# Research Papers — 2025-11 · bundle page 81 of 197 > Full-text markdown of papers #4001–4050 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/81 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/80.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/82.md) ### PuzzlePoles: Cylindrical Fiducial Markers Based on the PuzzleBoard Pattern Authors: Juri Zach, Peer Stelldinger Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.19448v1 Reliable perception of the environment is a key enabler for autonomous systems, where calibration and localization tasks often rely on robust visual markers. We introduce the PuzzlePole, a new type of fiducial markers derived from the recently proposed PuzzleBoard calibration pattern. The PuzzlePole is a cylindrical marker, enabling reliable recognition and pose estimation from 360° viewing direction. By leveraging the unique combinatorial structure of the PuzzleBoard pattern, PuzzlePoles provide a high accuracy in localization and orientation while being robust to occlusions. The design offers flexibility for deployment in diverse autonomous systems scenarios, ranging from robot navigation and SLAM to tangible interfaces. --- ### An Ecologically-Informed Deep Learning Framework for Interpretable and Validatable Habitat Mapping Authors: Iván Felipe Benavides-Martínez, Cristiam Victoriano Portilla-Cabrera, Katherine E. Mills, Claire Enterline, José Garcés-Vargas, Andrew J. Allyn, Auroop R Ganguly Published: 2025-11-18 Categories: q-bio.PE, cs.LG arXiv: https://arxiv.org/abs/2511.17627v1 Benthic habitat is challenging due to the environmental complexity of the seafloor, technological limitations, and elevated operational costs, especially in under-explored regions. This generates knowledge gaps for the sustainable management of hydrobiological resources and their nexus with society. We developed ECOSAIC (Ecological Compression via Orthogonal Specialized Autoencoders for Interpretable Classification), an Artificial Intelligence framework for automatic classification of benthic habitats through interpretable latent representations using a customizable autoencoder. ECOSAIC compresses n-dimensional feature space by optimizing specialization and orthogonality between domain-informed features. We employed two domain-informed categories: biogeochemical and hydrogeomorphological, that together integrate biological, physicochemical, hydrological and geomorphological, features, whose constraints on habitats have been recognized in ecology for a century. We applied the model to the Colombian Pacific Ocean and the results revealed 16 benthic habitats, expanding from mangroves to deep rocky areas up to 1000 m depth. The candidate habitats exhibited a strong correspondence between their environmental constraints, represented in latent space, and their expected species composition. This correspondence reflected meaningful ecological associations rather than purely statistical correlations, where the habitat's environmental offerings align semantically with the species' requirements. This approach could improve the management and conservation of benthic habitats, facilitating the development of functional maps that support marine planning, biodiversity conservation and fish stock assessment. We also hope it provides new insights into how ecological principles can inform AI frameworks, particularly given the substantial data limitations that characterize ecological research. --- ### Efficient Large-Scale Learning of Minimax Risk Classifiers Authors: Kartheek Bondugula, Santiago Mazuelas, Aritz Pérez Published: 2025-11-18 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.17626v1 Supervised learning with large-scale data usually leads to complex optimization problems, especially for classification tasks with multiple classes. Stochastic subgradient methods can enable efficient learning with a large number of samples for classification techniques that minimize the average loss over the training samples. However, recent techniques, such as minimax risk classifiers (MRCs), minimize the maximum expected loss and are not amenable to stochastic subgradient methods. In this paper, we present a learning algorithm based on the combination of constraint and column generation that enables efficient learning of MRCs with large-scale data for classification tasks with multiple classes. Experiments on multiple benchmark datasets show that the proposed algorithm provides upto a 10x speedup for general large-scale data and around a 100x speedup with a sizeable number of classes. --- ### QML-HCS: A Hypercausal Quantum Machine Learning Framework for Non-Stationary Environments Authors: Hector E Mozo Published: 2025-11-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.17624v1 QML-HCS is a research-grade framework for constructing and analyzing quantum-inspired machine learning models operating under hypercausal feedback dynamics. Hypercausal refers to AI systems that leverage extended, deep, or nonlinear causal relationships (expanded causality) to reason, predict, and infer states beyond the capabilities of traditional causal models. Current machine learning and quantum-inspired systems struggle in non-stationary environments, where data distributions drift and models lack mechanisms for continuous adaptation, causal stability, and coherent state updating. QML-HCS addresses this limitation through a unified computational architecture that integrates quantum-inspired superposition principles, dynamic causal feedback, and deterministic-stochastic hybrid execution to enable adaptive behavior in changing environments. The framework implements a hypercausal processing core capable of reversible transformations, multipath causal propagation, and evaluation of alternative states under drift. Its architecture incorporates continuous feedback to preserve causal consistency and adjust model behavior without requiring full retraining. QML-HCS provides a reproducible and extensible Python interface backed by efficient computational routines, enabling experimentation in quantum-inspired learning, causal reasoning, and hybrid computation without the need for specialized hardware. A minimal simulation demonstrates how a hypercausal model adapts to a sudden shift in the input distribution while preserving internal coherence. This initial release establishes the foundational architecture for future theoretical extensions, benchmarking studies, and integration with classical and quantum simulation platforms. --- ### M$^2$OE$^2$-GL: A Family of Probabilistic Load Forecasters That Scales to Massive Customers Authors: Haoran Li, Zhe Cheng, Muhao Guo, Yang Weng, Yannan Sun, Victor Tran, John Chainaranont Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.17623v1 Probabilistic load forecasting is widely studied and underpins power system planning, operation, and risk-aware decision making. Deep learning forecasters have shown strong ability to capture complex temporal and contextual patterns, achieving substantial accuracy gains. However, at the scale of thousands or even hundreds of thousands of loads in large distribution feeders, a deployment dilemma emerges: training and maintaining one model per customer is computationally and storage intensive, while using a single global model ignores distributional shifts across customer types, locations, and phases. Prior work typically focuses on single-load forecasters, global models across multiple loads, or adaptive/personalized models for relatively small settings, and rarely addresses the combined challenges of heterogeneity and scalability in large feeders. We propose M2OE2-GL, a global-to-local extension of the M2OE2 probabilistic forecaster. We first pretrain a single global M2OE2 base model across all feeder loads, then apply lightweight fine-tuning to derive a compact family of group-specific forecasters. Evaluated on realistic utility data, M2OE2-GL yields substantial error reductions while remaining scalable to very large numbers of loads. --- ### Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identification Authors: Weidao Chen, Yuxiao Yang, Yueming Wang Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.17622v1 Major Depressive Disorder (MDD), affecting millions worldwide, exhibits complex pathophysiology manifested through disrupted brain network dynamics. Although graph neural networks that leverage neuroimaging data have shown promise in depression diagnosis, existing approaches are predominantly data-driven and operate largely as black-box models, lacking neurobiological interpretability. Here, we present NH-GCAT (Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks), a novel framework that bridges neuroscience domain knowledge with deep learning by explicitly and hierarchically modeling depression-specific mechanisms at different spatial scales. Our approach introduces three key technical contributions: (1) at the local brain regional level, we design a residual gated fusion module that integrates temporal blood oxygenation level dependent (BOLD) dynamics with functional connectivity patterns, specifically engineered to capture local depression-relevant low-frequency neural oscillations; (2) at the multi-regional circuit level, we propose a hierarchical circuit encoding scheme that aggregates regional node representations following established depression neurocircuitry organization, and (3) at the multi-circuit network level, we develop a variational latent causal attention mechanism that leverages a continuous probabilistic latent space to infer directed information flow among critical circuits, characterizing disease-altered whole-brain inter-circuit interactions. Rigorous leave-one-site-out cross-validation on the REST-meta-MDD dataset demonstrates NH-GCAT's state-of-the-art performance in depression classification, achieving a sample-size weighted-average accuracy of 73.3\% and an AUROC of 76.4\%, while simultaneously providing neurobiologically meaningful explanations. --- ### From Competition to Coordination: Market Making as a Scalable Framework for Safe and Aligned Multi-Agent LLM Systems Authors: Brendan Gho, Suman Muppavarapu, Afnan Shaik, Tyson Tsay, Atharva Mohan, James Begin, Kevin Zhu, Archana Vaidheeswaran, Vasu Sharma Published: 2025-11-18 Categories: cs.MA, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2511.17621v2 As foundation models are increasingly deployed as interacting agents in multi-agent systems, their collective behavior raises new challenges for trustworthiness, transparency, and accountability. Traditional coordination mechanisms, such as centralized oversight or adversarial adjudication, struggle to scale and often obscure how decisions emerge. We introduce a market-making framework for multi-agent large language model (LLM) coordination that organizes agent interactions as structured economic exchanges. In this setup, each agent acts as a market participant, updating and trading probabilistic beliefs, to converge toward shared, truthful outcomes. By aligning local incentives with collective epistemic goals, the framework promotes self-organizing, verifiable reasoning without requiring external enforcement. Empirically, we evaluate this approach across factual reasoning, ethical judgment, and commonsense inference tasks. Market-based coordination yields accuracy gains of up to 10% over single-shot baselines while preserving interpretability and transparency of intermediate reasoning steps. Beyond these improvements, our findings demonstrate that economic coordination principles can operationalize accountability and robustness in multi-agent LLM systems, offering a scalable pathway toward self-correcting, socially responsible AI capable of maintaining trust and oversight in real world deployment scenarios. --- ### Rethinking the Encoding and Annotating of 3D Bounding Box: Corner-Aware 3D Object Detection from Point Clouds Authors: Qinghao Meng, Junbo Yin, Jianbing Shen, Yunde Jia Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17619v1 Center-aligned regression remains dominant in LiDAR-based 3D object detection, yet it suffers from fundamental instability: object centers often fall in sparse or empty regions of the bird's-eye-view (BEV) due to the front-surface-biased nature of LiDAR point clouds, leading to noisy and inaccurate bounding box predictions. To circumvent this limitation, we revisit bounding box representation and propose corner-aligned regression, which shifts the prediction target from unstable centers to geometrically informative corners that reside in dense, observable regions. Leveraging the inherent geometric constraints among corners and image 2D boxes, partial parameters of 3D bounding boxes can be recovered from corner annotations, enabling a weakly supervised paradigm without requiring complete 3D labels. We design a simple yet effective corner-aware detection head that can be plugged into existing detectors. Experiments on KITTI show our method improves performance by 3.5% AP over center-based baseline, and achieves 83% of fully supervised accuracy using only BEV corner clicks, demonstrating the effectiveness of our corner-aware regression strategy. --- ### Foundational Question Generation for Video Question Answering via an Embedding-Integrated Approach Authors: Ju-Young Oh Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17618v1 Conventional VQA approaches primarily rely on question-answer (Q&A) pairs to learn the spatio-temporal dynamics of video content. However, most existing annotations are event-centric, which restricts the model's ability to capture the comprehensive context of a scene. The lack of fundamental information such as object categories, spatial configurations, and descriptive visual attributes prevents the model from forming a complete understanding of the environment, ultimately limiting its generalization and reasoning capability. In this paper, we introduce Foundational Question Generation for Video Question Answering via an Embedding-Integrated Approach (FIQ), a framework designed to enhance the reasoning capability of VQA models by improving their foundational comprehension of video content. FIQ generates Q&A pairs from descriptive information extracted directly from videos, thereby enriching the dataset with core scene-level attributes. These generated pairs help the model develop a more holistic understanding of the video, leading to improved generalizability and reasoning performance. In addition, we propose a VQ-CAlign module that aligns task-specific question embeddings with corresponding visual features, preserving essential contextual cues and enhancing adaptability to downstream tasks. Experimental results on the SUTD-TrafficQA dataset demonstrate that FIQ achieves state-of-the-art performance, surpassing existing baseline approaches. --- ### Tensor Gauge Flow Models Authors: Alexander Strunk, Roland Assam Published: 2025-11-18 Categories: cs.LG, cs.AI, math.DG arXiv: https://arxiv.org/abs/2511.17616v1 This paper introduces Tensor Gauge Flow Models, a new class of Generative Flow Models that generalize Gauge Flow Models and Higher Gauge Flow Models by incorporating higher-order Tensor Gauge Fields into the Flow Equation. This extension allows the model to encode richer geometric and gauge-theoretic structure in the data, leading to more expressive flow dynamics. Experiments on Gaussian mixture models show that Tensor Gauge Flow Models achieve improved generative performance compared to both standard and gauge flow baselines. --- ### Plug-and-Play Multi-Concept Adaptive Blending for High-Fidelity Text-to-Image Synthesis Authors: Young-Beom Woo Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.17615v1 Integrating multiple personalized concepts into a single image has recently become a significant area of focus within Text-to-Image (T2I) generation. However, existing methods often underperform on complex multi-object scenes due to unintended alterations in both personalized and non-personalized regions. This not only fails to preserve the intended prompt structure but also disrupts interactions among regions, leading to semantic inconsistencies. To address this limitation, we introduce plug-and-play multi-concept adaptive blending for high-fidelity text-to-image synthesis (PnP-MIX), an innovative, tuning-free approach designed to seamlessly embed multiple personalized concepts into a single generated image. Our method leverages guided appearance attention to faithfully reflect the intended appearance of each personalized concept. To further enhance compositional fidelity, we present a mask-guided noise mixing strategy that preserves the integrity of non-personalized regions such as the background or unrelated objects while enabling the precise integration of personalized objects. Finally, to mitigate concept leakage, i.e., the inadvertent leakage of personalized concept features into other regions, we propose background dilution++, a novel strategy that effectively reduces such leakage and promotes accurate localization of features within personalized regions. Extensive experimental results demonstrate that PnP-MIX consistently surpasses existing methodologies in both single- and multi-concept personalization scenarios, underscoring its robustness and superior performance without additional model tuning. --- ### HSMix: Hard and Soft Mixing Data Augmentation for Medical Image Segmentation Authors: Danyang Sun, Fadi Dornaika, Nagore Barrena Published: 2025-11-18 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2511.17614v1 Due to the high cost of annotation or the rarity of some diseases, medical image segmentation is often limited by data scarcity and the resulting overfitting problem. Self-supervised learning and semi-supervised learning can mitigate the data scarcity challenge to some extent. However, both of these paradigms are complex and require either hand-crafted pretexts or well-defined pseudo-labels. In contrast, data augmentation represents a relatively simple and straightforward approach to addressing data scarcity issues. It has led to significant improvements in image recognition tasks. However, the effectiveness of local image editing augmentation techniques in the context of segmentation has been less explored. We propose HSMix, a novel approach to local image editing data augmentation involving hard and soft mixing for medical semantic segmentation. In our approach, a hard-augmented image is created by combining homogeneous regions (superpixels) from two source images. A soft mixing method further adjusts the brightness of these composed regions with brightness mixing based on locally aggregated pixel-wise saliency coefficients. The ground-truth segmentation masks of the two source images undergo the same mixing operations to generate the associated masks for the augmented images. Our method fully exploits both the prior contour and saliency information, thus preserving local semantic information in the augmented images while enriching the augmentation space with more diversity. Our method is a plug-and-play solution that is model agnostic and applicable to a range of medical imaging modalities. Extensive experimental evidence has demonstrated its effectiveness in a variety of medical segmentation tasks. The source code is available in https://github.com/DanielaPlusPlus/HSMix. --- ### Unified Low-Light Traffic Image Enhancement via Multi-Stage Illumination Recovery and Adaptive Noise Suppression Authors: Siddiqua Namrah Published: 2025-11-18 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.17612v1 Enhancing low-light traffic images is crucial for reliable perception in autonomous driving, intelligent transportation, and urban surveillance systems. Nighttime and dimly lit traffic scenes often suffer from poor visibility due to low illumination, noise, motion blur, non-uniform lighting, and glare from vehicle headlights or street lamps, which hinder tasks such as object detection and scene understanding. To address these challenges, we propose a fully unsupervised multi-stage deep learning framework for low-light traffic image enhancement. The model decomposes images into illumination and reflectance components, progressively refined by three specialized modules: (1) Illumination Adaptation, for global and local brightness correction; (2) Reflectance Restoration, for noise suppression and structural detail recovery using spatial-channel attention; and (3) Over-Exposure Compensation, for reconstructing saturated regions and balancing scene luminance. The network is trained using self-supervised reconstruction, reflectance smoothness, perceptual consistency, and domain-aware regularization losses, eliminating the need for paired ground-truth images. Experiments on general and traffic-specific datasets demonstrate superior performance over state-of-the-art methods in both quantitative metrics (PSNR, SSIM, LPIPS, NIQE) and qualitative visual quality. Our approach enhances visibility, preserves structure, and improves downstream perception reliability in real-world low-light traffic scenarios. --- ### AI-driven Generation of MALDI-TOF MS for Microbial Characterization Authors: Lucía Schmidt-Santiago, David Rodríguez-Temporal, Carlos Sevilla-Salcedo, Vanessa Gómez-Verdejo Published: 2025-11-18 Categories: cs.LG, q-bio.QM arXiv: https://arxiv.org/abs/2511.17611v1 Matrix-Assisted Laser Desorption/Ionization Time-of-Flight Mass Spectrometry (MALDI-TOF MS) has become a cornerstone technology in clinical microbiology, enabling rapid and accurate microbial identification. However, the development of data-driven diagnostic models remains limited by the lack of sufficiently large, balanced, and standardized spectral datasets. This study investigates the use of deep generative models to synthesize realistic MALDI-TOF MS spectra, aiming to overcome data scarcity and support the development of robust machine learning tools in microbiology. We adapt and evaluate three generative models, Variational Autoencoders (MALDIVAEs), Generative Adversarial Networks (MALDIGANs), and Denoising Diffusion Probabilistic Model (MALDIffusion), for the conditional generation of microbial spectra guided by species labels. Generation is conditioned on species labels, and spectral fidelity and diversity are assessed using diverse metrics. Our experiments show that synthetic data generated by MALDIVAE, MALDIGAN, and MALDIffusion are statistically and diagnostically comparable to real measurements, enabling classifiers trained exclusively on synthetic samples to reach performance levels similar to those trained on real data. While all models faithfully reproduce the peak structure and variability of MALDI-TOF spectra, MALDIffusion obtains this fidelity at a substantially higher computational cost, and MALDIGAN shows competitive but slightly less stable behaviour. In contrast, MALDIVAE offers the most favorable balance between realism, stability, and efficiency. Furthermore, augmenting minority species with synthetic spectra markedly improves classification accuracy, effectively mitigating class imbalance and domain mismatch without compromising the authenticity of the generated data. --- ### Finding Pre-Injury Patterns in Triathletes from Lifestyle, Recovery and Load Dynamics Features Authors: Leonardo Rossi, Bruno Rodrigues Published: 2025-11-18 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.17610v1 Triathlon training, which involves high-volume swimming, cycling, and running, places athletes at substantial risk for overuse injuries due to repetitive physiological stress. Current injury prediction approaches primarily rely on training load metrics, often neglecting critical factors such as sleep quality, stress, and individual lifestyle patterns that significantly influence recovery and injury susceptibility. We introduce a novel synthetic data generation framework tailored explicitly for triathlon. This framework generates physiologically plausible athlete profiles, simulates individualized training programs that incorporate periodization and load-management principles, and integrates daily-life factors such as sleep quality, stress levels, and recovery states. We evaluated machine learning models (LASSO, Random Forest, and XGBoost) showing high predictive performance (AUC up to 0.86), identifying sleep disturbances, heart rate variability, and stress as critical early indicators of injury risk. This wearable-driven approach not only enhances injury prediction accuracy but also provides a practical solution to overcoming real-world data limitations, offering a pathway toward a holistic, context-aware athlete monitoring. --- ### 3D Ground Truth Reconstruction from Multi-Camera Annotations Using UKF Authors: Linh Van Ma, Unse Fatima, Tepy Sokun Chriv, Haroon Imran, Moongu Jeon Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.17609v1 Accurate 3D ground truth estimation is critical for applications such as autonomous navigation, surveillance, and robotics. This paper introduces a novel method that uses an Unscented Kalman Filter (UKF) to fuse 2D bounding box or pose keypoint ground truth annotations from multiple calibrated cameras into accurate 3D ground truth. By leveraging human-annotated ground-truth 2D, our proposed method, a multi-camera single-object tracking algorithm, transforms 2D image coordinates into robust 3D world coordinates through homography-based projection and UKF-based fusion. Our proposed algorithm processes multi-view data to estimate object positions and shapes while effectively handling challenges such as occlusion. We evaluate our method on the CMC, Wildtrack, and Panoptic datasets, demonstrating high accuracy in 3D localization compared to the available 3D ground truth. Unlike existing approaches that provide only ground-plane information, our method also outputs the full 3D shape of each object. Additionally, the algorithm offers a scalable and fully automatic solution for multi-camera systems using only 2D image annotations. --- ### Robustness of Structured Data Extraction from Perspectively Distorted Documents Authors: Hyakka Nakada, Yoshiyasu Tanaka Published: 2025-11-18 Categories: cs.CV, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2511.17607v1 Optical Character Recognition (OCR) for data extraction from documents is essential to intelligent informatics, such as digitizing medical records and recognizing road signs. Multi-modal Large Language Models (LLMs) can solve this task and have shown remarkable performance. Recently, it has been noticed that the accuracy of data extraction by multi-modal LLMs can be affected when in-plane rotations are present in the documents. However, real-world document images are usually not only in-plane rotated but also perspectively distorted. This study investigates the impacts of such perturbations on the data extraction accuracy for the state-of-the-art model, Gemini-1.5-pro. Because perspective distortions have a high degree of freedom, designing experiments in the same manner as single-parametric rotations is difficult. We observed typical distortions of document images and showed that most of them approximately follow an isosceles-trapezoidal transformation, which allows us to evaluate distortions with a small number of parameters. We were able to reduce the number of independent parameters from eight to two, i.e. rotation angle and distortion ratio. Then, specific entities were extracted from synthetically generated sample documents with varying these parameters. As the performance of LLMs, we evaluated not only a character-recognition accuracy but also a structure-recognition accuracy. Whereas the former represents the classical indicators for optical character recognition, the latter is related to the correctness of reading order. In particular, the structure-recognition accuracy was found to be significantly degraded by document distortion. In addition, we found that this accuracy can be improved by a simple rotational correction. This insight will contribute to the practical use of multi-modal LLMs for OCR tasks. --- ### Energy-based Autoregressive Generation for Neural Population Dynamics Authors: Ningling Ge, Sicheng Dai, Yu Zhu, Shan Yu Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.17606v1 Understanding brain function represents a fundamental goal in neuroscience, with critical implications for therapeutic interventions and neural engineering applications. Computational modeling provides a quantitative framework for accelerating this understanding, but faces a fundamental trade-off between computational efficiency and high-fidelity modeling. To address this limitation, we introduce a novel Energy-based Autoregressive Generation (EAG) framework that employs an energy-based transformer learning temporal dynamics in latent space through strictly proper scoring rules, enabling efficient generation with realistic population and single-neuron spiking statistics. Evaluation on synthetic Lorenz datasets and two Neural Latents Benchmark datasets (MC_Maze and Area2_bump) demonstrates that EAG achieves state-of-the-art generation quality with substantial computational efficiency improvements, particularly over diffusion-based methods. Beyond optimal performance, conditional generation applications show two capabilities: generalizing to unseen behavioral contexts and improving motor brain-computer interface decoding accuracy using synthetic neural data. These results demonstrate the effectiveness of energy-based modeling for neural population dynamics with applications in neuroscience research and neural engineering. Code is available at https://github.com/NinglingGe/Energy-based-Autoregressive-Generation-for-Neural-Population-Dynamics. --- ### Copula Based Fusion of Clinical and Genomic Machine Learning Risk Scores for Breast Cancer Risk Stratification Authors: Agnideep Aich, Sameera Hewage, Md Monzur Murshed Published: 2025-11-18 Categories: cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2511.17605v2 Clinical and gene-expression models predict breast cancer outcomes, but simple linear fusion ignores dependence between their risk scores. Using METABRIC, we tested whether modeling the joint distribution of clinical and gene-expression scores improved stratification of 5-year cancer-specific mortality. We defined clinical and mRNA-expression predictor views, trained classifiers, and obtained out-of-fold probabilities through 5-fold cross-validation. The scores were transformed into pseudo-observations on (0,1)^2 and used to fit Gaussian, Clayton, Gumbel, and Frank copulas. The clinical model discriminated better than the gene-expression model (AUC 0.783 vs 0.721). Frank had the smallest goodness-of-fit statistic, with Gaussian performing similarly. Copula fusion did not improve ROC-AUC over the clinical model. However, joint score groups showed clear survival differences, with patients scoring high on both views having the poorest outcomes. Competing-risks analysis showed the same pattern for cancer-death incidence. We also conducted an external evaluation in independent TCGA data using shared predictors and a harmonized 5-year overall-mortality endpoint. Copula-fused, individual, and simple-fusion scores showed comparable discrimination with overlapping confidence intervals. All received the same METABRIC-based recalibration. No gene met the prespecified stability criterion under repeated cross-validated permutation importance, so gene-level findings were treated as exploratory. Copulas provide an explicit, interpretable description of dependence between clinical and gene-expression risk scores and support descriptive joint-group analyses. This methodological study does not establish superior prediction, validated clinical risk categories, or clinical utility. --- ### BrainHGT: A Hierarchical Graph Transformer for Interpretable Brain Network Analysis Authors: Jiajun Ma, Yongchao Zhang, Chao Zhang, Zhao Lv, Shengbing Pei Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.17604v1 Graph Transformer shows remarkable potential in brain network analysis due to its ability to model graph structures and complex node relationships. Most existing methods typically model the brain as a flat network, ignoring its modular structure, and their attention mechanisms treat all brain region connections equally, ignoring distance-related node connection patterns. However, brain information processing is a hierarchical process that involves local and long-range interactions between brain regions, interactions between regions and sub-functional modules, and interactions among functional modules themselves. This hierarchical interaction mechanism enables the brain to efficiently integrate local computations and global information flow, supporting the execution of complex cognitive functions. To address this issue, we propose BrainHGT, a hierarchical Graph Transformer that simulates the brain's natural information processing from local regions to global communities. Specifically, we design a novel long-short range attention encoder that utilizes parallel pathways to handle dense local interactions and sparse long-range connections, thereby effectively alleviating the over-globalizing issue. To further capture the brain's modular architecture, we designe a prior-guided clustering module that utilizes a cross-attention mechanism to group brain regions into functional communities and leverage neuroanatomical prior to guide the clustering process, thereby improving the biological plausibility and interpretability. Experimental results indicate that our proposed method significantly improves performance of disease identification, and can reliably capture the sub-functional modules of the brain, demonstrating its interpretability. --- ### Beyond Surface-Level Similarity: Hierarchical Contamination Detection for Synthetic Training Data in Foundation Models Authors: Sushant Mehta Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.17602v1 Synthetic data has become essential for training foundation models, yet benchmark contamination threatens evaluation integrity. Although existing detection methods identify token-level overlap, they fail to detect semantic-level contamination where synthetic data conceptually resemble benchmarks without lexical overlap. This gap is critical as foundation models increasingly train on synthetic data that may implicitly encode benchmark knowledge. We propose a hierarchical contamination detection framework operating at four levels: token level, semantic level, reasoning pattern, and performance cliff detection. Through controlled experiments on MMLU, GSM8K and HumanEval, we demonstrate that semantic-level contamination evades existing methods (F1=0.17-0.49) but is effectively detected by our hierarchical approach (F1 = 0.76), with an average improvement of 26. 5\% over state-of-the-art baselines. Our framework provides practitioners with practical tools for audit pipelines and enables responsible deployment of synthetic training data. --- ### Generalizable and Efficient Automated Scoring with a Knowledge-Distilled Multi-Task Mixture-of-Experts Authors: Luyang Fang, Tao Wang, Ping Ma, Xiaoming Zhai Published: 2025-11-18 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.17601v1 Automated scoring of written constructed responses typically relies on separate models per task, straining computational resources, storage, and maintenance in real-world education settings. We propose UniMoE-Guided, a knowledge-distilled multi-task Mixture-of-Experts (MoE) approach that transfers expertise from multiple task-specific large models (teachers) into a single compact, deployable model (student). The student combines (i) a shared encoder for cross-task representations, (ii) a gated MoE block that balances shared and task-specific processing, and (iii) lightweight task heads. Trained with both ground-truth labels and teacher guidance, the student matches strong task-specific models while being far more efficient to train, store, and deploy. Beyond efficiency, the MoE layer improves transfer and generalization: experts develop reusable skills that boost cross-task performance and enable rapid adaptation to new tasks with minimal additions and tuning. On nine NGSS-aligned science-reasoning tasks (seven for training/evaluation and two held out for adaptation), UniMoE-Guided attains performance comparable to per-task models while using $\sim$6$\times$ less storage than maintaining separate students, and $87\times$ less than the 20B-parameter teacher. The method offers a practical path toward scalable, reliable, and resource-efficient automated scoring for classroom and large-scale assessment systems. --- ### SALPA: Spaceborne LiDAR Point Adjustment for Enhanced GEDI Footprint Geolocation Authors: Narumasa Tsutsumida, Rei Mitsuhashi, Yoshito Sawada, Akira Kato Published: 2025-11-18 Categories: eess.IV, cs.LG arXiv: https://arxiv.org/abs/2511.17600v1 Spaceborne Light Detection and Ranging (LiDAR) systems, such as NASA's Global Ecosystem Dynamics Investigation (GEDI), provide forest structure for global carbon assessments. However, geolocation uncertainties (typically 5-15 m) propagate systematically through derived products, undermining forest profile estimates, including carbon stock assessments. Existing correction methods face critical limitations: waveform simulation approaches achieve meter-level accuracy but require high-resolution LiDAR data unavailable in most regions, while terrain-based methods employ deterministic grid searches that may overlook optimal solutions in continuous solution spaces. We present SALPA (Spaceborne LiDAR Point Adjustment), a multi-algorithm optimization framework integrating three optimization paradigms with five distance metrics. Operating exclusively with globally available digital elevation models and geoid data, SALPA explores continuous solution spaces through gradient-based, evolutionary, and swarm intelligence approaches. Validation across contrasting sites: topographically complex Nikko, Japan, and flat Landes, France, demonstrates 15-16% improvements over original GEDI positions and 0.5-2% improvements over the state-of-the-art GeoGEDI algorithm. L-BFGS-B with Area-based metrics achieves optimal accuracy-efficiency trade-offs, while population-based algorithms (genetic algorithms, particle swarm optimization) excel in complex terrain. The platform-agnostic framework facilitates straightforward adaptation to emerging spaceborne LiDAR missions, providing a generalizable foundation for universal geolocation correction essential for reliable global forest monitoring and climate policy decisions. --- ### From Projection to Prediction: Beyond Logits for Scalable Language Models Authors: Jianbing Dong, Jianbin Chang Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.17599v1 Training Large Language Models (LLMs) typically involves a two-stage pipeline at the output layer: hidden states are projected into vocabulary logits via a linear transformation (lm_head), followed by cross-entropy loss computation against target tokens. While conceptually simple, this design incurs substantial overhead. The intermediate logits tensor, with dimensions proportional to batch size, sequence length, and vocabulary size, must be fully materialized in GPU memory, even though only one target token per position is ultimately used. This leads to significant memory footprint and bandwidth comsumption, limiting scalability and slowing training throughput. In this work, we introduce a novel approach to integrates the output projection and loss prediction into a single operation. By directly computing the loss from hidden states and target tokens, our approach bypasses explicit logits materialization. This design reduces memory usage and alleviates bandwidth pressure. Experiments on LLM training demonstrate that our method achieves substantial memory savings and measurable speedups compared to the standard two-stage pipeline, enabling large batch sizes and longer sequences without sacrificing accuracy. Our work highlights the benefits of rethinking the boundary between projection and prediction, offering a practical systems optimization for efficient LLM training. --- ### RAG-Driven Data Quality Governance for Enterprise ERP Systems Authors: Sedat Bin Vedat, Enes Kutay Yarkan, Meftun Akarsu, Recep Kaan Karaman, Arda Sar, Çağrı Çelikbilek, Savaş Saygılı Published: 2025-11-18 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2511.16700v1 Enterprise ERP systems managing hundreds of thousands of employee records face critical data quality challenges when human resources departments perform decentralized manual entry across multiple languages. We present an end-to-end pipeline combining automated data cleaning with LLM-driven SQL query generation, deployed on a production system managing 240,000 employee records over six months. The system operates in two integrated stages: a multi-stage cleaning pipeline that performs translation normalization, spelling correction, and entity deduplication during periodic synchronization from Microsoft SQL Server to PostgreSQL; and a retrieval-augmented generation framework powered by GPT-4o that translates natural-language questions in Turkish, Russian, and English into validated SQL queries. The query engine employs LangChain orchestration, FAISS vector similarity search, and few-shot learning with 500+ validated examples. Our evaluation demonstrates 92.5% query validity, 95.1% schema compliance, and 90.7\% semantic accuracy on 2,847 production queries. The system reduces query turnaround time from 2.3 days to under 5 seconds while maintaining 99.2% uptime, with GPT-4o achieving 46% lower latency and 68% cost reduction versus GPT-3.5. This modular architecture provides a reproducible framework for AI-native enterprise data governance, demonstrating real-world viability at enterprise scale with 4.3/5.0 user satisfaction. --- ### Connecting the Dots: A Machine Learning Ready Dataset for Ionospheric Forecasting Models Authors: Linnea M. Wolniewicz, Halil S. Kelebek, Simone Mestici, Michael D. Vergalla, Giacomo Acciarini, Bala Poduval, Olga Verkhoglyadova, Madhulika Guhathakurta, Thomas E. Berger, Atılım Güneş Baydin, Frank Soboczenski Published: 2025-11-18 Categories: cs.LG, astro-ph.EP, astro-ph.IM arXiv: https://arxiv.org/abs/2511.15743v2 Operational forecasting of the ionosphere remains a critical space weather challenge due to sparse observations, complex coupling across geospatial layers, and a growing need for timely, accurate predictions that support Global Navigation Satellite System (GNSS), communications, aviation safety, as well as satellite operations. As part of the 2025 NASA Heliolab, we present a curated, open-access dataset that integrates diverse ionospheric and heliospheric measurements into a coherent, machine learning-ready structure, designed specifically to support next-generation forecasting models and address gaps in current operational frameworks. Our workflow integrates a large selection of data sources comprising Solar Dynamic Observatory data, solar irradiance indices (F10.7), solar wind parameters (velocity and interplanetary magnetic field), geomagnetic activity indices (Kp, AE, SYM-H), and NASA JPL's Global Ionospheric Maps of Total Electron Content (GIM-TEC). We also implement geospatially sparse data such as the TEC derived from the World-Wide GNSS Receiver Network and crowdsourced Android smartphone measurements. This novel heterogeneous dataset is temporally and spatially aligned into a single, modular data structure that supports both physical and data-driven modeling. Leveraging this dataset, we train and benchmark several spatiotemporal machine learning architectures for forecasting vertical TEC under both quiet and geomagnetically active conditions. This work presents an extensive dataset and modeling pipeline that enables exploration of not only ionospheric dynamics but also broader Sun-Earth interactions, supporting both scientific inquiry and operational forecasting efforts. --- ### Uncertainty-Resilient Multimodal Learning via Consistency-Guided Cross-Modal Transfer Authors: Hyo-Jeong Jang Published: 2025-11-18 Categories: cs.AI, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2511.15741v1 Multimodal learning systems often face substantial uncertainty due to noisy data, low-quality labels, and heterogeneous modality characteristics. These issues become especially critical in human-computer interaction settings, where data quality, semantic reliability, and annotation consistency vary across users and recording conditions. This thesis tackles these challenges by exploring uncertainty-resilient multimodal learning through consistency-guided cross-modal transfer. The central idea is to use cross-modal semantic consistency as a basis for robust representation learning. By projecting heterogeneous modalities into a shared latent space, the proposed framework mitigates modality gaps and uncovers structural relations that support uncertainty estimation and stable feature learning. Building on this foundation, the thesis investigates strategies to enhance semantic robustness, improve data efficiency, and reduce the impact of noise and imperfect supervision without relying on large, high-quality annotations. Experiments on multimodal affect-recognition benchmarks demonstrate that consistency-guided cross-modal transfer significantly improves model stability, discriminative ability, and robustness to noisy or incomplete supervision. Latent space analyses further show that the framework captures reliable cross-modal structure even under challenging conditions. Overall, this thesis offers a unified perspective on resilient multimodal learning by integrating uncertainty modeling, semantic alignment, and data-efficient supervision, providing practical insights for developing reliable and adaptive brain-computer interface systems. --- ### Extending Test-Time Scaling: A 3D Perspective with Context, Batch, and Turn Authors: Chao Yu, Qixin Tan, Jiaxuan Gao, Shi Yu, Hong Lu, Xinting Yang, Zelai Xu, Yu Wang, Yi Wu, Eugene Vinitsky Published: 2025-11-18 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.15738v2 Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time as the length of the reasoning context increases. However, compared with training-time scaling, test-time scaling is fundamentally limited by the limited context length of base models, which remains orders of magnitude smaller than the amount of tokens consumed during training. We revisit test-time enhancement techniques through the lens of scaling effect and introduce a unified framework of multi-dimensional test-time scaling to extend the capacity of test-time reasoning. Beyond conventional context-length scaling, we consider two additional dimensions: batch scaling, where accuracy improves with parallel sampling, and turn scaling, where iterative self-refinement enhances reasoning quality. Building on this perspective, we propose 3D test-time scaling, which integrates context, batch, and turn scaling. We show that: (1) each dimension demonstrates a test-time scaling effect, but with a bounded capacity; (2) combining all three dimensions substantially improves the reasoning performance of challenging testbeds, including IOI, IMO, and CPHO, and further benefits from human preference feedback; and (3) the human-in-the-loop framework naturally extends to a more open-ended domain, i.e., embodied learning, which enables the design of humanoid control behaviors. --- ### Sovereign AI: Rethinking Autonomy in the Age of Global Interdependence Authors: Shalabh Kumar Singh, Shubhashis Sengupta Published: 2025-11-18 Categories: cs.CY, cs.AI, econ.GN arXiv: https://arxiv.org/abs/2511.15734v1 Artificial intelligence (AI) is emerging as a foundational general-purpose technology, raising new dilemmas of sovereignty in an interconnected world. While governments seek greater control over it, the very foundations of AI--global data pipelines, semiconductor supply chains, open-source ecosystems, and international standards--resist enclosure. This paper develops a conceptual and formal framework for understanding sovereign AI as a continuum rather than a binary condition, balancing autonomy with interdependence. Drawing on classical theories, historical analogies, and contemporary debates on networked autonomy, we present a planner's model that identifies two policy heuristics: equalizing marginal returns across the four sovereignty pillars and setting openness where global benefits equal exposure risks. We apply the model to India, highlighting sovereign footholds in data, compute, and norms but weaker model autonomy. The near-term challenge is integration via coupled Data x Compute investment, lifecycle governance (ModelOps), and safeguarded procurement. We then apply the model to the Middle East (Saudi Arabia and the UAE), where large public investment in Arabic-first models and sovereign cloud implies high sovereignty weights, lower effective fiscal constraints, and strong Data x Compute complementarities. An interior openness setting with guardrails emerges as optimal. Across contexts, the lesson is that sovereignty in AI needs managed interdependence, not isolation. --- ### Technique to Baseline QE Artefact Generation Aligned to Quality Metrics Authors: Eitan Farchi, Kiran Nayak, Papia Ghosh Majumdar, Saritha Route Published: 2025-11-18 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2511.15733v1 Large Language Models (LLMs) are transforming Quality Engineering (QE) by automating the generation of artefacts such as requirements, test cases, and Behavior Driven Development (BDD) scenarios. However, ensuring the quality of these outputs remains a challenge. This paper presents a systematic technique to baseline and evaluate QE artefacts using quantifiable metrics. The approach combines LLM-driven generation, reverse generation , and iterative refinement guided by rubrics technique for clarity, completeness, consistency, and testability. Experimental results across 12 projects show that reverse-generated artefacts can outperform low-quality inputs and maintain high standards when inputs are strong. The framework enables scalable, reliable QE artefact validation, bridging automation with accountability. --- ### Just Asking Questions: Doing Our Own Research on Conspiratorial Ideation by Generative AI Chatbots Authors: Katherine M. FitzGerald, Michelle Riedlinger, Axel Bruns, Stephen Harrington, Timothy Graham, Daniel Angus Published: 2025-11-18 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2511.15732v1 Interactive chat systems that build on artificial intelligence frameworks are increasingly ubiquitous and embedded into search engines, Web browsers, and operating systems, or are available on websites and apps. Researcher efforts have sought to understand the limitations and potential for harm of generative AI, which we contribute to here. Conducting a systematic review of six AI-powered chat systems (ChatGPT 3.5; ChatGPT 4 Mini; Microsoft Copilot in Bing; Google Search AI; Perplexity; and Grok in Twitter/X), this study examines how these leading products respond to questions related to conspiracy theories. This follows the platform policy implementation audit approach established by Glazunova et al. (2023). We select five well-known and comprehensively debunked conspiracy theories and four emerging conspiracy theories that relate to breaking news events at the time of data collection. Our findings demonstrate that the extent of safety guardrails against conspiratorial ideation in generative AI chatbots differs markedly, depending on chatbot model and conspiracy theory. Our observations indicate that safety guardrails in AI chatbots are often very selectively designed: generative AI companies appear to focus especially on ensuring that their products are not seen to be racist; they also appear to pay particular attention to conspiracy theories that address topics of substantial national trauma such as 9/11 or relate to well-established political issues. Future work should include an ongoing effort extended to further platforms, multiple languages, and a range of conspiracy theories extending well beyond the United States. --- ### Logit-Based Losses Limit the Effectiveness of Feature Knowledge Distillation Authors: Nicholas Cooper, Lijun Chen, Sailesh Dwivedy, Danna Gurari Published: 2025-11-18 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.14981v1 Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model. The status quo for feature KD methods is to utilize loss functions based on logits (i.e., pre-softmax class scores) and intermediate layer features (i.e., latent representations). Unlike previous approaches, we propose a feature KD framework for training the student's backbone using feature-based losses exclusively (i.e., without logit-based losses such as cross entropy). Leveraging recent discoveries about the geometry of latent representations, we introduce a knowledge quality metric for identifying which teacher layers provide the most effective knowledge for distillation. Experiments on three image classification datasets with four diverse student-teacher pairs, spanning convolutional neural networks and vision transformers, demonstrate our KD method achieves state-of-the-art performance, delivering top-1 accuracy boosts of up to 15% over standard approaches. We publically share our code to facilitate future work at https://github.com/Thegolfingocto/KD_wo_CE. --- ### Selective Forgetting in Option Calibration: An Operator-Theoretic Gauss-Newton Framework Authors: Ahmet Umur Özsoy Published: 2025-11-18 Categories: q-fin.MF, cs.LG arXiv: https://arxiv.org/abs/2511.14980v1 Calibration of option pricing models is routinely repeated as markets evolve, yet modern systems lack an operator for removing data from a calibrated model without full retraining. When quotes become stale, corrupted, or subject to deletion requirements, existing calibration pipelines must rebuild the entire nonlinear least-squares problem, even if only a small subset of data must be excluded. In this work, we introduce a principled framework for selective forgetting (machine unlearning) in parametric option calibration. We provide stability guarantees, perturbation bounds, and show that the proposed operators satisfy local exactness under standard regularity assumptions. --- ### SVBRD-LLM: Self-Verifying Behavioral Rule Discovery for Autonomous Vehicle Identification Authors: Xiangyu Li, Tianyi Wang, Junfeng Jiao, Christian Claudel, Zhaomiao Guo Published: 2025-11-18 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2511.14977v3 As autonomous vehicles (AVs) are increasingly deployed on public roads, understanding their real-world behaviors is critical for traffic safety analysis and regulatory oversight. However, many data-driven methods lack interpretability and cannot provide verifiable explanations of AV behavior in mixed traffic. This paper proposes SVBRD-LLM, a self-verifying behavioral rule discovery framework that automatically extracts interpretable behavioral rules from real-world traffic videos through zero-shot large language model (LLM) reasoning. The framework first derives vehicle trajectories using YOLOv26-based detection and ByteTrack-based tracking, then computes kinematic features and contextual information. It then employs GPT-5 zero-shot prompting to perform comparative behavioral analysis between AVs and human-driven vehicles (HDVs) across lane-changing and normal driving behaviors, generating 26 structured rule hypotheses that comprises both numerical thresholds and statistical behavioral patterns. These rules are subsequently evaluated through the AV identification task using an independent validation dataset, and iteratively refined through failure case analysis to filter spurious correlations and improve robustness. The resulting rule library contains 20 high-confidence behavioral rules, each including semantic description, quantitative thresholds or behavioral patterns, applicable context, and validation confidence. Experiments conducted on over 1,500 hours of real-world traffic videos from Waymo's commercial operating area demonstrate that the proposed framework achieves 90.0% accuracy and 93.3% F1-score in AV identification, with 98.0% recall. The discovered rules capture key AV traits in smoothness, conservatism, and lane discipline, informing safety assessment, regulatory compliance, and traffic management in mixed traffic. The dataset is available at: svbrd-llm-roadside-video-av. --- ### Harmful Traits of AI Companions Authors: W. Bradley Knox, Katie Bradford, Samanta Varela Castro, Desmond C. Ong, Sean Williams, Jacob Romanow, Carly Nations, Peter Stone, Samuel Baker Published: 2025-11-18 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2511.14972v2 Amid the growing prevalence of human-AI interaction, large language models and other AI-based entities increasingly provide forms of companionship to human users. Such AI companionship -- i.e., bonded relationships between humans and AI systems that resemble the relationships people have with family members, friends, and romantic partners -- might substantially benefit humans. Yet such relationships can also do profound harm. We propose a framework for analyzing potential negative impacts of AI companionship by identifying specific harmful traits of AI companions and speculatively mapping causal pathways back from these traits to possible causes and forward to potential harmful effects. We provide detailed, structured analysis of four potentially harmful traits -- the absence of natural endpoints for relationships, vulnerability to product sunsetting, high attachment anxiety, and propensity to engender protectiveness -- and briefly discuss fourteen others. For each trait, we propose hypotheses connecting causes -- such as misaligned optimization objectives and the digital nature of AI companions -- to fundamental harms -- including reduced autonomy, diminished quality of human relationships, and deception. Each hypothesized causal connection identifies a target for potential empirical evaluation. Our analysis examines harms at three levels: to human partners directly, to their relationships with other humans, and to society broadly. We examine how existing law struggles to address these emerging harms, discuss potential benefits of AI companions, and conclude with design recommendations for mitigating risks. This analysis offers immediate suggestions for reducing risks while laying a foundation for deeper investigation of this critical but understudied topic. --- ### EGSA-PT:Edge-Guided Spatial Attention with Progressive Training for Monocular Depth Estimation and Segmentation of Transparent Objects Authors: Gbenga Omotara, Ramy Farag, Seyed Mohamad Ali Tousi, G. N. DeSouza Published: 2025-11-18 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2511.14970v1 Transparent object perception remains a major challenge in computer vision research, as transparency confounds both depth estimation and semantic segmentation. Recent work has explored multi-task learning frameworks to improve robustness, yet negative cross-task interactions often hinder performance. In this work, we introduce Edge-Guided Spatial Attention (EGSA), a fusion mechanism designed to mitigate destructive interactions by incorporating boundary information into the fusion between semantic and geometric features. On both Syn-TODD and ClearPose benchmarks, EGSA consistently improved depth accuracy over the current state of the art method (MODEST), while preserving competitive segmentation performance, with the largest improvements appearing in transparent regions. Besides our fusion design, our second contribution is a multi-modal progressive training strategy, where learning transitions from edges derived from RGB images to edges derived from predicted depth images. This approach allows the system to bootstrap learning from the rich textures contained in RGB images, and then switch to more relevant geometric content in depth maps, while it eliminates the need for ground-truth depth at training time. Together, these contributions highlight edge-guided fusion as a robust approach capable of improving transparent object perception. --- ### Quality-Controlled Multimodal Emotion Recognition in Conversations with Identity-Based Transfer Learning and MAMBA Fusion Authors: Zanxu Wang, Homayoon Beigi Published: 2025-11-18 Categories: eess.AS, cs.AI, cs.LG, eess.IV, eess.SP arXiv: https://arxiv.org/abs/2511.14969v1 This paper addresses data quality issues in multimodal emotion recognition in conversation (MERC) through systematic quality control and multi-stage transfer learning. We implement a quality control pipeline for MELD and IEMOCAP datasets that validates speaker identity, audio-text alignment, and face detection. We leverage transfer learning from speaker and face recognition, assuming that identity-discriminative embeddings capture not only stable acoustic and Facial traits but also person-specific patterns of emotional expression. We employ RecoMadeEasy(R) engines for extracting 512-dimensional speaker and face embeddings, fine-tune MPNet-v2 for emotion-aware text representations, and adapt these features through emotion-specific MLPs trained on unimodal datasets. MAMBA-based trimodal fusion achieves 64.8% accuracy on MELD and 74.3% on IEMOCAP. These results show that combining identity-based audio and visual embeddings with emotion-tuned text representations on a quality-controlled subset of data yields consistent competitive performance for multimodal emotion recognition in conversation and provides a basis for further improvement on challenging, low-frequency emotion classes. --- ### MermaidSeqBench: An Evaluation Benchmark for NL-to-Mermaid Sequence Diagram Generation Authors: Basel Shbita, Farhan Ahmed, Chad DeLuca Published: 2025-11-18 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.14967v3 Large language models (LLMs) have shown great promise in generating structured diagrams from natural language descriptions, particularly Mermaid sequence diagrams for software engineering. However, the lack of existing benchmarks to assess the LLM's correctness on this task hinders rigorous, systematic evaluation and principled comparison of model capabilities on this task. To address this shortcoming, we introduce MermaidSeqBench, a human-verified and synthetically extended benchmark for assessing LLM capabilities in generating Mermaid sequence diagrams from natural language prompts. The benchmark consists of 132 samples developed via a hybrid methodology of human-verified flows, LLM-based augmentation, and rule-based expansion. The evaluation uses an LLM-as-a-judge model to assess generation across various fine-grained metrics such as syntax correctness, activation handling, error handling, and practical usability. To demonstrate the effectiveness and flexibility of our benchmark, we perform initial evaluations on numerous state-of-the-art LLMs with multiple LLM judges which reveal significant capability gaps across models and evaluation modes. MermaidSeqBench provides a foundation for evaluating structured diagram generation and advances the scientific understanding of LLM capabilities and limitations in structured generation tasks. --- ### How Should the Law Treat Future AI Systems? Fictional Legal Personhood versus Legal Identity Authors: Heather J. Alexander, Jonathan A. Simon, Frédéric Pinard Published: 2025-11-18 Categories: cs.CY, cs.AI, cs.HC arXiv: https://arxiv.org/abs/2511.14964v1 The law draws a sharp distinction between objects and persons, and between two kinds of persons, the ''fictional'' kind (i.e. corporations), and the ''non-fictional'' kind (individual or ''natural'' persons). This paper will assess whether we maximize overall long-term legal coherence by (A) maintaining an object classification for all future AI systems, (B) creating fictional legal persons associated with suitably advanced, individuated AI systems (giving these fictional legal persons derogable rights and duties associated with certified groups of existing persons, potentially including free speech, contract rights, and standing to sue ''on behalf of'' the AI system), or (C) recognizing non-fictional legal personhood through legal identity for suitably advanced, individuated AI systems (recognizing them as entities meriting legal standing with non-derogable rights which for the human case include life, due process, habeas corpus, freedom from slavery, and freedom of conscience). We will clarify the meaning and implications of each option along the way, considering liability, copyright, family law, fundamental rights, civil rights, citizenship, and AI safety regulation. We will tentatively find that the non-fictional personhood approach may be best from a coherence perspective, for at least some advanced AI systems. An object approach may prove untenable for sufficiently humanoid advanced systems, though we suggest that it is adequate for currently existing systems as of 2025. While fictional personhood would resolve some coherence issues for future systems, it would create others and provide solutions that are neither durable nor fit for purpose. Finally, our review will suggest that ''hybrid'' approaches are likely to fail and lead to further incoherence: the choice between object, fictional person and non-fictional person is unavoidable. --- ### Reconstruction of three-dimensional shapes of normal and disease-related erythrocytes from partial observations using multi-fidelity neural networks Authors: Haizhou Wen, He Li, Zhen Li Published: 2025-11-18 Categories: physics.comp-ph, cs.LG, eess.IV, physics.bio-ph, q-bio.QM arXiv: https://arxiv.org/abs/2511.14962v1 Reconstruction of 3D erythrocyte or red blood cell (RBC) morphology from partial observations, such as microscope images, is essential for understanding the physiology of RBC aging and the pathology of various RBC disorders. In this study, we propose a multi-fidelity neural network (MFNN) approach to fuse high-fidelity cross-sections of an RBC, with a morphologically similar low-fidelity reference 3D RBC shape to recover its full 3D surface. The MFNN predictor combines a convolutional neural network trained on low-fidelity reference RBC data with a feedforward neural network that captures nonlinear morphological correlations, and augments training with surface area and volume constraints for regularization in the low-fidelity branch. This approach is theoretically grounded by a topological homeomorphism between a sphere and 3D RBC surfaces, with training data generated by dissipative particle dynamics simulations of stomatocyte-discocyte-echinocyte transformation. Benchmarking across diverse RBC shapes observed in normal and aged populations, our results show that the MFNN predictor can reconstruct complex RBC morphologies with over 95% coordinate accuracy when provided with at least two orthogonal cross-sections. It is observed that informative oblique cross-sections intersecting spicule tips of echinocytes improve both local and global feature reconstruction, highlighting the value of feature-aware sampling. Our study further evaluates the influence of sampling strategies, shape dissimilarity, and noise, showing enhanced robustness under physically constrained training. Altogether, these results demonstrate the capability of MFNN to reconstruct the 3D shape of normal and aged RBCs from partial cross-sections as observed in conventional microscope images, which could facilitate the quantitative analysis of RBC morphological parameters in normal and disease-related RBC samples. --- ### Graph Memory: A Structured and Interpretable Framework for Modality-Agnostic Embedding-Based Inference Authors: Artur A. Oliveira, Mateus Espadoto, Roberto M. Cesar, Roberto Hirata Published: 2025-11-18 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2511.14961v2 We introduce Graph Memory (GM), a structured non-parametric framework that represents an embedding space through a compact graph of reliability-annotated prototype regions. GM encodes local geometry and regional ambiguity through prototype relations and performs inference by diffusing query evidence across this structure, unifying instance retrieval, prototype-based reasoning, and graph diffusion within a single inductive and interpretable model. The framework is inherently modality-agnostic: in multimodal settings, independent prototype graphs are constructed for each modality and their calibrated predictions are combined through reliability-aware late fusion, enabling transparent integration of heterogeneous sources such as whole-slide images and gene-expression profiles. Experiments on synthetic benchmarks, breast histopathology (IDC), and the multimodal AURORA dataset show that GM matches or exceeds the accuracy of kNN and Label Spreading while providing substantially better calibration, smoother decision boundaries, and an order-of-magnitude smaller memory footprint. By explicitly modeling regional reliability and relational structure, GM offers a principled and interpretable approach to non-parametric inference across single- and multi-modal domains. --- ### Compiling to recurrent neurons Authors: Joey Velez-Ginorio, Nada Amin, Konrad Kording, Steve Zdancewic Published: 2025-11-18 Categories: cs.PL, cs.LG arXiv: https://arxiv.org/abs/2511.14953v2 Discrete structures are currently second-class in differentiable programming. Since functions over discrete structures lack overt derivatives, differentiable programs do not differentiate through them and limit where they can be used. For example, when programming a neural network, conditionals and iteration cannot be used everywhere; they can break the derivatives necessary for gradient-based learning to work. This limits the class of differentiable algorithms we can directly express, imposing restraints on how we build neural networks and differentiable programs more generally. However, these restraints are not fundamental. Recent work shows conditionals can be first-class, by compiling them into differentiable form as linear neurons. Similarly, this work shows iteration can be first-class -- by compiling to linear recurrent neurons. We present a minimal typed, higher-order and linear programming language with iteration called $\textsf{Cajal}\scriptstyle(\mathbb{\multimap}, \mathbb{2}, \mathbb{N})$. We prove its programs compile correctly to recurrent neurons, allowing discrete algorithms to be expressed in a differentiable form compatible with gradient-based learning. With our implementation, we conduct two experiments where we link these recurrent neurons against a neural network solving an iterative image transformation task. This determines part of its function prior to learning. As a result, the network learns faster and with greater data-efficiency relative to a neural network programmed without first-class iteration. A key lesson is that recurrent neurons enable a rich interplay between learning and the discrete structures of ordinary programming. --- ### Artificial intelligence approaches for energy-efficient laser cutting machines Authors: Mohamed Abdallah Salem, Hamdy Ahmed Ashour, Ahmed Elshenawy Published: 2025-11-18 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2511.14952v1 This research addresses the significant challenges of energy consumption and environmental impact in laser cutting by proposing novel deep learning (DL) methodologies to achieve energy reduction. Recognizing the current lack of adaptive control and the open-loop nature of CO2 laser suction pumps, this study utilizes closed-loop configurations that dynamically adjust pump power based on both the material being cut and the smoke level generated. To implement this adaptive system, diverse material classification methods are introduced, including techniques leveraging lens-less speckle sensing with a customized Convolutional Neural Network (CNN) and an approach using a USB camera with transfer learning via the pre-trained VGG16 CNN model. Furthermore, a separate DL model for smoke level detection is employed to simultaneously refine the pump's power output. This integration prompts the exhaust suction pump to automatically halt during inactive times and dynamically adjust power during operation, leading to experimentally proven and remarkable energy savings, with results showing a 20% to 50% reduction in the smoke suction pump's energy consumption, thereby contributing substantially to sustainable development in the manufacturing sector. --- ### RocSync: Millisecond-Accurate Temporal Synchronization for Heterogeneous Camera Systems Authors: Jaro Meyer, Frédéric Giraud, Joschua Wüthrich, Marc Pollefeys, Philipp Fürnstahl, Lilian Calvet Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14948v1 Accurate spatiotemporal alignment of multi-view video streams is essential for a wide range of dynamic-scene applications such as multi-view 3D reconstruction, pose estimation, and scene understanding. However, synchronizing multiple cameras remains a significant challenge, especially in heterogeneous setups combining professional and consumer-grade devices, visible and infrared sensors, or systems with and without audio, where common hardware synchronization capabilities are often unavailable. This limitation is particularly evident in real-world environments, where controlled capture conditions are not feasible. In this work, we present a low-cost, general-purpose synchronization method that achieves millisecond-level temporal alignment across diverse camera systems while supporting both visible (RGB) and infrared (IR) modalities. The proposed solution employs a custom-built \textit{LED Clock} that encodes time through red and infrared LEDs, allowing visual decoding of the exposure window (start and end times) from recorded frames for millisecond-level synchronization. We benchmark our method against hardware synchronization and achieve a residual error of 1.34~ms RMSE across multiple recordings. In further experiments, our method outperforms light-, audio-, and timecode-based synchronization approaches and directly improves downstream computer vision tasks, including multi-view pose estimation and 3D reconstruction. Finally, we validate the system in large-scale surgical recordings involving over 25 heterogeneous cameras spanning both IR and RGB modalities. This solution simplifies and streamlines the synchronization pipeline and expands access to advanced vision-based sensing in unconstrained environments, including industrial and clinical applications. --- ### Unsupervised Discovery of Long-Term Spatiotemporal Periodic Workflows in Human Activities Authors: Fan Yang, Quanting Xie, Atsunori Moteki, Shoichi Masui, Shan Jiang, Kanji Uchino, Yonatan Bisk, Graham Neubig Published: 2025-11-18 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.14945v2 Periodic human activities with implicit workflows are common in manufacturing, sports, and daily life. While short-term periodic activities -- characterized by simple structures and high-contrast patterns -- have been widely studied, long-term periodic workflows with low-contrast patterns remain largely underexplored. To bridge this gap, we introduce the first benchmark comprising 580 multimodal human activity sequences featuring long-term periodic workflows. The benchmark supports three evaluation tasks aligned with real-world applications: unsupervised periodic workflow detection, task completion tracking, and procedural anomaly detection. We also propose a lightweight, training-free baseline for modeling diverse periodic workflow patterns. Experiments show that: (i) our benchmark presents significant challenges to both unsupervised periodic detection methods and zero-shot approaches based on powerful large language models (LLMs); (ii) our baseline outperforms competing methods by a substantial margin in all evaluation tasks; and (iii) in real-world applications, our baseline demonstrates deployment advantages on par with traditional supervised workflow detection approaches, eliminating the need for annotation and retraining. Our project page is https://sites.google.com/view/periodicworkflow. --- ### Fine-tuning Pre-trained Audio Models for COVID-19 Detection: A Technical Report Authors: Daniel Oliveira de Brito, Letícia Gabriella de Souza, Marcelo Matheus Gauy, Marcelo Finger, Arnaldo Candido Junior Published: 2025-11-18 Categories: cs.SD, cs.LG, eess.AS arXiv: https://arxiv.org/abs/2511.14939v1 This technical report investigates the performance of pre-trained audio models on COVID-19 detection tasks using established benchmark datasets. We fine-tuned Audio-MAE and three PANN architectures (CNN6, CNN10, CNN14) on the Coswara and COUGHVID datasets, evaluating both intra-dataset and cross-dataset generalization. We implemented a strict demographic stratification by age and gender to prevent models from exploiting spurious correlations between demographic characteristics and COVID-19 status. Intra-dataset results showed moderate performance, with Audio-MAE achieving the strongest result on Coswara (0.82 AUC, 0.76 F1-score), while all models demonstrated limited performance on Coughvid (AUC 0.58-0.63). Cross-dataset evaluation revealed severe generalization failure across all models (AUC 0.43-0.68), with Audio-MAE showing strong performance degradation (F1-score 0.00-0.08). Our experiments demonstrate that demographic balancing, while reducing apparent model performance, provides more realistic assessment of COVID-19 detection capabilities by eliminating demographic leakage - a confounding factor that inflate performance metrics. Additionally, the limited dataset sizes after balancing (1,219-2,160 samples) proved insufficient for deep learning models that typically require substantially larger training sets. These findings highlight fundamental challenges in developing generalizable audio-based COVID-19 detection systems and underscore the importance of rigorous demographic controls for clinically robust model evaluation. --- ### How to Train Private Clinical Language Models: A Comparative Study of Privacy-Preserving Pipelines for ICD-9 Coding Authors: Mathieu Dufour, Andrew Duncan Published: 2025-11-18 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2511.14936v1 Large language models trained on clinical text risk exposing sensitive patient information, yet differential privacy (DP) methods often severely degrade the diagnostic accuracy needed for deployment. Despite rapid progress in DP optimisation and text generation, it remains unclear which privacy-preserving strategy actually works best for clinical language tasks. We present the first systematic head-to-head comparison of four training pipelines for automated diagnostic coding from hospital discharge summaries. All pipelines use identical 1B-parameter models and matched privacy budgets to predict ICD-9 codes. At moderate and relaxed privacy budgets ($\varepsilon \in \{4, 6\}$), knowledge distillation from DP-trained teachers outperforms both direct DP-SGD and DP-synthetic data training, recovering up to 63\% of the non-private performance whilst maintaining strong empirical privacy (membership-inference AUC $\approx$ 0.5). These findings expose large differences in the privacy-utility trade-off across architectures and identify knowledge distillation as the most practical route to privacy-preserving clinical NLP. --- ### Fifty Shades of Greenwashing: The Political Economy of Climate Change Advertising on Social Media Authors: Robert Kubinec, Aseem Mahajan Published: 2025-11-18 Categories: stat.AP, cs.AI, econ.GN arXiv: https://arxiv.org/abs/2511.14930v1 In this paper, we provide a novel measure for greenwashing -- i.e., climate-related misinformation -- that shows how polluting companies can use social media advertising related to climate change to redirect criticism. To do so, we identify greenwashing content in 11 million social-political ads in Meta's Ad Targeting Datset with a measurement technique that combines large language models, human coders, and advances in Bayesian item response theory. We show that what is called greenwashing has diverse actors and components, but we also identify a very pernicious form, which we call political greenwashing, that appears to be promoted by fossil fuel companies and related interest groups. Based on ad targeting data, we show that much of this advertising happens via organizations with undisclosed links to the fossil fuel industry. Furthermore, we show that greenwashing ad content is being micro-targeted at left-leaning communities with fossil fuel assets, though we also find comparatively little evidence of ad targeting aimed at influencing public opinion at the national level. --- ### CPSL: Representing Volumetric Video via Content-Promoted Scene Layers Authors: Kaiyuan Hu, Yili Jin, Junhua Liu, Xize Duan, Hong Kang, Xue Liu Published: 2025-11-18 Categories: cs.CV, cs.MM arXiv: https://arxiv.org/abs/2511.14927v1 Volumetric video enables immersive and interactive visual experiences by supporting free viewpoint exploration and realistic motion parallax. However, existing volumetric representations from explicit point clouds to implicit neural fields, remain costly in capture, computation, and rendering, which limits their scalability for on-demand video and reduces their feasibility for real-time communication. To bridge this gap, we propose Content-Promoted Scene Layers (CPSL), a compact 2.5D video representation that brings the perceptual benefits of volumetric video to conventional 2D content. Guided by per-frame depth and content saliency, CPSL decomposes each frame into a small set of geometry-consistent layers equipped with soft alpha bands and an edge-depth cache that jointly preserve occlusion ordering and boundary continuity. These lightweight, 2D-encodable assets enable parallax-corrected novel-view synthesis via depth-weighted warping and front-to-back alpha compositing, bypassing expensive 3D reconstruction. Temporally, CPSL maintains inter-frame coherence using motion-guided propagation and per-layer encoding, supporting real-time playback with standard video codecs. Across multiple benchmarks, CPSL achieves superior perceptual quality and boundary fidelity compared with layer-based and neural-field baselines while reducing storage and rendering cost by several folds. Our approach offer a practical path from 2D video to scalable 2.5D immersive media. --- ### Integrating Causal Inference with Graph Neural Networks for Alzheimer's Disease Analysis Authors: Pranay Kumar Peddi, Dhrubajyoti Ghosh Published: 2025-11-18 Categories: cs.LG, stat.ME arXiv: https://arxiv.org/abs/2511.14922v1 Deep graph learning has advanced Alzheimer's (AD) disease classification from MRI, but most models remain correlational, confounding demographic and genetic factors with disease specific features. We present Causal-GCN, an interventional graph convolutional framework that integrates do-calculus-based back-door adjustment to identify brain regions exerting stable causal influence on AD progression. Each subject's MRI is represented as a structural connectome where nodes denote cortical and subcortical regions and edges encode anatomical connectivity. Confounders such as age, sec, and APOE4 genotype are summarized via principal components and included in the causal adjustment set. After training, interventions on individual regions are simulated by serving their incoming edges and altering node features to estimate average causal effects on disease probability. Applied to 484 subjects from the ADNI cohort, Causal-GCN achieves performance comparable to baseline GNNs while providing interpretable causal effect rankings that highlight posterior, cingulate, and insular hubs consistent with established AD neuropathology. ---