March 2026

arXiv:2603.08898v1 Announce Type: new Abstract: In this paper, we introduce visual query segmentation (VQS), a new paradigm of visual query localization (VQL) that aims to segment all pixel-level occurrences of an object of interest in an untrimmed video, given an external visual query. Compared to existing VQL locating only the last appearance of a target using bounding boxes, VQS enables more comprehensive (i.e., all object occurrences) and precise (i.e., pixel-level masks) localization, making it more practical for real-world […]

Ver mais

arXiv:2603.08897v1 Announce Type: new Abstract: Vision-language models are emerging for autonomous driving, yet their robustness to physical adversarial attacks remains unexplored. This paper presents a systematic framework for comparative adversarial evaluation across three VLM architectures: Dolphins, OmniDrive (Omni-L), and LeapVAD. Using black-box optimization with semantic homogenization for fair comparison, we evaluate physically realizable patch attacks in CARLA simulation. Results reveal severe vulnerabilities across all architectures, sustained multi-frame failures, and critical object detection degradation. Our analysis exposes distinct architectural […]

Ver mais

arXiv:2603.08894v1 Announce Type: new Abstract: Socially shared metacognition (SSM) refers to the collective monitoring and regulation of joint cognitive processes in collaborative problem-solving, and is essential for effective knowledge work and learning. Generative AI (GenAI)-based systems offer new opportunities to support SSM, but emerging evidence suggests that poorly designed systems can encourage over-reliance on AI-generated explicit instruction and erode groups’ capacity to develop autonomous regulatory processes. Group awareness tools (GATs) address this challenge through established design principles that […]

Ver mais

arXiv:2603.08893v1 Announce Type: new Abstract: Recent progress in artificial intelligence has been driven largely by the scaling of centralized large language models through increased parameters, datasets, and computational resources. While effective, this paradigm introduces structural constraints related to compute concentration, energy consumption, data availability, and governance. This paper proposes an alternative architectural approach through the H3LIX Decentralized Frontier Model Architecture (DFMA), a distributed AI framework in which locally operating AI instances generate synthetic learning signals derived from reasoning […]

Ver mais

arXiv:2603.08890v1 Announce Type: new Abstract: To measure the shape similarity of point sets, various notions of the Hausdorff distance under translation are widely studied. In this context, for an $n$-point set $P$ and $m$-point set $Q$ in $mathbb{R}^d$, we consider the task of computing the minimum $d(P,Q+tau)$ over translations $tau in T$, where $d(cdot, cdot)$ denotes the Hausdorff distance under the $L_infty$-norm. We analyze continuous ($T=mathbb{R}^d$) vs. discrete ($T$ is finite) and directed vs. undirected variants. Applying fine-grained […]

Ver mais

arXiv:2603.08889v1 Announce Type: new Abstract: The use of a wide range of sensory modalities is increasingly central to technologies for learning, communication, and affective regulation. During the preschool years, sensory integration develops rapidly, shaping how children perceive and make sense of their environments. A key component of this process is cross-sensory correspondence: the systematic ways in which perceptions in different sensory modalities influence one another. Despite its relevance, little is known about cross-sensory correspondences in preschool-aged children (2-4 […]

Ver mais

arXiv:2603.08887v1 Announce Type: new Abstract: Building on existing $hp$-adaptive algorithms driven by equilibrated-flux estimators from [ESAIM Math. Model. Numer. Anal. 57 (2023), 329–366] and the references therein, we propose a novel $h$-adaptive algorithm for a fixed polynomial degree $p$. We consider a conforming finite element discretization of the Poisson equation in two or three space dimensions. Supposing piecewise polynomial right-hand side, we show that the algorithm yields error contraction at each step, with a contraction factor that is […]

Ver mais

arXiv:2603.08886v1 Announce Type: new Abstract: We study a class of finite-state channels, known as POST channels, in which the previous channel output serves as the current state. A POST channel is deemed approximately memoryless when the state-dependent transition matrices are sufficiently close to one another. For this family of channels, under a surjectivity condition on the associated memoryless reference channel, we show that the feedback capacity coincides with the non-feedback capacity. Consequently, for almost all approximately memoryless POST […]

Ver mais

arXiv:2603.08880v1 Announce Type: new Abstract: Database workloads are increasingly nesting artificial intelligence (AI) and machine learning (ML) pipelines and AI/ML model inferences with data processing, yielding hybrid SQL+AI/ML queries that mix relational operators with expensive, opaque AI/ML operators, often expressed as UDFs. These workloads are challenging to optimize because ML operators behave like black boxes, data-dependent effects such as sparsity, selectivity, and cardinalities can dominate runtime, domain experts often rely on practical heuristics that are difficult to develop […]

Ver mais

arXiv:2603.08879v1 Announce Type: new Abstract: Accessing sensitive patient data for machine learning is challenging due to privacy concerns. Datasets with annotations of personally identifiable information are crucial for developing and testing anonymization systems to enable safe data sharing that complies with privacy regulations. Since accessing real patient data is a bottleneck, synthetic data offers an efficient solution for data scarcity, bypassing privacy regulations that apply to real data. Moreover, neural machine translation can help to create high-quality data […]

Ver mais