Stay updated with the latest research and technology news
arXiv:2602.14910v1 Announce Type: new Abstract: Current approaches to AI training treat reasoning as an emergent property of scale. We argue instead that robust reasoning emerges...
arXiv:2602.14912v1 Announce Type: new Abstract: Residual-based a~posteriori error estimators are derived for the modified Morley FEM, proposed by Wang, Xu, Hu [J. Comput. Math, 24(2),...
arXiv:2602.14913v1 Announce Type: new Abstract: Conformal prediction (CP) offers distribution-free marginal coverage guarantees under an exchangeability assumption, but these guarantees can fail if the data...
arXiv:2602.14914v1 Announce Type: new Abstract: Off-policy evaluation (OPE) is essential for assessing ranking and recommendation systems without costly online interventions. Self-Normalised Inverse Propensity Scoring (SNIPS)...
arXiv:2602.14915v1 Announce Type: new Abstract: Both the antiferromagnetic Ising model and the hard-core model could be said to be tractable on line graphs of bounded...
arXiv:2602.14917v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) such as OpenAI o1 and DeepSeek-R1 have shown excellent performance in reasoning tasks using long reasoning...
arXiv:2602.14919v1 Announce Type: new Abstract: Hypergraph Neural Networks (HyGNNs) have demonstrated remarkable success in modeling higher-order relationships among entities. However, their performance often degrades on...
arXiv:2602.14921v1 Announce Type: new Abstract: We study the approximation of $L_p$-functions, $p\in (0,\infty]$, on cylindrical space-time domains $\Omega_T:=[0,T]\times \Omega$, $0
arXiv:2602.14922v1 Announce Type: new Abstract: To address the ``reusability dilemma'' and structural hallucinations in enterprise Agentic AI,this paper proposes ReusStdFlow, a framework centered on a...
arXiv:2602.14926v1 Announce Type: new Abstract: To address the global health threat of antimicrobial resistance, antimicrobial peptides (AMP) are being explored for their potent and promising...
arXiv:2602.14929v1 Announce Type: new Abstract: Aligning ground-level imagery with geo-registered satellite maps is crucial for mapping, navigation, and situational awareness, yet remains challenging under large...
arXiv:2602.14938v1 Announce Type: new Abstract: In machine unlearning, $(\varepsilon,\delta)-$unlearning is a popular framework that provides formal guarantees on the effectiveness of the removal of a...
arXiv:2602.14939v1 Announce Type: new Abstract: In recent times, there has been considerable interest in fault detection within electrical power systems, garnering attention from both academic...
arXiv:2602.14940v1 Announce Type: new Abstract: Commons suffer from neglect, free-riding, and a persistent deficit of care. Inspired by Shinto animism -- where every forest, river,...
arXiv:2602.14941v1 Announce Type: new Abstract: Maintaining spatial world consistency over long horizons remains a central challenge for camera-controllable video generation. Existing memory-based approaches often condition...
arXiv:2602.14947v1 Announce Type: new Abstract: This paper presents a physics-informed neural network approach for dynamic modeling of saturable synchronous machines, including cases with spatial harmonics....
arXiv:2602.14948v1 Announce Type: new Abstract: Advanced Aerial Mobility (AAM) operations require strategic flight planning services that predict both spatial and temporal uncertainties to safely validate...
arXiv:2602.14951v1 Announce Type: new Abstract: AI agents deployed on decentralized infrastructures are beginning to exhibit properties that extend beyond autonomy toward what we describe as...
arXiv:2602.14952v1 Announce Type: new Abstract: We consider the general problem of learning a predictor that satisfies multiple objectives of interest simultaneously, a broad framework that...
arXiv:2602.14955v1 Announce Type: new Abstract: We present a domain-grounded framework and benchmark for tool-aware plan generation in contact centers, where answering a query for business...
arXiv:2602.14958v1 Announce Type: new Abstract: Kinematics of mechanisms is intricately coupled to their geometry and their utility often arises out of the ability to perform...
arXiv:2602.14960v1 Announce Type: new Abstract: Neural models are increasingly used in Web-scale Information Retrieval (IR). However, relying on these models introduces substantial computational and energy...
arXiv:2602.14961v1 Announce Type: new Abstract: We initiate the study of distortion in stable matching. Concretely, we aim to design algorithms that have limited access to...
arXiv:2602.14965v1 Announce Type: new Abstract: Articulated objects are central to interactive 3D applications, including embodied AI, robotics, and VR/AR, where functional part decomposition and kinematic...