Stay updated with the latest research and technology news
arXiv:2510.02389v3 Announce Type: replace Abstract: Large language models show promise for vulnerability discovery, yet prevailing methods inspect code in isolation, struggle with long contexts, and...
arXiv:2510.02712v4 Announce Type: replace Abstract: Large Language Models (LLMs) have revolutionized conversational AI, yet their robustness in extended multi-turn dialogues remains poorly understood. Existing evaluation...
arXiv:2510.03969v2 Announce Type: replace Abstract: Large Language Models (LLMs) can produce catastrophic responses in conversational settings that pose serious risks to public safety and security.Existing...
arXiv:2510.04192v2 Announce Type: replace Abstract: The growing electricity demand and use of smart appliances are placing pressure on power grids, making efficient energy management more...
arXiv:2510.04437v4 Announce Type: replace Abstract: Against the backdrop of deepening digital and intelligent transformation in human resource management, traditional recruitment models struggle to fully meet...
arXiv:2510.04441v2 Announce Type: replace Abstract: Domain generalization (DG) is the problem of generalizing from several distributions (or domains), for which labeled training data are available,...
arXiv:2510.04670v3 Announce Type: replace Abstract: Naturalistic fMRI encoding must handle multimodal inputs, shifting fusion styles, and pronounced inter-subject variability. We introduce AFIRE (Agnostic Framework for...
arXiv:2510.04769v2 Announce Type: replace Abstract: Many machine learning algorithms rely on iterative updates of uncertainty representations, ranging from variational inference and expectation-maximization, to reinforcement learning,...
arXiv:2510.05975v5 Announce Type: replace Abstract: Approximate nearest neighbor (ANN) search in high-dimensional metric spaces is a fundamental problem with many applications. Over the past decade,...
arXiv:2510.06050v3 Announce Type: replace Abstract: Temporal point processes (TPPs) are a fundamental tool for modeling event sequences in continuous time, but most existing approaches rely...
arXiv:2510.07473v2 Announce Type: replace Abstract: Hierarchical data with multiple observations per group is ubiquitous in empirical sciences and is often analyzed using mixed-effects regression. In...
arXiv:2510.07896v2 Announce Type: replace Abstract: Large Language Models (LLMs) require efficient knowledge editing (KE) to update factual information, yet existing methods exhibit significant performance decay...
arXiv:2510.08810v2 Announce Type: replace Abstract: Library migration is the process of replacing a library with a similar one in a software project. Manual library migration...
arXiv:2510.09492v2 Announce Type: replace Abstract: Generative AI (GenAI) tools are increasingly pervasive, pushing instructors to redesign how students use GenAI tools in coursework. We conceptualize...
arXiv:2510.09712v2 Announce Type: replace Abstract: Online fake news profoundly distorts public judgment and erodes trust in social platforms. While existing detectors achieve competitive performance on...
arXiv:2510.10540v2 Announce Type: replace Abstract: Is module-lattice reduction better than unstructured lattice reduction? This question was highlighted as 'Q8' in the Kyber NIST standardization submission...
arXiv:2510.11955v3 Announce Type: replace Abstract: Modern continuous-time generative models typically induce \emph{V-shaped} flows: each sample travels independently along a nearly straight trajectory from the prior...
arXiv:2510.12780v2 Announce Type: replace Abstract: Voice anonymization techniques have been found to successfully obscure a speaker's acoustic identity in short, isolated utterances in benchmarks such...
arXiv:2510.13021v2 Announce Type: replace Abstract: This paper is interested in the computation of stresses within jammed packings of rigid polygonal cells. The cells are considered...
arXiv:2510.13025v2 Announce Type: replace Abstract: The Koopman operator provides a powerful framework for modeling dynamical systems and has attracted growing interest from the machine learning...
arXiv:2510.13060v2 Announce Type: replace Abstract: Reverse Kullback-Leibler (KL) divergence-based regularization with respect to a fixed reference policy is widely used in modern reinforcement learning to...
arXiv:2510.13272v2 Announce Type: replace Abstract: Inspired by the success of reinforcement learning (RL) in Large Language Model (LLM) training for domains like math and code,...
arXiv:2510.13580v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit substantial performance disparities across languages, particularly between high- and low-resource settings. We propose a framework...
arXiv:2510.13893v2 Announce Type: replace Abstract: Jailbreaking techniques pose a significant threat to the safety of Large Language Models (LLMs). Existing defenses typically focus on single-turn...