Stay updated with the latest research and technology news
arXiv:2503.16553v3 Announce Type: replace Abstract: Large Language Models (LLMs) are widely applied to domain-specific tasks due to their massive general knowledge and remarkable inference capacities....
arXiv:2503.16718v4 Announce Type: replace Abstract: Speaker verification is a typical zero-shot learning task, where inference of unseen classes is performed by comparing embeddings of test...
arXiv:2503.17279v5 Announce Type: replace Abstract: The meaning conveyed by a sentence often depends on the context in which it appears. Despite the progress of sentence...
arXiv:2503.19859v2 Announce Type: replace Abstract: The substantial computational demands of modern large-scale deep learning present significant challenges for efficient training and deployment. Recent research has...
arXiv:2503.21223v5 Announce Type: replace Abstract: Recently, the emergence of large language models (LLMs) has motivated integrating language descriptions into graphs, forming text-attributed graphs (TAGs) that...
arXiv:2503.23993v2 Announce Type: replace Abstract: The depth completion task is a critical problem in autonomous driving, involving the generation of dense depth maps from sparse...
arXiv:2503.24047v3 Announce Type: replace Abstract: As scientific research becomes increasingly complex, innovative tools are needed to manage vast data, facilitate interdisciplinary collaboration, and accelerate discovery....
arXiv:2504.00573v2 Announce Type: replace Abstract: Retrieval-Augmented Language Models boost task performance, owing to the retriever that provides external knowledge. Although crucial, the retriever primarily focuses...
arXiv:2504.01154v2 Announce Type: replace Abstract: Fairness is an important consideration for dynamic resource allocation in multi-agent systems. Many existing methods treat fairness as a one-shot...
arXiv:2504.01842v3 Announce Type: replace Abstract: This paper introduces the shapr R package, a versatile tool for generating Shapley value-based prediction explanations for machine learning and...
arXiv:2504.01847v3 Announce Type: replace Abstract: Sets of equations E play an important computational role in rewriting-based systems R by defining an equivalence relation =E inducing...
arXiv:2504.03408v3 Announce Type: replace Abstract: We propose a novel multimesh rational approximation scheme for the numerical solution of the (homogeneous) Dirichlet problem for the spectral...
arXiv:2504.05002v2 Announce Type: replace Abstract: Smart contracts deployed on blockchain platforms are vulnerable to various security vulnerabilities. However, only a small number of Ethereum contracts...
arXiv:2504.05006v2 Announce Type: replace Abstract: Decentralized applications (DApps) face significant security risks due to vulnerabilities in smart contracts, with traditional detection methods struggling to address...
arXiv:2504.05520v3 Announce Type: replace Abstract: Reinforcement finetuning (RFT) has shown great potential for enhancing the mathematical reasoning capabilities of large language models (LLMs), but it...
arXiv:2504.05711v2 Announce Type: replace Abstract: Enforcing archival standards requires specialized expertise, and manually creating metadata descriptions for archival materials is a tedious and error-prone task....
arXiv:2504.06592v4 Announce Type: replace Abstract: Verifying traces of systems is a central topic in formal verification. We study model checking of Markov chains (MCs) against...
arXiv:2504.08697v4 Announce Type: replace Abstract: Span annotation - annotating specific text features at the span level - can be used to evaluate texts where single-score...
arXiv:2504.09970v2 Announce Type: replace Abstract: Graph clustering is a longstanding topic in machine learning. Recently, deep methods have achieved results but still require predefined cluster...
arXiv:2504.11450v2 Announce Type: replace Abstract: We study the algorithmic problem of finding a large independent set in the Erd{\"o}s-R\'{e}nyi random graph $G(n,p)$. For constant $p$...
arXiv:2504.12114v2 Announce Type: replace Abstract: Retinal surgery requires extreme precision due to constrained anatomical spaces in the human retina. To assist surgeons achieve this level...
arXiv:2504.12720v2 Announce Type: replace Abstract: With the booming development of blockchain technology, smart contracts have been widely used in finance, supply chain, Internet of things...
arXiv:2504.14325v4 Announce Type: replace Abstract: Letting AI agents interact in multi-agent applications adds a layer of complexity to the interpretability and prediction of AI outcomes,...
arXiv:2504.16063v2 Announce Type: replace Abstract: News data have become essential resources across various disciplines. Still, access to full-text news corpora remains challenging due to high...