# Research Papers — 2026-03 · bundle page 217 of 243 > Full-text markdown of papers #10801–10850 of 12123 published in 2026-03, newest first. AI-readable mirrors of the full 12123-paper 2026-03 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-03/page/217 [← Previous bundle](https://aipod.dev/papers/archive/2026-03/page/216.md) [Next bundle →](https://aipod.dev/papers/archive/2026-03/page/218.md) ### Slice-wise quality assessment of high b-value breast DWI via deep learning-based artifact detection Authors: Ameya Markale, Luise Brock, Ihor Horishnyi, Dominika Skwierawska, Tri-Thien Nguyen, Hannes Schreiter, Shirin Heidarikahkesh, Lorenz A. Kapsner, Michael Uder, Sabine Ohlmeyer, Frederik B Laun, Andrzej Liebert et al. Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03941v1 Diffusion-weighted imaging (DWI) can support lesion detection and characterization in breast magnetic resonance imaging (MRI), however especially high b-value diffusion-weighted acquisitions can be prone to intensity artifacts that can affect diagnostic image assessment. This study aims to detect both hyper- and hypointense artifacts on high b-value diffusion-weighted images (b=1500 s/mm2) using deep learning, employing either a binary classification (artifact presence) or a multiclass classification (artifact intensity) approach on a slice-wise dataset.This IRB-approved retrospective study used the single-center dataset comprising n=11806 slices from routine 3T breast MRI examinations performed between 2022 and mid-2023. Three convolutional neural network (CNN) architectures (DenseNet121, ResNet18, and SEResNet50) were trained for binary classification of hyper- and hypointense artifacts. The best performing model (DenseNet121) was applied to an independent holdout test set and was further trained separately for multiclass classification. Evaluation included area under receiver operating characteristic curve (AUROC), area under precision recall curve (AUPRC), precision, and recall, as well as analysis of predicted bounding box positions, derived from the network Grad-CAM heatmaps. DenseNet121 achieved AUROCs of 0.92 and 0.94 for hyper- and hypointense artifact detection, respectively, and weighted AUROCs of 0.85 and 0.88 for multiclass classification on single-slice high b-value diffusion-weighted images. A radiologist evaluated bounding box precision on a 1-5 Likert-like scale across 200 slices, achieving mean scores of 3.33+-1.04 for hyperintense artifacts and 2.62+-0.81 for hypointense artifacts. Hyper- and hypointense artifact detection in slice-wise breast DWI MRI dataset (b=1500 s/mm2) using CNNs particularly DenseNet121, seems promising and requires further validation. --- ### Cross-Modal Mapping and Dual-Branch Reconstruction for 2D-3D Multimodal Industrial Anomaly Detection Authors: Radia Daci, Vito Renò, Cosimo Patruno, Angelo Cardellicchio, Abdelmalik Taleb-Ahmed, Marco Leo, Cosimo Distante Published: 2026-03-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.03939v1 Multimodal industrial anomaly detection benefits from integrating RGB appearance with 3D surface geometry, yet existing \emph{unsupervised} approaches commonly rely on memory banks, teacher-student architectures, or fragile fusion schemes, limiting robustness under noisy depth, weak texture, or missing modalities. This paper introduces \textbf{CMDR-IAD}, a lightweight and modality-flexible unsupervised framework for reliable anomaly detection in 2D+3D multimodal as well as single-modality (2D-only or 3D-only) settings. \textbf{CMDR-IAD} combines bidirectional 2D$\leftrightarrow$3D cross-modal mapping to model appearance-geometry consistency with dual-branch reconstruction that independently captures normal texture and geometric structure. A two-part fusion strategy integrates these cues: a reliability-gated mapping anomaly highlights spatially consistent texture-geometry discrepancies, while a confidence-weighted reconstruction anomaly adaptively balances appearance and geometric deviations, yielding stable and precise anomaly localization even in depth-sparse or low-texture regions. On the MVTec 3D-AD benchmark, CMDR-IAD achieves state-of-the-art performance while operating without memory banks, reaching 97.3\% image-level AUROC (I-AUROC), 99.6\% pixel-level AUROC (P-AUROC), and 97.6\% AUPRO. On a real-world polyurethane cutting dataset, the 3D-only variant attains 92.6\% I-AUROC and 92.5\% P-AUROC, demonstrating strong effectiveness under practical industrial conditions. These results highlight the framework's robustness, modality flexibility, and the effectiveness of the proposed fusion strategies for industrial visual inspection. Our source code is available at https://github.com/ECGAI-Research/CMDR-IAD/ --- ### DISC: Dense Integrated Semantic Context for Large-Scale Open-Set Semantic Mapping Authors: Felix Igelbrink, Lennart Niecksch, Martin Atzmueller, Joachim Hertzberg Published: 2026-03-04 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2603.03935v1 Open-set semantic mapping enables language-driven robotic perception, but current instance-centric approaches are bottlenecked by context-depriving and computationally expensive crop-based feature extraction. To overcome this fundamental limitation, we introduce DISC (Dense Integrated Semantic Context), featuring a novel single-pass, distance-weighted extraction mechanism. By deriving high-fidelity CLIP embeddings directly from the vision transformer's intermediate layers, our approach eliminates the latency and domain-shift artifacts of traditional image cropping, yielding pure, mask-aligned semantic representations. To fully leverage these features in large-scale continuous mapping, DISC is built upon a fully GPU-accelerated architecture that replaces periodic offline processing with precise, on-the-fly voxel-level instance refinement. We evaluate our approach on standard benchmarks (Replica, ScanNet) and a newly generated large-scale-mapping dataset based on Habitat-Matterport 3D (HM3DSEM) to assess scalability across complex scenes in multi-story buildings. Extensive evaluations demonstrate that DISC significantly surpasses current state-of-the-art zero-shot methods in both semantic accuracy and query retrieval, providing a robust, real-time capable framework for robotic deployment. The full source code, data generation and evaluation pipelines will be made available at https://github.com/DFKI-NI/DISC. --- ### Selecting Offline Reinforcement Learning Algorithms for Stochastic Network Control Authors: Nicolas Helson, Pegah Alizadeh, Anastasios Giovanidis Published: 2026-03-04 Categories: cs.NI, cs.AI, cs.LG, cs.PF, eess.SY arXiv: https://arxiv.org/abs/2603.03932v1 Offline Reinforcement Learning (RL) is a promising approach for next-generation wireless networks, where online exploration is unsafe and large amounts of operational data can be reused across the model lifecycle. However, the behavior of offline RL algorithms under genuinely stochastic dynamics -- inherent to wireless systems due to fading, noise, and traffic mobility -- remains insufficiently understood. We address this gap by evaluating Bellman-based (Conservative Q-Learning), sequence-based (Decision Transformers), and hybrid (Critic-Guided Decision Transformers) offline RL methods in an open-access stochastic telecom environment (mobile-env). Our results show that Conservative Q-Learning consistently produces more robust policies across different sources of stochasticity, making it a reliable default choice in lifecycle-driven AI management frameworks. Sequence-based methods remain competitive and can outperform Bellman-based approaches when sufficient high-return trajectories are available. These findings provide practical guidance for offline RL algorithm selection in AI-driven network control pipelines, such as O-RAN and future 6G functions, where robustness and data availability are key operational constraints. --- ### N-gram Injection into Transformers for Dynamic Language Model Adaptation in Handwritten Text Recognition Authors: Florent Meyer, Laurent Guichard, Yann Soullard, Denis Coquenet, Guillaume Gravier, Bertrand Coüasnon Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03930v2 Transformer-based encoder-decoder networks have recently achieved impressive results in handwritten text recognition, partly thanks to their auto-regressive decoder which implicitly learns a language model. However, such networks suffer from a large performance drop when evaluated on a target corpus whose language distribution is shifted from the source text seen during training. To retain recognition accuracy despite this language shift, we propose an external n-gram injection (NGI) for dynamic adaptation of the network's language modeling at inference time. Our method allows switching to an n-gram language model estimated on a corpus close to the target distribution, therefore mitigating bias without any extra training on target image-text pairs. We opt for an early injection of the n-gram into the transformer decoder so that the network learns to fully leverage text-only data at the low additional cost of n-gram inference. Experiments on three handwritten datasets demonstrate that the proposed NGI significantly reduces the performance gap between source and target corpora. --- ### Hierarchical Inference and Closure Learning via Adaptive Surrogates for ODEs and PDEs Authors: Pengyu Zhang, Arnaud Vadeboncoeur, Alex Glyn-Davies, Mark Girolami Published: 2026-03-04 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2603.03922v1 Inverse problems are the task of calibrating models to match data. They play a pivotal role in diverse engineering applications by allowing practitioners to align models with reality. In many applications, engineers and scientists do not have a complete picture of i) the detailed properties of a system (such as material properties, geometry, initial conditions, etc.); ii) the complete laws describing all dynamics at play (such as friction laws, complicated damping phenomena, and general nonlinear interactions). In this paper, we develop a principled methodology for leveraging data from collections of distinct yet related physical systems to jointly estimate the individual model parameters of each system, and learn the shared unknown dynamics in the form of an ML-based closure model. To robustly infer the unknown parameters for each system, we employ a hierarchical Bayesian framework, which allows for the joint inference of multiple systems and their population-level statistics. To learn the closures, we use a maximum marginal likelihood estimate of a neural network embeded within the ODE/PDE formulation of the problem. To realize this framework we utilize the ensemble Metropolis-Adjusted Langevin Algorithm (MALA) for stable and efficient sampling. To mitigate the computational bottleneck of repetitive forward evaluations in solving inverse problems, we introduce a bilevel optimization strategy to simultaneously train a surrogate forward model alongside the inference. Within this framework, we evaluate and compare distinct surrogate architectures, specifically Fourier Neural Operators (FNO) and parametric Physics-Informed Neural Network (PINNs). --- ### BD-Merging: Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning Authors: Yuhan Xie, Chen Lyu Published: 2026-03-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.03920v2 Model Merging (MM) has emerged as a scalable paradigm for multi-task learning (MTL), enabling multiple task-specific models to be integrated without revisiting the original training data. Despite recent progress, the reliability of MM under test-time distribution shift remains insufficiently understood. Most existing MM methods typically assume that test data are clean and distributionally aligned with both the training and auxiliary sources. However, this assumption rarely holds in practice, often resulting in biased predictions with degraded generalization. To address this issue, we present BD-Merging, a bias-aware unsupervised model merging framework that explicitly models uncertainty to achieve adaptive reliability under distribution shift. First, BD-Merging introduces a joint evidential head that learns uncertainty over a unified label space, capturing cross-task semantic dependencies in MM. Second, building upon this evidential foundation, we propose an Adjacency Discrepancy Score (ADS) that quantifies evidential alignment among neighboring samples. Third, guided by ADS, a discrepancy-aware contrastive learning mechanism refines the merged representation by aligning consistent samples and separating conflicting ones. Combined with general unsupervised learning, this process trains a debiased router that adaptively allocates task-specific or layer-specific weights on a per-sample basis, effectively mitigating the adverse effects of distribution shift. Extensive experiments across diverse tasks demonstrate that BD-Merging achieves superior effectiveness and robustness compared to state-of-the-art MM baselines. --- ### Rethinking Role-Playing Evaluation: Anonymous Benchmarking and a Systematic Study of Personality Effects Authors: Ji-Lun Peng, Yun-Nung Chen Published: 2026-03-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03915v2 Large Language Models (LLMs) have shown remarkable potential in developing role-playing agents (RPAs). However, current evaluation frameworks rely heavily on well-known fictional characters, raising a critical concern: models may be leveraging their internal training memory of these characters rather than demonstrating role-playing capabilities. This reliance often leads to significant performance degradation when RPAs encounter unseen or out-of-distribution personas. To address this, we propose a more rigorous evaluation protocol designed to decouple role-playing proficiency from character recognition. Our experiments across multiple benchmarks demonstrate that anonymizing characters degrades performance, confirming that name exposure provides implicit cues that mask a model's true capability. To mitigate this, we investigate diverse personality augmentation as a method to enhance role fidelity in anonymous settings. We systematically analyze the impact of various personality-description methods on agent behavior and consistency. Our results show that incorporating personality information consistently improves RPA performance. This work establishes a more equitable evaluation standard and validates a scalable, personality-enhanced framework for constructing robust RPAs. --- ### From Threat Intelligence to Firewall Rules: Semantic Relations in Hybrid AI Agent and Expert System Architectures Authors: Chiara Bonfanti, Davide Colaiacomo, Luca Cagliero, Cataldo Basile Published: 2026-03-04 Categories: cs.AI, cs.CL, cs.CR arXiv: https://arxiv.org/abs/2603.03911v1 Web security demands rapid response capabilities to evolving cyber threats. Agentic Artificial Intelligence (AI) promises automation, but the need for trustworthy security responses is of the utmost importance. This work investigates the role of semantic relations in extracting information for sensitive operational tasks, such as configuring security controls for mitigating threats. To this end, it proposes to leverage hypernym-hyponym textual relations to extract relevant information from Cyber Threat Intelligence (CTI) reports. By leveraging a neuro-symbolic approach, the multi-agent system automatically generates CLIPS code for an expert system creating firewall rules to block malicious network traffic. Experimental results show the superior performance of the hypernym-hyponym retrieval strategy compared to various baselines and the higher effectiveness of the agentic approach in mitigating threats. --- ### Fine-grained Image Aesthetic Assessment: Learning Discriminative Scores from Relative Ranks Authors: Zhichao Yang, Jianjie Wang, Zhixianhe Zhang, Pangu Xie, Xiangfei Sheng, Pengfei Chen, Leida Li Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03907v1 Image aesthetic assessment (IAA) has extensive applications in content creation, album management, and recommendation systems, etc. In such applications, it is commonly needed to pick out the most aesthetically pleasing image from a series of images with subtle aesthetic variations, a topic we refer to as fine-grained IAA. Unfortunately, state-of-the-art IAA models are typically designed for coarse-grained evaluation, where images with notable aesthetic differences are evaluated independently on an absolute scale. These models are inherently limited in discriminating fine-grained aesthetic differences. To address the dilemma, we contribute FGAesthetics, a fine-grained IAA database with 32,217 images organized into 10,028 series, which are sourced from diverse categories including Natural, AIGC, and Cropping. Annotations are collected via pairwise comparisons within each series. We also devise Series Refinement and Rank Calibration to ensure the reliability of data and labels. Based on FGAesthetics, we further propose FGAesQ, a novel IAA framework that learns discriminative aesthetic scores from relative ranks through Difference-preserved Tokenization (DiffToken), Comparative Text-assisted Alignment (CTAlign), and Rank-aware Regression (RankReg). FGAesQ enables accurate aesthetic assessment in fine-grained scenarios while still maintains competitive performance in coarse-grained evaluation. Extensive experiments and comparisons demonstrate the superiority of the proposed method. --- ### Architecture and evaluation protocol for transformer-based visual object tracking in UAV applications Authors: Augustin Borne, Pierre Notin, Christophe Hennequin, Sebastien Changey, Stephane Bazeille, Christophe Cudel, Franz Quint Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03904v2 Object tracking from Unmanned Aerial Vehicles (UAVs) is challenged by platform dynamics, camera motion, and limited onboard resources. Existing visual trackers either lack robustness in complex scenarios or are too computationally demanding for real-time embedded use. We propose an Modular Asynchronous Tracking Architecture (MATA) that combines a transformer-based tracker with an Extended Kalman Filter, integrating ego-motion compensation from sparse optical flow and an object trajectory model. We further introduce a hardware-independent, embedded oriented evaluation protocol and a new metric called Normalized time to Failure (NT2F) to quantify how long a tracker can sustain a tracking sequence without external help. Experiments on UAV benchmarks, including an augmented UAV123 dataset with synthetic occlusions, show consistent improvements in Success and NT2F metrics across multiple tracking processing frequency. A ROS 2 implementation on a Nvidia Jetson AGX Orin confirms that the evaluation protocol more closely matches real-time performance on embedded systems. --- ### From Misclassifications to Outliers: Joint Reliability Assessment in Classification Authors: Yang Li, Youyang Sha, Yinzhi Wang, Timothy Hospedales, Xi Shen, Shell Xu Hu, Xuanlong Yu Published: 2026-03-04 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2603.03903v1 Building reliable classifiers is a fundamental challenge for deploying machine learning in real-world applications. A reliable system should not only detect out-of-distribution (OOD) inputs but also anticipate in-distribution (ID) errors by assigning low confidence to potentially misclassified samples. Yet, most prior work treats OOD detection and failure prediction as separated problems, overlooking their closed connection. We argue that reliability requires evaluating them jointly. To this end, we propose a unified evaluation framework that integrates OOD detection and failure prediction, quantified by our new metrics DS-F1 and DS-AURC, where DS denotes double scoring functions. Experiments on the OpenOOD benchmark show that double scoring functions yield classifiers that are substantially more reliable than traditional single scoring approaches. Our analysis further reveals that OOD-based approaches provide notable gains under simple or far-OOD shifts, but only marginal benefits under more challenging near-OOD conditions. Beyond evaluation, we extend the reliable classifier SURE and introduce SURE+, a new approach that significantly improves reliability across diverse scenarios. Together, our framework, metrics, and method establish a new benchmark for trustworthy classification and offer practical guidance for deploying robust models in real-world settings. The source code is publicly available at https://github.com/Intellindust-AI-Lab/SUREPlus. --- ### PatchDecomp: Interpretable Patch-Based Time Series Forecasting Authors: Hiroki Tomioka, Genta Yoshimura Published: 2026-03-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.03902v1 Time series forecasting, which predicts future values from past observations, plays a central role in many domains and has driven the development of highly accurate neural network models. However, the complexity of these models often limits human understanding of the rationale behind their predictions. We propose PatchDecomp, a neural network-based time series forecasting method that achieves both high accuracy and interpretability. PatchDecomp divides input time series into subsequences (patches) and generates predictions by aggregating the contributions of each patch. This enables clear attribution of each patch, including those from exogenous variables, to the final prediction. Experiments on multiple benchmark datasets demonstrate that PatchDecomp provides predictive performance comparable to recent forecasting methods. Furthermore, we show that the model's explanations not only influence predicted values quantitatively but also offer qualitative interpretability through visualization of patch-wise contributions. --- ### IROSA: Interactive Robot Skill Adaptation using Natural Language Authors: Markus Knauer, Samuel Bustamante, Thomas Eiband, Alin Albu-Schäffer, Freek Stulp, João Silvério Published: 2026-03-04 Categories: cs.RO, cs.AI, cs.CL, cs.HC, cs.LG arXiv: https://arxiv.org/abs/2603.03897v3 Foundation models have demonstrated impressive capabilities across diverse domains, while imitation learning provides principled methods for robot skill adaptation from limited data. Combining these approaches holds significant promise for direct application to robotics, yet this combination has received limited attention, particularly for industrial deployment. We present a novel framework that enables open-vocabulary skill adaptation through a tool-based architecture, maintaining a protective abstraction layer between the language model and robot hardware. Our approach leverages pre-trained LLMs to select and parameterize specific tools for adapting robot skills without requiring fine-tuning or direct model-to-robot interaction. We demonstrate the framework on a 7-DoF torque-controlled robot performing an industrial bearing ring insertion task, showing successful skill adaptation through natural language commands for speed adjustment, trajectory correction, and obstacle avoidance while maintaining safety, transparency, and interpretability. --- ### A novel network for classification of cuneiform tablet metadata Authors: Frederik Hagelskjær Published: 2026-03-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.03892v2 In this paper, we present a network structure for classifying metadata of cuneiform tablets. The problem is of practical importance, as the size of the existing corpus far exceeds the number of experts available to analyze it. But the task is made difficult by the combination of limited annotated datasets and the high-resolution point-cloud representation of each tablet. To address this, we develop a convolution-inspired architecture that gradually down-scales the point cloud while integrating local neighbor information. The final down-scaled point cloud is then processed by computing neighbors in the feature space to include global information. Our method is compared with the state-of-the-art transformer-based network Point-BERT, and consistently obtains the best performance. Source code and data available at github.com/fhagelskjaer/cuneiform3d --- ### CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents Authors: Martin Kostelník, Michal Hradiš, Martin Dočekal Published: 2026-03-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03884v2 Topic localization aims to identify spans of text that express a given topic defined by a name and description. To study this task, we introduce a human-annotated benchmark based on Czech historical documents, containing human-defined topics together with manually annotated spans and supporting evaluation at both document and word levels. Evaluation is performed relative to human agreement rather than a single reference annotation. We evaluate a diverse range of large language models alongside BERT-based models fine-tuned on a distilled development dataset. Results reveal substantial variability among LLMs, with performance ranging from near-human topic detection to pronounced failures in span localization. While the strongest models approach human agreement, the distilled token embedding models remain competitive despite their smaller scale. The dataset and evaluation framework are publicly available at: https://github.com/dcgm/czechtopic. --- ### CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents Authors: Martin Kostelník, Michal Hradiš, Martin Dočekal Published: 2026-03-04 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2603.03884v1 Topic localization aims to identify spans of text that express a given topic defined by a name and description. To study this task, we introduce a human-annotated benchmark based on Czech historical documents, containing human-defined topics together with manually annotated spans and supporting evaluation at both document and word levels. Evaluation is performed relative to human agreement rather than a single reference annotation. We evaluate a diverse range of large language models alongside BERT-based models fine-tuned on a distilled development dataset. Results reveal substantial variability among LLMs, with performance ranging from near-human topic detection to pronounced failures in span localization. While the strongest models approach human agreement, the distilled token embedding models remain competitive despite their smaller scale. The dataset and evaluation framework are publicly available at: https://github.com/dcgm/czechtopic. --- ### UniSync: Towards Generalizable and High-Fidelity Lip Synchronization for Challenging Scenarios Authors: Ruidi Fan, Yang Zhou, Siyuan Wang, Tian Yu, Yutong Jiang, Xusheng Liu Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03882v1 Lip synchronization aims to generate realistic talking videos that match given audio, which is essential for high-quality video dubbing. However, current methods have fundamental drawbacks: mask-based approaches suffer from local color discrepancies, while mask-free methods struggle with global background texture misalignment. Furthermore, most methods struggle with diverse real-world scenarios such as stylized avatars, face occlusion, and extreme lighting conditions. In this paper, we propose UniSync, a unified framework designed for achieving high-fidelity lip synchronization in diverse scenarios. Specifically, UniSync uses a mask-free pose-anchored training strategy to keep head motion and eliminate synthesis color artifacts, while employing mask-based blending consistent inference to ensure structural precision and smooth blending. Notably, fine-tuning on compact but diverse videos empowers our model with exceptional domain adaptability, handling complex corner cases effectively. We also introduce the RealWorld-LipSync benchmark to evaluate models under real-world demands, which covers diverse application scenarios including both human faces and stylized avatars. Extensive experiments demonstrate that UniSync significantly outperforms state-of-the-art methods, advancing the field towards truly generalizable and production-ready lip synchronization. --- ### On the Suitability of LLM-Driven Agents for Dark Pattern Audits Authors: Chen Sun, Yash Vekaria, Rishab Nithyanand Published: 2026-03-04 Categories: cs.CR, cs.AI, cs.CL, cs.CY, cs.HC arXiv: https://arxiv.org/abs/2603.03881v1 As LLM-driven agents begin to autonomously navigate the web, their ability to interpret and respond to manipulative interface design becomes critical. A fundamental question that emerges is: can such agents reliably recognize patterns of friction, misdirection, and coercion in interface design (i.e., dark patterns)? We study this question in a setting where the workflows are consequential: website portals associated with the submission of CCPA-related data rights requests. These portals operationalize statutory rights, but they are implemented as interactive interfaces whose design can be structured to facilitate, burden, or subtly discourage the exercise of those rights. We design and deploy an LLM-driven auditing agent capable of end-to-end traversal of rights-request workflows, structured evidence gathering, and classification of potential dark patterns. Across a set of 456 data broker websites, we evaluate: (1) the ability of the agent to consistently locate and complete request flows, (2) the reliability and reproducibility of its dark pattern classifications, and (3) the conditions under which it fails or produces poor judgments. Our findings characterize both the feasibility and the limitations of using LLM-driven agents for scalable dark pattern auditing. --- ### Joint Hardware-Workload Co-Optimization for In-Memory Computing Accelerators Authors: Olga Krestinskaya, Mohammed E. Fouda, Ahmed Eltawil, Khaled N. Salama Published: 2026-03-04 Categories: cs.AR, cs.AI, cs.ET, cs.NE, eess.SY arXiv: https://arxiv.org/abs/2603.03880v1 Software-hardware co-design is essential for optimizing in-memory computing (IMC) hardware accelerators for neural networks. However, most existing optimization frameworks target a single workload, leading to highly specialized hardware designs that do not generalize well across models and applications. In contrast, practical deployment scenarios require a single IMC platform that can efficiently support multiple neural network workloads. This work presents a joint hardware-workload co-optimization framework based on an optimized evolutionary algorithm for designing generalized IMC accelerator architectures. By explicitly capturing cross-workload trade-offs rather than optimizing for a single model, the proposed approach significantly reduces the performance gap between workload-specific and generalized IMC designs. The framework is evaluated on both RRAM- and SRAM-based IMC architectures, demonstrating strong robustness and adaptability across diverse design scenarios. Compared to baseline methods, the optimized designs achieve energy-delay-area product (EDAP) reductions of up to 76.2% and 95.5% when optimizing across a small set (4 workloads) and a large set (9 workloads), respectively. The source code of the framework is available at https://github.com/OlgaKrestinskaya/JointHardwareWorkloadOptimizationIMC. --- ### Yolo-Key-6D: Single Stage Monocular 6D Pose Estimation with Keypoint Enhancements Authors: Kemal Alperen Çetiner, Hazım Kemal Ekenel Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03879v1 Estimating the 6D pose of objects from a single RGB image is a critical task for robotics and extended reality applications. However, state-of-the-art multi stage methods often suffer from high latency, making them unsuitable for real time use. In this paper, we present Yolo-Key-6D, a novel single stage, end-to-end framework for monocular 6D pose estimation designed for both speed and accuracy. Our approach enhances a YOLO based architecture by integrating an auxiliary head that regresses the 2D projections of an object's 3D bounding box corners. This keypoint detection task significantly improves the network's understanding of 3D geometry. For stable end-to-end training, we directly regress rotation using a continuous 9D representation projected to SO(3) via singular value decomposition. On the LINEMOD and LINEMOD-Occluded benchmarks, YOLO-Key-6D achieves competitive accuracy scores of 96.24% and 69.41%, respectively, with the ADD(-S) 0.1d metric, while proving itself to operate in real time. Our results demonstrate that a carefully designed single stage method can provide a practical and effective balance of performance and efficiency for real world deployment. --- ### Believe Your Model: Distribution-Guided Confidence Calibration Authors: Xizhong Yang, Haotian Zhang, Huiming Wang, Mofei Song Published: 2026-03-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.03872v1 Large Reasoning Models have demonstrated remarkable performance with the advancement of test-time scaling techniques, which enhances prediction accuracy by generating multiple candidate responses and selecting the most reliable answer. While prior work has analyzed that internal model signals like confidence scores can partly indicate response correctness and exhibit a distributional correlation with accuracy, such distributional information has not been fully utilized to guide answer selection. Motivated by this, we propose DistriVoting, which incorporates distributional priors as another signal alongside confidence during voting. Specifically, our method (1) first decomposes the mixed confidence distribution into positive and negative components using Gaussian Mixture Models, (2) then applies a reject filter based on positive/negative samples from them to mitigate overlap between the two distributions. Besides, to further alleviate the overlap from the perspective of distribution itself, we propose SelfStepConf, which uses step-level confidence to dynamically adjust inference process, increasing the separation between the two distributions to improve the reliability of confidences in voting. Experiments across 16 models and 5 benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches. --- ### Bridging Human Evaluation to Infrared and Visible Image Fusion Authors: Jinyuan Liu, Xingyuan Li, Qingyun Mei, Haoyuan Xu, Zhiying Jiang, Long Ma, Risheng Liu, Xin Fan Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03871v1 Infrared and visible image fusion (IVIF) integrates complementary modalities to enhance scene perception. Current methods predominantly focus on optimizing handcrafted losses and objective metrics, often resulting in fusion outcomes that do not align with human visual preferences. This challenge is further exacerbated by the ill-posed nature of IVIF, which severely limits its effectiveness in human perceptual environments such as security surveillance and driver assistance systems. To address these limitations, we propose a feedback reinforcement framework that bridges human evaluation to infrared and visible image fusion. To address the lack of human-centric evaluation metrics and data, we introduce the first large-scale human feedback dataset for IVIF, containing multidimensional subjective scores and artifact annotations, and enriched by a fine-tuned large language model with expert review. Based on this dataset, we design a domain-specific reward function and train a reward model to quantify perceptual quality. Guided by this reward, we fine-tune the fusion network through Group Relative Policy Optimization, achieving state-of-the-art performance that better aligns fused images with human aesthetics. Code is available at https://github.com/ALKA-Wind/EVAFusion. --- ### k-hop Fairness: Addressing Disparities in Graph Link Prediction Beyond First-Order Neighborhoods Authors: Lilian Marey, Tiphaine Viard, Charlotte Laclau Published: 2026-03-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.03867v1 Link prediction (LP) plays a central role in graph-based applications, particularly in social recommendation. However, real-world graphs often reflect structural biases, most notably homophily, the tendency of nodes with similar attributes to connect. While this property can improve predictive performance, it also risks reinforcing existing social disparities. In response, fairness-aware LP methods have emerged, often seeking to mitigate these effects by promoting inter-group connections, that is, links between nodes with differing sensitive attributes (e.g., gender), following the principle of dyadic fairness. However, dyadic fairness overlooks potential disparities within the sensitive groups themselves. To overcome this issue, we propose $k$-hop fairness, a structural notion of fairness for LP, that assesses disparities conditioned on the distance between nodes in the graph. We formalize this notion through predictive fairness and structural bias metrics, and propose pre- and post-processing mitigation strategies. Experiments across standard LP benchmarks reveal: (1) a strong tendency of models to reproduce structural biases at different $k$-hops; (2) interdependence between structural biases at different hops when rewiring graphs; and (3) that our post-processing method achieves favorable $k$-hop performance-fairness trade-offs compared to existing fair LP baselines. --- ### Structure-Aware Distributed Backdoor Attacks in Federated Learning Authors: Wang Jian, Shen Hong, Ke Wei, Liu Xue Hua Published: 2026-03-04 Categories: cs.LG, cs.AI, cs.CR arXiv: https://arxiv.org/abs/2603.03865v1 While federated learning protects data privacy, it also makes the model update process vulnerable to long-term stealthy perturbations. Existing studies on backdoor attacks in federated learning mainly focus on trigger design or poisoning strategies, typically assuming that identical perturbations behave similarly across different model architectures. This assumption overlooks the impact of model structure on perturbation effectiveness. From a structure-aware perspective, this paper analyzes the coupling relationship between model architectures and backdoor perturbations. We introduce two metrics, Structural Responsiveness Score (SRS) and Structural Compatibility Coefficient (SCC), to measure a model's sensitivity to perturbations and its preference for fractal perturbations. Based on these metrics, we develop a structure-aware fractal perturbation injection framework (TFI) to study the role of architectural properties in the backdoor injection process. Experimental results show that model architecture significantly influences the propagation and aggregation of perturbations. Networks with multi-path feature fusion can amplify and retain fractal perturbations even under low poisoning ratios, while models with low structural compatibility constrain their effectiveness. Further analysis reveals a strong correlation between SCC and attack success rate, suggesting that SCC can predict perturbation survivability. These findings highlight that backdoor behaviors in federated learning depend not only on perturbation design or poisoning intensity but also on the interaction between model architecture and aggregation mechanisms, offering new insights for structure-aware defense design. --- ### Assessing the Effectiveness of LLMs in Delivering Cognitive Behavioral Therapy Authors: Navdeep Singh Bedi, Ana-Maria Bucur, Noriko Kando, Fabio Crestani Published: 2026-03-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.03862v1 As mental health issues continue to rise globally, there is an increasing demand for accessible and scalable therapeutic solutions. Many individuals currently seek support from Large Language Models (LLMs), even though these models have not been validated for use in counseling services. In this paper, we evaluate LLMs' ability to emulate professional therapists practicing Cognitive Behavioral Therapy (CBT). Using anonymized, transcribed role-play sessions between licensed therapists and clients, we compare two approaches: (1) a generation-only method and (2) a Retrieval-Augmented Generation (RAG) approach using CBT guidelines. We evaluate both proprietary and open-source models for linguistic quality, semantic coherence, and therapeutic fidelity using standard natural language generation (NLG) metrics, natural language inference (NLI), and automated scoring for skills assessment. Our results indicate that while LLMs can generate CBT-like dialogues, they are limited in their ability to convey empathy and maintain consistency. --- ### DeepScan: A Training-Free Framework for Visually Grounded Reasoning in Large Vision-Language Models Authors: Yangfu Li, Hongjian Zhan, Jiawei Chen, Yuning Gong, Qi Liu, Yue Lu Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03857v1 Humans can robustly localize visual evidence and provide grounded answers even in noisy environments by identifying critical cues and then relating them to the full context in a bottom-up manner. Inspired by this, we propose DeepScan, a training-free framework that combines Hierarchical Scanning, Refocusing, and Evidence-Enhanced Reasoning for visually grounded reasoning in Large Vision-Language Models (LVLMs). Unlike existing methods that pursue one-shot localization of complete evidence, Hierarchical Scanning performs local cue exploration and multi-scale evidence extraction to recover evidence in a bottom-up manner, effectively mitigating the impacts of distractive context. Refocusing then optimizes the localized evidence view through collaboration of LVLMs and visual experts. Finally, Evidence-Enhanced Reasoning aggregates multi-granular views via a hybrid evidence memory and yields accurate and interpretable answers. Experimental results demonstrate that DeepScan significantly boosts LVLMs in diverse visual tasks, especially in fine-grained visual understanding. It achieves 90.6% overall accuracy on V* when integrated with Qwen2.5-VL-7B. Moreover, DeepScan provides consistent improvements for LVLMs across various architectures and model scales without additional adaptation cost. --- ### Coupling Local Context and Global Semantic Prototypes via a Hierarchical Architecture for Rhetorical Roles Labeling Authors: Anas Belfathi, Nicolas Hernandez, Laura Monceaux, Warren Bonnard, Mary Catherine Lavissiere, Christine Jacquin, Richard Dufour Published: 2026-03-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.03856v1 Rhetorical Role Labeling (RRL) identifies the functional role of each sentence in a document, a key task for discourse understanding in domains such as law and medicine. While hierarchical models capture local dependencies effectively, they are limited in modeling global, corpus-level features. To address this limitation, we propose two prototype-based methods that integrate local context with global representations. Prototype-Based Regularization (PBR) learns soft prototypes through a distance-based auxiliary loss to structure the latent space, while Prototype-Conditioned Modulation (PCM) constructs corpus-level prototypes and injects them during training and inference. Given the scarcity of RRL resources, we introduce SCOTUS-Law, the first dataset of U.S. Supreme Court opinions annotated with rhetorical roles at three levels of granularity: category, rhetorical function, and step. Experiments on legal, medical, and scientific benchmarks show consistent improvements over strong baselines, with 4 Macro-F1 gains on low-frequency roles. We further analyze the implications in the era of Large Language Models and complement our findings with expert evaluation. --- ### Benchmarking Motivational Interviewing Competence of Large Language Models Authors: Aishwariya Jha, Prakrithi Shivaprakash, Lekhansh Shukla, Animesh Mukherjee, Prabhat Chand, Pratima Murthy Published: 2026-03-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.03846v1 Motivational interviewing (MI) promotes behavioural change in substance use disorders. Its fidelity is measured using the Motivational Interviewing Treatment Integrity (MITI) framework. While large language models (LLMs) can potentially generate MI-consistent therapist responses, their competence using MITI is not well-researched, especially in real world clinical transcripts. We aim to benchmark MI competence of proprietary and open-source models compared to human therapists in real-world transcripts and assess distinguishability from human therapists. Methods: We shortlisted 3 proprietary and 7 open-source LLMs from LMArena, evaluated performance using MITI 4.2 framework on two datasets (96 handcrafted model transcripts, 34 real-world clinical transcripts). We generated parallel LLM-therapist utterances iteratively for each transcript while keeping client responses static, and ranked performance using a composite ranking system with MITI components and verbosity. We conducted a distinguishability experiment with two independent psychiatrists to identify human-vs-LLM responses. Results: All 10 tested LLMs had fair (MITI global scores >3.5) to good (MITI global scores >4) competence across MITI measures, and three best-performing models (gemma-3-27b-it, gemini-2.5-pro, grok-3) were tested on real-world transcripts. All showed good competence, with LLMs outperforming human-expert in Complex Reflection percentage (39% vs 96%) and Reflection-Question ratio (1.2 vs >2.8). In the distinguishability experiment, psychiatrists identified LLM responses with only 56% accuracy, with d-prime: 0.17 and 0.25 for gemini-2.5-pro and gemma-3-27b-it respectively. Conclusion: LLMs can achieve good MI proficiency in real-world clinical transcripts using MITI framework. These findings suggest that even open-source LLMs are viable candidates for expanding MI counselling sessions in low-resource settings. --- ### Semantic Bridging Domains: Pseudo-Source as Test-Time Connector Authors: Xizhong Yang, Huiming Wang, Ning Xu, Mofei Song Published: 2026-03-04 Categories: cs.CL arXiv: https://arxiv.org/abs/2603.03844v1 Distribution shifts between training and testing data are a critical bottleneck limiting the practical utility of models, especially in real-world test-time scenarios. To adapt models when the source domain is unknown and the target domain is unlabeled, previous works constructed pseudo-source domains via data generation and translation, then aligned the target domain with them. However, significant discrepancies exist between the pseudo-source and the original source domain, leading to potential divergence when correcting the target directly. From this perspective, we propose a Stepwise Semantic Alignment (SSA) method, viewing the pseudo-source as a semantic bridge connecting the source and target, rather than a direct substitute for the source. Specifically, we leverage easily accessible universal semantics to rectify the semantic features of the pseudo-source, and then align the target domain using the corrected pseudo-source semantics. Additionally, we introduce a Hierarchical Feature Aggregation (HFA) module and a Confidence-Aware Complementary Learning (CACL) strategy to enhance the semantic quality of the SSA process in the absence of source and ground truth of target domains. We evaluated our approach on tasks like semantic segmentation and image classification, achieving a 5.2% performance boost on GTA2Cityscapes over the state-of-the-art. --- ### Invariance-Based Dynamic Regret Minimization Authors: Margherita Lazzaretto, Jonas Peters, Niklas Pfister Published: 2026-03-04 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2603.03843v1 We consider stochastic non-stationary linear bandits where the linear parameter connecting contexts to the reward changes over time. Existing algorithms in this setting localize the policy by gradually discarding or down-weighting past data, effectively shrinking the time horizon over which learning can occur. However, in many settings historical data may still carry partial information about the reward model. We propose to leverage such data while adapting to changes, by assuming the reward model decomposes into stationary and non-stationary components. Based on this assumption, we introduce ISD-linUCB, an algorithm that uses past data to learn invariances in the reward model and subsequently exploits them to improve online performance. We show both theoretically and empirically that leveraging invariance reduces the problem dimensionality, yielding significant regret improvements in fast-changing environments when sufficient historical data is available. --- ### All-in-One Image Restoration via Causal-Deconfounding Wavelet-Disentangled Prompt Network Authors: Bingnan Wang, Bin Qin, Jiangmeng Li, Fanjiang Xu, Fuchun Sun, Hui Xiong Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03839v1 Image restoration represents a promising approach for addressing the inherent defects of image content distortion. Standard image restoration approaches suffer from high storage cost and the requirement towards the known degradation pattern, including type and degree, which can barely be satisfied in dynamic practical scenarios. In contrast, all-in-one image restoration (AiOIR) eliminates multiple degradations within a unified model to circumvent the aforementioned issues. However, according to our causal analysis, we disclose that two significant defects still exacerbate the effectiveness and generalization of AiOIR models: 1) the spurious correlation between non-degradation semantic features and degradation patterns; 2) the biased estimation of degradation patterns. To obtain the true causation between degraded images and restored images, we propose Causal-deconfounding Wavelet-disentangled Prompt Network (CWP-Net) to perform effective AiOIR. CWP-Net introduces two modules for decoupling, i.e., wavelet attention module of encoder and wavelet attention module of decoder. These modules explicitly disentangle the degradation and semantic features to tackle the issue of spurious correlation. To address the issue stemming from the biased estimation of degradation patterns, CWP-Net leverages a wavelet prompt block to generate the alternative variable for causal deconfounding. Extensive experiments on two all-in-one settings prove the effectiveness and superior performance of our proposed CWP-Net over the state-of-the-art AiOIR methods. --- ### Non-Invasive Reconstruction of Cardiac Activation Dynamics Using Physics-Informed Neural Networks Authors: Nathan Dermul, Hans Dierckx Published: 2026-03-04 Categories: physics.med-ph, cs.LG arXiv: https://arxiv.org/abs/2603.03832v1 Cardiac arrhythmogenesis is governed by complex electromechanical interactions that are not directly observable in vivo, motivating the development of non-invasive computational approaches for reconstructing three-dimensional activation dynamics. We present a physics-informed neural network framework for recovering cardiac activation patterns, active tension propagation, deformation fields, and hydrostatic pressure from measurable deformation data in simplified left ventricular geometries. Our approach integrates nonlinear anisotropic constitutive modeling, heterogeneous fiber orientation, weak formulations of the governing mechanics, and finite-element-based loss functions to embed physical constraints directly into training. We demonstrate that the proposed framework accurately reconstructs spatiotemporal activation dynamics under varying levels of measurement noise and reduced spatial resolution, while preserving global propagation patterns and activation timing. By coupling mechanistic modeling with data-driven inference, this method establishes a pathway toward patient-specific, non-invasive reconstruction of cardiac activation, with potential applications in digital phenotyping and computational support for arrhythmia assessment. --- ### Universal Pansharpening Model Authors: Hebaixu Wang, Jing Zhang, Haonan Guo, Di Wang, Jiayi Ma, Bo Du, Liangpei Zhang Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03831v2 Pansharpening generates the high-resolution multi-spectral (MS) image by integrating spatial details from a texture-rich panchromatic (PAN) image and spectral attributes from a low-resolution MS image. Existing methods are predominantly satellite-specific and scene-dependent, which severely limits their generalization across heterogeneous sensors and varied scenes, thereby reducing their real-world practicality. To address these challenges, we present UniPS, a universal pansharpening model for satellite-agnostic and scene-robust fusion. Specifically, we introduce a modality-interleaved transformer that learns band-wise modal specializations to form reversible spectral affine bases, mapping arbitrary-band MS into a unified latent space via tensor multiplication. Building upon this, we construct a latent diffusion bridge model to progressively evolve latent representations, and incorporate bridge posterior sampling to couple latent diffusion with pixel-space observations, enabling stable and controllable fusion. Furthermore, we devise infinite-dimensional pixel-to-latent interaction mechanisms to comprehensively capture the cross-domain dependencies between PAN observations and MS representations, thereby facilitating complementary information fusion. In addition, to support large-scale training and evaluation, we construct a comprehensive pansharpening benchmark, termed PSBench, consisting of worldwide MS and PAN image pairs from multiple satellites across diverse scenes. Extensive experiments verify that UniPS consistently outperforms state-of-the-art methods, exhibiting superior generalization and robustness across a wide range of tasks. --- ### Large-Margin Hyperdimensional Computing: A Learning-Theoretical Perspective Authors: Nikita Zeulin, Olga Galinina, Ravikumar Balakrishnan, Nageen Himayat, Sergey Andreev Published: 2026-03-04 Categories: cs.LG arXiv: https://arxiv.org/abs/2603.03830v1 Overparameterized machine learning (ML) methods such as neural networks may be prohibitively resource intensive for devices with limited computational capabilities. Hyperdimensional computing (HDC) is an emerging resource efficient and low-complexity ML method that allows hardware efficient implementations of (re-)training and inference procedures. In this paper, we propose a maximum-margin HDC classifier, which significantly outperforms baseline HDC methods on several benchmark datasets. Our method leverages a formal relation between HDC and support vector machines (SVMs) that we established for the first time. Our findings may inspire novel HDC methods with potentially more hardware-oriented implementations compared to SVMs, thus enabling more efficient learning solutions for various intelligent resource-constrained applications. --- ### From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning Authors: Ruilin Luo, Chufan Shi, Yizhen Zhang, Cheng Yang, Songtao Jiang, Tongkun Guan, Ruizhe Chen, Ruihang Chu, Peng Wang, Mingkun Yang, Yujiu Yang, Junyang Lin et al. Published: 2026-03-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.03825v1 The cold-start initialization stage plays a pivotal role in training Multimodal Large Reasoning Models (MLRMs), yet its mechanisms remain insufficiently understood. To analyze this stage, we introduce the Visual Attention Score (VAS), an attention-based metric that quantifies how much a model attends to visual tokens. We find that reasoning performance is strongly correlated with VAS (r=0.9616): models with higher VAS achieve substantially stronger multimodal reasoning. Surprisingly, multimodal cold-start fails to elevate VAS, resulting in attention distributions close to the base model, whereas text-only cold-start leads to a clear increase. We term this counter-intuitive phenomenon Lazy Attention Localization. To validate its causal role, we design training-free interventions that directly modulate attention allocation during inference, performance gains of 1$-$2% without any retraining. Building on these insights, we further propose Attention-Guided Visual Anchoring and Reflection (AVAR), a comprehensive cold-start framework that integrates visual-anchored data synthesis, attention-guided objectives, and visual-anchored reward shaping. Applied to Qwen2.5-VL-7B, AVAR achieves an average gain of 7.0% across 7 multimodal reasoning benchmarks. Ablation studies further confirm that each component of AVAR contributes step-wise to the overall gains. The code, data, and models are available at https://github.com/lrlbbzl/Qwen-AVAR. --- ### In-Context Environments Induce Evaluation-Awareness in Language Models Authors: Maheep Chaudhary Published: 2026-03-04 Categories: cs.AI, cs.CL, cs.LG, cs.MA arXiv: https://arxiv.org/abs/2603.03824v2 Humans often become more self-aware under threat, yet can lose self-awareness when absorbed in a task; we hypothesize that language models exhibit environment-dependent \textit{evaluation awareness}. This raises concerns that models could strategically underperform, or \textit{sandbag}, to avoid triggering capability-limiting interventions such as unlearning or shutdown. Prior work demonstrates sandbagging under hand-crafted prompts, but this underestimates the true vulnerability ceiling. We introduce a black-box adversarial optimization framework treating the in-context prompt as an optimizable environment, and develop two approaches to characterize sandbagging: (1) measuring whether models expressing intent to underperform can actually execute it across different task structures, and (2) causally isolating whether underperformance is driven by genuine evaluation-aware reasoning or shallow prompt-following. Evaluating Claude-3.5-Haiku, GPT-4o-mini, and Llama-3.3-70B across four benchmarks (Arithmetic, GSM8K, MMLU, and HumanEval), optimized prompts induce up to 94 percentage point (pp) degradation on arithmetic (GPT-4o-mini: 97.8\%$\rightarrow$4.0\%), far exceeding hand-crafted baselines which produce near-zero behavioral change. Code generation exhibits model-dependent resistance: Claude degrades only 0.6pp, while Llama's accuracy drops to 0\%. The intent -- execution gap reveals a monotonic resistance ordering: Arithmetic $<$ GSM8K $<$ MMLU, demonstrating that vulnerability is governed by task structure rather than prompt strength. CoT causal intervention confirms that 99.3\% of sandbagging is causally driven by verbalized eval-aware reasoning, ruling out shallow instruction-following. These findings demonstrate that adversarially optimized prompts pose a substantially greater threat to evaluation reliability than previously understood. --- ### SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration Authors: Jialong Chen, Xander Xu, Hu Wei, Chuan Chen, Bing Zhao Published: 2026-03-04 Categories: cs.SE, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2603.03823v4 Large language model (LLM)-powered agents have demonstrated strong capabilities in automating software engineering tasks such as static bug fixing. However, in the real world, the development of mature software is typically predicated on complex requirement changes and long-term feature iterations -- a process that static, one-shot repair paradigms fail to capture. To bridge this gap, we propose SWE-CI, the first repository-level benchmark built upon the Continuous Integration loop, aiming to shift the evaluation paradigm for code generation from static, short-term functional correctness toward dynamic, long-term maintainability. The key insight is simple: Maintainability can be revealed by tracking how functional correctness changes over time. The benchmark comprises 100 tasks, each deriving from a real-world code repository with a development history spanning an average of 233 days and 71 consecutive commits. SWE-CI requires agents to systematically resolve these tasks through dozens of rounds of analysis and coding iterations. SWE-CI provides valuable insights into how well agents can sustain code quality throughout long-term evolution. --- ### Fairness Begins with State: Purifying Latent Preferences for Hierarchical Reinforcement Learning in Interactive Recommendation Authors: Yun Lu, Xiaoyu Shi, Hong Xie, Xiangyu Zhao, Mingsheng Shang Published: 2026-03-04 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2603.03820v1 Interactive recommender systems (IRS) are increasingly optimized with Reinforcement Learning (RL) to capture the sequential nature of user-system dynamics. However, existing fairness-aware methods often suffer from a fundamental oversight: they assume the observed user state is a faithful representation of true preferences. In reality, implicit feedback is contaminated by popularity-driven noise and exposure bias, creating a distorted state that misleads the RL agent. We argue that the persistent conflict between accuracy and fairness is not merely a reward-shaping issue, but a state estimation failure. In this work, we propose \textbf{DSRM-HRL}, a framework that reformulates fairness-aware recommendation as a latent state purification problem followed by decoupled hierarchical decision-making. We introduce a Denoising State Representation Module (DSRM) based on diffusion models to recover the low-entropy latent preference manifold from high-entropy, noisy interaction histories. Built upon this purified state, a Hierarchical Reinforcement Learning (HRL) agent is employed to decouple conflicting objectives: a high-level policy regulates long-term fairness trajectories, while a low-level policy optimizes short-term engagement under these dynamic constraints. Extensive experiments on high-fidelity simulators (KuaiRec, KuaiRand) demonstrate that DSRM-HRL effectively breaks the "rich-get-richer" feedback loop, achieving a superior Pareto frontier between recommendation utility and exposure equity. --- ### Direct Bayesian Additive Regression Trees for Conditional Average Treatment Effects in Regression Discontinuity Designs Authors: Daisuke Kondo, Shonosuke Sugasawa Published: 2026-03-04 Categories: stat.ME, stat.ML arXiv: https://arxiv.org/abs/2603.03819v1 Regression discontinuity designs (RDD) are widely used for causal inference. In many empirical applications, treatment effects vary substantially with covariates, and ignoring such heterogeneity can lead to misleading conclusions, which motivates flexible modeling of heterogeneous treatment effects in RDD. To this end, we propose a Bayesian nonparametric approach to estimating heterogeneous treatment effects based on Bayesian Additive Regression Trees (BART). The key feature of our method lies in adopting a general Bayesian framework using a pseudo-model defined through a loss function for fitting local linear models around the cutoff, which gives direct modeling of heterogeneous treatment effects by BART. Optimal selection of the bandwidth parameter for the local model is implemented using the Hyvärinen score. Through numerical experiments, we demonstrate that the proposed approach flexibly captures complicated structures of heterogeneous treatment effects as a function of covariates. --- ### Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning Authors: Huihan Liu, Changyeon Kim, Bo Liu, Minghuan Liu, Yuke Zhu Published: 2026-03-04 Categories: cs.LG, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2603.03818v2 Continual learning is a long-standing challenge in robot policy learning, where a policy must acquire new skills over time without catastrophically forgetting previously learned ones. While prior work has extensively studied continual learning in relatively small behavior cloning (BC) policy models trained from scratch, its behavior in modern large-scale pretrained Vision-Language-Action (VLA) models remains underexplored. In this work, we found that pretrained VLAs are remarkably resistant to forgetting compared with smaller policy models trained from scratch. Simple Experience Replay (ER) works surprisingly well on VLAs, sometimes achieving zero forgetting even with a small replay data size. Our analysis reveals that pretraining plays a critical role in downstream continual learning performance: large pretrained models mitigate forgetting with a small replay buffer size while maintaining strong forward learning capabilities. Furthermore, we found that VLAs can retain relevant knowledge from prior tasks despite performance degradation during learning new tasks. This knowledge retention enables rapid recovery of seemingly forgotten skills through finetuning. Together, these insights imply that large-scale pretraining fundamentally changes the dynamics of continual learning, enabling models to continually acquire new skills over time with simple replay. Code and more information can be found at https://continual-vlas.github.io/forget-me-not/ --- ### Structure-aware Prompt Adaptation from Seen to Unseen for Open-Vocabulary Compositional Zero-Shot Learning Authors: Yihang Duan, Jiong Wang, Pengpeng Zeng, Ji Zhang, Lei Zhao, Chong Wang, Jingkuan Song, Lianli Gao Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03815v1 The goal of Open-Vocabulary Compositional Zero-Shot Learning (OV-CZSL) is to recognize attribute-object compositions in the open-vocabulary setting, where compositions of both seen and unseen attributes and objects are evaluated. Recently, prompt tuning methods have demonstrated strong generalization capabilities in the closed setting, where only compositions of seen attributes and objects are evaluated, i.e., Compositional Zero-Shot Learning (CZSL). However, directly applying these methods to OV-CZSL may not be sufficient to generalize to unseen attributes, objects and their compositions, as it is limited to seen attributes and objects. Normally, when faced with unseen concepts, humans adopt analogies with seen concepts that have the similar semantics thereby inferring their meaning (e.g., "wet" and "damp", "shirt" and "jacket"). In this paper, we experimentally show that the distribution of semantically related attributes or objects tends to form consistent local structures in the embedding space. Based on the above structures, we propose Structure-aware Prompt Adaptation (SPA) method, which enables models to generalize from seen to unseen attributes and objects. Specifically, in the training stage, we design a Structure-aware Consistency Loss (SCL) that encourages the local structure's consistency of seen attributes and objects in each iteration. In the inference stage, we devise a Structure-guided Adaptation Strategy (SAS) that adaptively aligns the structures of unseen attributes and objects with those of trained seen attributes and objects with similar semantics. Notably, SPA is a plug-and-play method that can be seamlessly integrated into existing CZSL prompt tuning methods. Extensive experiments on OV-CZSL benchmarks demonstrate that SPA achieves competitive closed-set performance while significantly improving open-vocabulary results. --- ### A Bi-Stage Framework for Automatic Development of Pixel-Based Planar Antenna Structures Authors: Khadijeh Askaripour, Adrian Bekasiewicz, Slawomir Koziel Published: 2026-03-04 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2603.03810v1 Development of modern antennas is a cognitive process that intertwines experience-driven determination of topology and tuning of its parameters to fulfill the performance specifications. Alternatively, the task can be formulated as an optimization problem so as to reduce reliance of geometry selection on engineering insight. In this work, a bi-stage framework for automatic generation of antennas is considered. The method determines free-form topology through optimization of interconnections between components (so-called pixels) that constitute the radiator. Here, the process involves global optimization of connections between pixels followed by fine-tuning of the resulting topology using a surrogate-assisted local-search algorithm to fulfill the design re-quirements. The approach has been demonstrated based on two case studies concerning development of broadband and dual-band monopole antennas. --- ### Vector-Quantized Soft Label Compression for Dataset Distillation Authors: Ali Abbasi, Ashkan Shahbazi, Hamed Pirsiavash, Soheil Kolouri Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03808v1 Dataset distillation is an emerging technique for reducing the computational and storage costs of training machine learning models by synthesizing a small, informative subset of data that captures the essential characteristics of a much larger dataset. Recent methods pair synthetic samples and their augmentations with soft labels from a teacher model, enabling student models to generalize effectively despite the small size of the distilled dataset. While soft labels are critical for effective distillation, the storage and communication overhead they incur, especially when accounting for augmentations, is often overlooked. In practice, each distilled sample is associated with multiple soft labels, making them the dominant contributor to storage costs, particularly in large-class settings such as ImageNet-1K. In this paper, we present a rigorous analysis of bit requirements across dataset distillation frameworks, quantifying the storage demands of both distilled samples and their soft labels. To address the overhead, we introduce a vector-quantized autoencoder (VQAE) for compressing soft labels, achieving substantial compression while preserving the effectiveness of the distilled data. We validate our method on both vision and language distillation benchmarks. On ImageNet-1K, our proposed VQAE achieves 30--40x additional compression over RDED, LPLD, SRE2L, and CDA baselines while retaining over $90\%$ of their original performance. --- ### Adaptive Enhancement and Dual-Pooling Sequential Attention for Lightweight Underwater Object Detection with YOLOv10 Authors: Md. Mushibur Rahman, Umme Fawzia Rahim, Enam Ahmed Taufik Published: 2026-03-04 Categories: cs.CV arXiv: https://arxiv.org/abs/2603.03807v1 Underwater object detection constitutes a pivotal endeavor within the realms of marine surveillance and autonomous underwater systems; however, it presents significant challenges due to pronounced visual impairments arising from phenomena such as light absorption, scattering, and diminished contrast. In response to these formidable challenges, this manuscript introduces a streamlined yet robust framework for underwater object detection, grounded in the YOLOv10 architecture. The proposed method integrates a Multi-Stage Adaptive Enhancement module to improve image quality, a Dual-Pooling Sequential Attention (DPSA) mechanism embedded into the backbone to strengthen multi-scale feature representation, and a Focal Generalized IoU Objectness (FGIoU) loss to jointly improve localization accuracy and objectness prediction under class imbalance. Comprehensive experimental evaluations conducted on the RUOD and DUO benchmark datasets substantiate that the proposed DPSA_FGIoU_YOLOv10n attains exceptional performance, achieving mean Average Precision (mAP) scores of 88.9% and 88.0% at IoU threshold 0.5, respectively. In comparison to the baseline YOLOv10n, this represents enhancements of 6.7% for RUOD and 6.2% for DUO, all while preserving a compact model architecture comprising merely 2.8M parameters. These findings validate that the proposed framework establishes an efficacious equilibrium among accuracy, robustness, and real-time operational efficiency, making it suitable for deployment in resource-constrained underwater settings. --- ### Separators in Enhancing Autoregressive Pretraining for Vision Mamba Authors: Hanpeng Liu, Zidan Wang, Shuoxi Zhang, Kaiyuan Gao, Kun He Published: 2026-03-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.03806v2 The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting considerable attention for its efficient handling of long-sequence tasks. Its inherent causal structure makes it particularly well suited for autoregressive pretraining. However, existing autoregressive pretraining methods in vision are largely limited to short-sequence settings and may not fully use Mamba's capacity to model longer contexts. To investigate this setting, we introduce SeparaTors for AutoRegressive pretraining (STAR), a new autoregressive pretraining method for Vision Mamba that explicitly marks the boundaries between different images. STAR increases the patch-token sequence length from 144 to 640 by packing four images and four separator clusters. This is approximately $4.4\times$ the ARM patch-token sequence length. The increase is achieved without changing the resolution of any individual image: we use $192\times192$ inputs for autoregressive pretraining and $224\times224$ inputs for downstream classification fine-tuning. With this long-sequence pretraining scheme, STAR-B achieves 83.5\% EMA top-1 accuracy on ImageNet-1K after 1,600 epochs of pretraining. The learned representation also transfers beyond in-distribution classification: compared with ARM, STAR-B improves COCO box AP from 46.11 to 46.84 and mask AP from 40.74 to 41.45, while raising the mean top-1 accuracy across five ImageNet robustness benchmarks from 55.1\% to 56.8\%. Under the evaluated four-image setting, these results indicate that separator-based long-sequence pretraining improves recognition robustness and dense visual prediction relative to ARM. --- ### Separators in Enhancing Autoregressive Pretraining for Vision Mamba Authors: Hanpeng Liu, Zidan Wang, Shuoxi Zhang, Kaiyuan Gao, Kun He Published: 2026-03-04 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2603.03806v1 The state space model Mamba has recently emerged as a promising paradigm in computer vision, attracting significant attention due to its efficient processing of long sequence tasks. Mamba's inherent causal mechanism renders it particularly suitable for autoregressive pretraining. However, current autoregressive pretraining methods are constrained to short sequence tasks, failing to fully exploit Mamba's prowess in handling extended sequences. To address this limitation, we introduce an innovative autoregressive pretraining method for Vision Mamba that substantially extends the input sequence length. We introduce new \textbf{S}epara\textbf{T}ors for \textbf{A}uto\textbf{R}egressive pretraining to demarcate and differentiate between different images, known as \textbf{STAR}. Specifically, we insert identical separators before each image to demarcate its inception. This strategy enables us to quadruple the input sequence length of Vision Mamba while preserving the original dimensions of the dataset images. Employing this long sequence pretraining technique, our STAR-B model achieved an impressive accuracy of 83.5\% on ImageNet-1k, which is highly competitive in Vision Mamba. These results underscore the potential of our method in enhancing the performance of vision models through improved leveraging of long-range dependencies. --- ### Relational In-Context Learning via Synthetic Pre-training with Structural Prior Authors: Yanbo Wang, Jiaxuan You, Chuan Shi, Muhan Zhang Published: 2026-03-04 Categories: cs.LG, cs.AI, cs.DB arXiv: https://arxiv.org/abs/2603.03805v5 Relational Databases (RDBs) are the backbone of modern business, yet they lack foundation models comparable to those in text or vision. A key obstacle is that high-quality RDBs are private, scarce, and structurally heterogeneous, making internet-scale pre-training infeasible. To overcome this data scarcity, we introduce RDB-PFN, the first relational foundation model trained purely via synthetic data. Inspired by Prior-Data Fitted Networks (PFNs), where synthetic data generated from Structural Causal Models (SCMs) enables reasoning on single tables, we design a Relational Prior Generator to create an infinite stream of diverse RDBs from scratch. Pre-training on over 2 million synthetic single-table and relational tasks, RDB-PFN learns to adapt to any new database instantly via genuine in-context learning. Experiments show that RDB-PFN achieves strong few-shot performance on 19 real-world relational prediction tasks, outperforming state-of-the-art tabular foundation models evaluated on the same DFS-linearized inputs, while using a lightweight architecture and fast inference. The code is available at https://github.com/MuLabPKU/RDBPFN. --- ### Zero-Knowledge Proof (ZKP) Authentication for Offline CBDC Payment System Using IoT Devices Authors: Santanu Mondal, T. Chithralekha Published: 2026-03-04 Categories: cs.CR, cs.AI, cs.CE arXiv: https://arxiv.org/abs/2603.03804v2 Central Bank Digital Currency (CBDCs) are becoming a new digital financial tool aimed at financial inclusion, increased monetary stability, and improved efficiency of payment systems, as they are issued by central banks. One of the most important aspects is that the CBDC must offer secure offline payment methods to users, allowing them to retain cash-like access without violating Anti-Money Laundering and Counter-terrorism Financing (AML/CFT) rules. The offline CBDC ecosystems will provide financial inclusion, empower underserved communities, and ensure equitable access to digital payments, even in connectivity-poor remote locations. With the rapid growth of Internet of Things (IoT) devices in our everyday lives, they are capable of performing secure digital transactions. Integrating offline CBDC payment with IoT devices enables seamless, automated payment without internet connectivity. However, IoT devices face special challenges due to their resource-constrained nature. This makes it difficult to include features such as double-spending prevention, privacy preservation, low-computation operation, and digital identity management. The work proposes a privacy-preserving offline CBDC model with integrated secure elements (SEs), zero-knowledge proofs (ZKPs), and intermittent synchronisation to conduct offline payments on IoT hardware. The proposed model is based on recent improvements in offline CBDC prototypes, regulations and cryptographic design choices such as hybrid architecture that involves using combination of online and offline payment in IoT devices using secure hardware with lightweight zero-knowledge proof cryptographic algorithm. --- ### Unsupervised Surrogate-Assisted Synthesis of Free-Form Planar Antenna Topologies for IoT Applications Authors: Khadijeh Askaripour, Adrian Bekasiewicz, Slawomir Koziel Published: 2026-03-04 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2603.03802v1 Design of antenna structures for Internet of Things (IoT) applications is a challenging problem. Contemporary radiators are often subject to a number of electric and/or radiation-related requirements, but also constraints imposed by specifics of IoT systems and/or intended operational environments. Conventional approaches to antenna design typically involve manual development of topology intertwined with its tuning. Although proved useful, the approach is prone to errors and engineering bias. Alternatively, geometries can be generated and optimized without supervision of the designer. The process can be controlled by suitable algorithms to determine and then adjust the antenna geometry according to the specifications. Unfortunately, automatic design of IoT radiators is associated with challenges such as determination of desirable geometries or high optimization cost. In this work, a variable-fidelity framework for performance-oriented development of free-form antennas represented using the generic simulation models is proposed. The method employs a surrogate-assisted classifier capable of identifying a suitable radiator topology from a set of automatically generated (and stored for potential re-use) candidate designs. The obtained geometry is then subject to a bi-stage tuning performed using a gradient-based optimization engine. The presented framework is demonstrated based on six numerical experiments concerning unsupervised development of bandwidth-enhanced patch antennas dedicated to work within 5 GHz to 6 GHz and 6 GHz to 7 GHz bands, respectively. Extensive benchmarks of the method, as well as the generated topologies are also performed. ---