Stay updated with the latest research and technology news
arXiv:2603.04325v1 Announce Type: new Abstract: Evaluation of AI systems often requires synthetic test cases, particularly for rare or safety-critical conditions that are difficult to observe...
arXiv:2603.04328v1 Announce Type: new Abstract: We study the deployment performance of machine learning based enforcement systems used in cryptocurrency anti money laundering (AML). Using forward...
arXiv:2603.04329v1 Announce Type: new Abstract: Reliable navigation in cluttered environments requires perception outputs that are not only accurate but also equipped with uncertainty sets suitable...
arXiv:2603.04333v1 Announce Type: new Abstract: Recent work shows that flow matching can be effective for scalar Q-value function estimation in reinforcement learning (RL), but it...
arXiv:2603.04334v1 Announce Type: new Abstract: We present SpotIt+, an open-source tool for evaluating Text-to-SQL systems via bounded equivalence verification. Given a generated SQL query and...
arXiv:2603.04335v1 Announce Type: new Abstract: This paper studies enhanced droop-free control strategies with sparse neighboring communication for achieving effective active power sharing of distributed energy...
arXiv:2603.04337v1 Announce Type: new Abstract: Constructing computer-aided design (CAD) models is labor-intensive but essential for engineering and manufacturing. Recent advances in Large Language Models (LLMs)...
arXiv:2603.04338v1 Announce Type: new Abstract: Synthesizing physically plausible articulated human-object interactions (HOI) without 3D/4D supervision remains a fundamental challenge. While recent zero-shot approaches leverage video...
arXiv:2603.04340v1 Announce Type: new Abstract: Deep learning in cardiac MRI (CMR) is fundamentally constrained by both data scarcity and privacy regulations. This study systematically benchmarks...
arXiv:2603.04341v1 Announce Type: new Abstract: In many CLIP adaptation methods, a blending ratio hyperparameter controls the trade-off between general pretrained CLIP knowledge and the limited,...
arXiv:2603.04343v1 Announce Type: new Abstract: Attributing authorship to paintings is a historically complex task, and one of its main challenges is the limited availability of...
arXiv:2603.04346v1 Announce Type: new Abstract: Large-scale Vision-Language Foundation Models (VLFMs), such as CLIP, now underpin a wide range of computer vision research and applications. VLFMs...
arXiv:2603.04348v1 Announce Type: new Abstract: Pathology report generation remains a relatively under-explored downstream task, primarily due to the gigapixel scale and complex morphological heterogeneity of...
arXiv:2603.04349v1 Announce Type: new Abstract: The ability to understand long videos is vital for embodied intelligent agents, because their effectiveness depends on how well they...
arXiv:2603.04350v1 Announce Type: new Abstract: This paper introduces Exp-ParaDiag, a novel time-parallel method that combines the strength of exponential integrators into the ParaDiag framework. We...
arXiv:2603.04351v1 Announce Type: new Abstract: Robots which make use of soft or compliant inter- actions often leverage tendon-driven actuation which enables actuators to be placed...
arXiv:2603.04352v1 Announce Type: new Abstract: Machines designed for operation in Space, as well as other extreme environments, need to be both resilient and adaptable when...
arXiv:2603.04353v1 Announce Type: new Abstract: Next-generation networks aim to provide performance guarantees to real-time interactive services that require timely and cost-efficient packet delivery. In this...
arXiv:2603.04354v1 Announce Type: new Abstract: Most PDE foundation models are pretrained and fine-tuned on fluid-centric benchmarks. Their utility under extreme-loading material dynamics remains unclear. We...
arXiv:2603.04355v1 Announce Type: new Abstract: Safety-aligned language models refuse harmful requests through learned refusal behaviors encoded in their internal representations. Recent activation-based jailbreaking methods circumvent...
arXiv:2603.04356v1 Announce Type: new Abstract: Recent advances in robot learning have accelerated progress toward generalist robots that can perform everyday tasks in human environments. Yet...
arXiv:2603.04359v1 Announce Type: new Abstract: Quantization can drastically increase the efficiency of large language and vision models, but typically incurs an accuracy drop. Recently, function-preserving...
arXiv:2603.04360v1 Announce Type: new Abstract: The Unscented Kalman Filter (UKF) is a ubiquitous tool for nonlinear state estimation; however, its performance is limited by the...
arXiv:2603.04361v1 Announce Type: new Abstract: Low Earth orbit (LEO) satellite constellations have become a critical enabler for global coverage, utilizing numerous satellites orbiting Earth at...