Stay updated with the latest research and technology news
arXiv:2510.10216v2 Announce Type: replace Abstract: Language models have shown remarkable proficiency in code generation; nevertheless, ensuring type correctness remains a challenge. Although traditional methods, such...
arXiv:2510.10763v2 Announce Type: replace Abstract: In-stent restenosis (ISR) after percutaneous coronary intervention is a multi-factorial process. Specific morphological lesion characteristics were observed to contribute to...
arXiv:2510.11730v2 Announce Type: replace Abstract: This study demonstrates the first realization of wireless strain, temperature and crack growth sensing within 3D-printed metallic structures using standard...
arXiv:2510.13215v2 Announce Type: replace Abstract: Personalized Learning Path Planning (PLPP) aims to design adaptive learning paths that align with individual goals. While large language models...
arXiv:2510.14388v2 Announce Type: replace Abstract: Building agents that autonomously operate mobile devices has attracted increasing attention. While Vision-Language Models (VLMs) show promise, most existing approaches...
arXiv:2510.14444v2 Announce Type: replace Abstract: Post-training pruning substantially reduces inference costs but often causes severe quality degradation without adapting the remaining weights. For LLMs, such...
arXiv:2510.14586v3 Announce Type: replace Abstract: Accurate prediction of protein-ligand binding poses is crucial for structure-based drug design, yet existing methods struggle to balance speed, accuracy,...
arXiv:2510.17290v2 Announce Type: replace Abstract: Ground-satellite links for 6G networks face critical challenges, including severe path loss, tight size-weight-power limits, and congested spectrum, all of...
arXiv:2510.18534v2 Announce Type: replace Abstract: One of the challenges apparent in the organisation of research projects is the uncertainties around the subject of demonstrators. A...
arXiv:2510.19585v3 Announce Type: replace Abstract: This paper presents a novel task of extracting low-resourced and noisy Latin fragments from mixed-language historical documents with varied layouts....
arXiv:2510.20714v2 Announce Type: replace Abstract: In this study we aim to better align fall risk prediction from the Johns Hopkins Fall Risk Assessment Tool (JHFRAT)...
arXiv:2510.21150v3 Announce Type: replace Abstract: We introduce String Seed of Thought (SSoT), a novel prompting method for LLMs that improves Probabilistic Instruction Following (PIF). We...
arXiv:2510.21413v4 Announce Type: replace Abstract: GenAI-based coding assistants have disrupted software development. The next generation of these tools is agent-based, operating with more autonomy and...
arXiv:2510.21798v2 Announce Type: replace Abstract: Manual annotation remains the gold standard for high-quality, dense temporal video datasets, yet it is inherently time-consuming. Vision-language models can...
arXiv:2510.23484v2 Announce Type: replace Abstract: Self-supervised learning (SSL) has emerged as a powerful paradigm for learning representations without labeled data, often by enforcing invariance to...
arXiv:2510.23912v5 Announce Type: replace Abstract: We theoretically investigate whether the Query, Key, Value weight triplet can be reduced in encoder-only and decoder-only transformers. Under mild...
arXiv:2510.26750v2 Announce Type: replace Abstract: Systematic reviews and mapping studies are critical to synthesize research, identify gaps, and guide future work, but are often labor-intensive...
arXiv:2510.26829v3 Announce Type: replace Abstract: We show that continual pretraining on plausible misinformation can overwrite specific factual knowledge in large language models without degrading overall...
arXiv:2511.00732v2 Announce Type: replace Abstract: Spiking Neural Networks (SNNs) are a promising, energy-efficient alternative to standard Artificial Neural Networks (ANNs) and are particularly well-suited to...
arXiv:2511.02071v2 Announce Type: replace Abstract: Scientific experimentation and manufacturing rely on prolonged protocol development and complex, multi-step implementation, which require continuous human expertise for precise...
arXiv:2511.05885v3 Announce Type: replace Abstract: Sequential recommendations (SR) predict users' future interactions based on their historical behavior. The rise of Large Language Models (LLMs) has...
arXiv:2511.05980v2 Announce Type: replace Abstract: Foundation models for time series imputation remain largely unexplored. Recently, two such models, TabPFN-TS and MoTM, have emerged. These models...
arXiv:2511.06516v2 Announce Type: replace Abstract: Many applications of large language models (LLMs) require only a narrow capability, yet common post-training quantization (PTQ) pipelines assign precision...
arXiv:2511.06701v2 Announce Type: replace Abstract: AI-Scientist systems that use large language models to automate research risk generating spurious discoveries through uncontrolled multiple testing. We present...