arXiv:2602.07125v1 Announce Type: new Abstract: Universal Multimodal Retrieval (UMR) seeks any-to-any search across text and vision, yet modern embedding models remain brittle when queries require latent reasoning (e.g., resolving underspecified references or matching compositional constraints). We argue this brittleness is often data-induced: when images carry “silent” evidence and queries leave key semantics implicit, a single embedding pass must both reason and compress, encouraging spurious feature matching. We propose a data-centric framework that decouples these roles by externalizing reasoning […]

Ver mais

arXiv:2601.07853v1 Announce Type: new Abstract: Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to plan, invoke tools, and manipulate mutable state introduce new security risks in high-stakes and highly regulated financial environments. However, existing safety evaluations largely focus on language-model-level content compliance or abstract agent settings, failing to capture execution-grounded risks arising from real operational workflows and state-changing actions. To bridge this gap, we […]

Ver mais

arXiv:2602.03864v1 Announce Type: new Abstract: Large language models (LLMs) have rapidly emerged in civil and environmental engineering (CEE) research, education, and practice as a tool for project ideation, execution, and communication. However, it is unknown how prevalent LLM adoption is across CEE scholarship and whether it meaningfully alters research prose. Inspired by a recent analysis of biomedical abstracts, this study adapts a vocabulary-based frequency-shift methodology to estimate the incidence of LLM-written abstracts in the field of CEE scholarship […]

Ver mais

arXiv:2602.03215v1 Announce Type: new Abstract: Accurate estimation of tacrolimus exposure, quantified by the area under the concentration-time curve (AUC), is essential for precision dosing after renal transplantation. Current practice relies on population pharmacokinetic (PopPK) models based on nonlinear mixed-effects (NLME) methods. However, these models depend on rigid, pre-specified assumptions and may struggle to capture complex, patient-specific dynamics, leading to model misspecification. In this study, we introduce a novel data-driven alternative based on Latent Ordinary Differential Equations (Latent ODEs) […]

Ver mais

arXiv:2601.09871v1 Announce Type: new Abstract: Human-AI complementarity is the claim that a human supported by an AI system can outperform either alone in a decision-making process. Since its introduction in the human-AI interaction literature, it has gained traction by generalizing the reliance paradigm and by offering a more practical alternative to the contested construct of ‘trust in AI.’ Yet complementarity faces key theoretical challenges: it lacks precise theoretical anchoring, it is formalized just as a post hoc indicator […]

Ver mais

arXiv:2602.07143v1 Announce Type: new Abstract: Audio is a critical component of multimodal perception, and any truly intelligent system must demonstrate a wide range of auditory capabilities. These capabilities include transcription, classification, retrieval, reasoning, segmentation, clustering, reranking, and reconstruction. Fundamentally, each task involves transforming a raw audio signal into a meaningful ’embedding’ – be it a single vector, a sequence of continuous or discrete representations, or another structured form – which then serves as the basis for generating the […]

Ver mais

arXiv:2602.22343v1 Announce Type: new Abstract: As interfaces evolve from static user pathways to dynamic human-AI collaboration, no standard methods exist for selecting appropriate interface patterns based on user needs and task complexity. Existing frameworks only provide guiding principles for designing AI agent capabilities. We propose a dimensional framework based on workflow complexity, AI autonomy, and AI reasoning to guide the design of context-aware, scalable AI interfaces aka modalities (e.g., prompt bars, split screens, full screens, etc.). The framework […]

Ver mais

Global air quality forecasting grapples with extreme spatial heterogeneity and the poor generalization of existing transductive models to unseen regions. To tackle this, we propose OmniAir, a semantic topology learning framework tailored for global station-level prediction. By encoding invariant physical environmental attributes into generalizable station identities and dynamically constructing adaptive sparse topologies, our approach effectively captures long-range non-Euclidean correlations and physical diffusion patterns across unevenly distributed global networks. We further curate WorldAir, a massive dataset covering over 7,800 […]

Ver mais

arXiv:2603.06703v1 Announce Type: new Abstract: Graph databases are widely used in systems that manage rich metadata, yet current modelling practices often embed descriptive attributes directly in nodes, leading to redundancy and inconsistent semantics. This paper introduces the Fifth Graph Normal Form (5GNF), a trait-based normalization framework for property graphs that represents recurring metadata as canonical Trait Nodes connected through HAS_TRAIT relationships. We formalize trait functional dependencies (tFDs) and present the TraitExtraction5GNF algorithm for identifying and extracting reusable traits. […]

Ver mais