Stay updated with the latest research and technology news
arXiv:2503.07982v4 Announce Type: replace Abstract: High-quality instance and panoptic segmentation has traditionally relied on dense instance-level annotations such as masks, boxes, or points, which are...
arXiv:2503.11238v2 Announce Type: replace Abstract: We study the problem of finding a subgroup of a given order in a finite group, where the group is...
arXiv:2503.15133v2 Announce Type: replace Abstract: While sentiment analysis has advanced from sentence to aspect-level, i.e., the identification of concrete terms related to a sentiment, the...
arXiv:2503.18659v3 Announce Type: replace Abstract: This article is concerned with a new filtered two-step variational integrator for solving the charged-particle dynamics in a mildly non-uniform...
arXiv:2503.23655v4 Announce Type: replace Abstract: This paper focuses on hyperchaotic-map construction and proposes a 3D-Cascading Crossing Coupling framework (3D-CCC), which cascades, crosses, and couples three...
arXiv:2504.00648v2 Announce Type: replace Abstract: We develop and analyse residual-based a posteriori error estimates for the virtual element discretisation of a nonlinear stress-assisted diffusion problem...
arXiv:2504.06533v3 Announce Type: replace Abstract: Graph Edit Distance (GED) is a widely used measure of graph similarity, valued for its flexibility in encoding domain knowledge...
arXiv:2504.07835v5 Announce Type: replace Abstract: Motivated by the growing demand for low-precision arithmetic in computational science, we exploit lower-precision emulation in Python -- widely regarded...
arXiv:2504.13703v3 Announce Type: replace Abstract: Group recommendation aims to recommend tailored items to groups of users, where the key challenge is modeling a consensus that...
arXiv:2504.14249v2 Announce Type: replace Abstract: Restoring multiple degradations efficiently via just one model has become increasingly significant and impactful, especially with the proliferation of mobile...
arXiv:2504.14868v2 Announce Type: replace Abstract: Modern text-to-image generation systems have enabled the creation of remarkably realistic and high-quality visuals, yet they often falter when handling...
arXiv:2504.16299v4 Announce Type: replace Abstract: Hoeffding's formulation and solution to the universal hypothesis testing (UHT) problem had a profound impact on many subsequent works dealing...
arXiv:2504.16874v3 Announce Type: replace Abstract: Reconfigurable intelligent surfaces (RISs) are emerging as key enablers of reliable industrial automation in the millimeter-wave (mmWave) band, particularly in...
arXiv:2504.17097v2 Announce Type: replace Abstract: The approximate minimum degree algorithm is widely used before numerical factorization to reduce fill-in for sparse matrices. While considerable attention...
arXiv:2504.17203v4 Announce Type: replace Abstract: The demand for high-fidelity test data is paramount in industrial settings where access to production data is largely restricted. Traditional...
arXiv:2504.20094v3 Announce Type: replace Abstract: Conversational recommender systems (CRS) have advanced with large language models, showing strong results in domains like movies. These domains typically...
arXiv:2504.21841v3 Announce Type: replace Abstract: Neural network-based policies have demonstrated success in many robotic applications, but often lack human-explanability, which poses challenges in safety-critical deployments....
arXiv:2505.03801v2 Announce Type: replace Abstract: Low-rank and sparse composite approximation is a natural idea to compress Large Language Models (LLMs). However, such an idea faces...
arXiv:2505.06721v3 Announce Type: replace Abstract: Understanding how co-authors distribute credit is critical for accurately assessing scholarly collaboration. In this study, we uncover the implicit structures...
arXiv:2505.06888v3 Announce Type: replace Abstract: In the "Big Data" era, a lot of data must be processed and moved between processing and memory units. New...
arXiv:2505.08246v2 Announce Type: replace Abstract: Diffusion models, today's leading image generative models, estimate the score function, i.e. the gradient of the log probability of (perturbed)...
arXiv:2505.09198v2 Announce Type: replace Abstract: The Shapes Constraint Language (SHACL) is the W3C Recommendation for validating a single RDF graph. This makes SHACL inadequate for...
arXiv:2505.11265v2 Announce Type: replace Abstract: Modern open and softwarized systems -- such as O-RAN telecom networks and cloud computing platforms -- host independently developed applications...
arXiv:2505.12481v2 Announce Type: replace Abstract: The operator splitting method has been widely used to solve differential equations by splitting the equation into more manageable parts....