arXiv:2604.12384v1 Announce Type: new
Abstract: Safety alignment in Large Language Models (LLMs) remains highly fragile during fine-tuning, where even benign adaptation can degrade pre-trained refusal behaviors and enable harmful responses. Existing d…
arXiv:2603.01045v2 Announce Type: replace-cross
Abstract: Large language models are increasingly deployed in multi-agent systems to overcome context limitations by distributing information across agents. Yet whether agents can reliably compute with di…
arXiv:2604.12456v1 Announce Type: cross
Abstract: Zero-shot voice conversion (VC) aims to convert a source utterance into the voice of an unseen target speaker while preserving its linguistic content. Although recent systems have improved conversion q…
arXiv:2512.21652v2 Announce Type: replace-cross
Abstract: Multimodal cardiovascular magnetic resonance (CMR) imaging provides comprehensive and non-invasive insights into cardiovascular disease (CVD) diagnosis and underlying mechanisms. Despite decade…
arXiv:2604.12543v1 Announce Type: new
Abstract: Large Language Models (LLMs) are increasingly used to translate the technical outputs of eXplainable Artificial Intelligence (XAI) methods into accessible natural-language explanations. However, existing…
arXiv:2604.12627v1 Announce Type: new
Abstract: RLVR improves reasoning in large language models, but its effectiveness is often limited by severe reward sparsity on hard problems. Recent hint-based RL methods mitigate sparsity by injecting partial so…
arXiv:2603.27557v2 Announce Type: replace-cross
Abstract: In this paper, we analyze two main factors of Bonafide Resource (BR) or AI-based Generator (AG) which affect the performance and the generality of a Deepfake Speech Detection (DSD) model. To th…
arXiv:2604.12994v1 Announce Type: cross
Abstract: Logical vulnerabilities in software stem from flaws in program logic rather than memory safety, which can lead to critical security failures. Although existing automated program repair techniques prima…
arXiv:2604.12660v1 Announce Type: new
Abstract: In nonmonotonic reasoning from conditional belief bases, an inference operator satisfying syntax splitting postulates allows for taking only the relevant parts of a belief base into account, provided tha…
arXiv:2604.12663v1 Announce Type: new
Abstract: Existing topic modeling methods, from LDA to recent neural and LLM-based approaches, which focus mainly on statistical coherence, often produce redundant or off-target topics that miss the user’s underly…