visually rendering product metadata is a simple yet effective enhancement for zero-shot multimodal retrieval in e-commerce applications. --- ### Evaluating Subword Tokenization Techniques for Bengali: A Benchmark Study with BengaliBPE Authors: Firoj Ahmmed Patwary, Abdullah Al Noman Published: 2025-11-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.05324v1 Tokenization is an important first step in Natural Language Processing (NLP) pipelines because it decides how models learn and represent linguistic information. However, current subword tokenizers like SentencePiece or HuggingFace BPE are mostly designed for Latin or multilingual corpora and do not perform well on languages with rich morphology such as Bengali. To address this limitation, we present BengaliBPE, a Byte Pair Encoding (BPE) tokenizer specifically developed for the Bengali script. BengaliBPE applies Unicode normalization, grapheme-level initialization, and morphology-aware merge rules to maintain linguistic consistency and preserve subword integrity. We use a large-scale Bengali news classification dataset to compare BengaliBPE with three baselines: Whitespace, SentencePiece BPE, and HuggingFace BPE. The evaluation considers tokenization granularity, encoding speed, and downstream classification accuracy. While all methods perform reasonably well, BengaliBPE provides the most detailed segmentation and the best morphological interpretability, albeit with slightly higher computational cost. These findings highlight the importance of language-aware tokenization for morphologically rich scripts and establish BengaliBPE as a strong foundation for future Bengali NLP systems, including large-scale pretraining of contextual language models. --- ### What Are the Facts? Automated Extraction of Court-Established Facts from Criminal-Court Opinions Authors: Klára Bendová, Tomáš Knap, Jan Černý, Vojtěch Pour, Jaromir Savelka, Ivana Kvapilíková, Jakub Drápal Published: 2025-11-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2511.05320v1 Criminal justice administrative data contain only a limited amount of information about the committed offense. However, there is an unused source of extensive information in continental European courts' decisions: descriptions of criminal behaviors in verdicts by which offenders are found guilty. In this paper, we study the feasibility of extracting these descriptions from publicly available court decisions from Slovakia. We use two different approaches for retrieval: regular expressions and large language models (LLMs). Our baseline was a simple method employing regular expressions to identify typical words occurring before and after the description. The advanced regular expression approach further focused on "sparing" and its normalization (insertion of spaces between individual letters), typical for delineating the description. The LLM approach involved prompting the Gemini Flash 2.0 model to extract the descriptions using predefined instructions. Although the baseline identified descriptions in only 40.5% of verdicts, both methods significantly outperformed it, achieving 97% with advanced regular expressions and 98.75% with LLMs, and 99.5% when combined. Evaluation by law students showed that both advanced methods matched human annotations in about 90% of cases, compared to just 34.5% for the baseline. LLMs fully matched human-labeled descriptions in 91.75% of instances, and a combination of advanced regular expressions with LLMs reached 92%. --- ### $\mathbf{S^2LM}$: Towards Semantic Steganography via Large Language Models Authors: Huanqi Wu, Huangbiao Xu, Yongliang Xu, Jiaxin Cai, Xiao Ke, Hang Cheng Published: 2025-11-07 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2511.05319v3 Despite remarkable progress in steganography, embedding sentence-level information into cover media remains challenging. In this work, we present the concept of \textbf{Semantic-Payload Steganography}, which aims to hide semantically meaningful and structured content, such as sentences, in cover media. Based on this concept, we present Sentence-to-Image Steganography as an instance that enables the hiding of sentence-level messages within a cover image. To accomplish this feat, we propose \textbf{S}emantic-Payload \textbf{S}teganographic \textbf{L}anguage \textbf{M}odel ($\mathbf{S^2LM}$), which leverages large language models to embed high-level textual information into images. $\mathbf{S^2LM}$ redesigns the entire pipeline, involving the LLM throughout the process to enable the hiding and recovery of sentences. To evaluate semantic-payload steganography methods, we establish a benchmark named \textbf{I}n\textbf{v}isible \textbf{T}ext (IVT), comprising a diverse set of corpus as secret messages. Experimental results demonstrate that $\mathbf{S^2LM}$ effectively recovers natural-language messages while maintaining high visual quality. The source code will be released at https://github.com/aoli-gei/S2LM. --- ### $\mathbf{S^2LM}$: Towards Semantic Steganography via Large Language Models Authors: Huanqi Wu, Huangbiao Xu, Runfeng Xie, Jiaxin Cai, Kaixin Zhang, Xiao Ke Published: 2025-11-07 Categories: cs.CV, cs.CR arXiv: https://arxiv.org/abs/2511.05319v1 Although steganography has made significant advancements in recent years, it still struggles to embed semantically rich, sentence-level information into carriers. However, in the era of AIGC, the capacity of steganography is more critical than ever. In this work, we present Sentence-to-Image Steganography, an instance of Semantic Steganography, a novel task that enables the hiding of arbitrary sentence-level messages within a cover image. Furthermore, we establish a benchmark named Invisible Text (IVT), comprising a diverse set of sentence-level texts as secret messages for evaluation. Finally, we present $\mathbf{S^2LM}$: Semantic Steganographic Language Model, which utilizes large language models (LLMs) to embed high-level textual information, such as sentences or even paragraphs, into images. Unlike traditional bit-level counterparts, $\mathrm{S^2LM}$ enables the integration of semantically rich content through a newly designed pipeline in which the LLM is involved throughout the entire process. Both quantitative and qualitative experiments demonstrate that our method effectively unlocks new semantic steganographic capabilities for LLMs. The source code will be released soon. --- ### Controllably Efficient Language Models Authors: Jatin Prakash, Aahlad Puli, Rajesh Ranganath Published: 2025-11-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.05313v2 The substantial inference costs of attention in transformers motivated the development of efficient sequence mixers: namely sparse and sliding window attention, convolutions and linear attention. Although these approaches result in impressive reductions in inference costs, they often trade-off with quality, specifically in-context recall. Apriori fixing this quality-cost tradeoff at training time means being suboptimal from the get-go: some downstream applications might fundamentally require more memory for in-context recall, while other tasks may require lower latency and memory. We propose a conceptually simple meta-sequence mixer with inference-cost controllability: the Compress & Attend Transformer (CAT). CAT decodes chunks of tokens by attending to compressed chunks of the sequence so far. Both compression and decoding can use any existing sequence mixer. Decoding from the compressed sequence yields compute and memory savings, with chunk size setting the operating point on the quality-cost trade-off. Importantly, training CAT across multiple chunk sizes at once unlocks test-time control of this trade-off without any retraining, all in a single model. Instantiated with the most basic choice, dense attention as the mixer, CAT surprisingly suffices to match 10 popular and diverse efficient models (linear, hybrids, sparse) on real-world long-context recall at comparable inference costs, all from a single trained model. CAT further performs competitively on long-context understanding benchmarks while providing 1.4-3.7x higher generation throughput than a dense transformer. Code is at: https://github.com/rajesh-lab/cat-transformer ---