large language models

Blockchain-Enabled Artificial Intelligence and AI Agents for Secure Data Sharing and Cybersecurity Applications

This paper presents a meta-synthesis that draws together four constituent studies covering adversarial machine learning, AI-powered anomaly detection in cloud environments, automated vulnerability patching by multi-agent large language model (LLM) pipelines, and the broader landscape of securing AI systems across their...

On-device large language model-powered intelligent copilot for on-site construction tutorials

Bilateral Kernel Regularization for Few-Shot Adaptation of Large Vision-Language Models

Multi-LLM Prototype: Open-source software for adaptive orchestration, conflict resolution, and cost-aware routing across heterogeneous large language models

Semantic metadata extraction from crop model components with large language models to facilitate platform interoperability

Large Vision Language Models With Object Structure Alignment for Image Matching

Home-based sarcopenia diagnosis via multimodal gait analysis and personalized large language model intervention

Estimating difficulty for the open-ended reading comprehension questions via Large Language Models

RAG Learner: An Interactive Tool for Teaching Retrieval-Augmented Generation

RAG Learner is designed as an interactive tool to teach core RAG concepts through structured modules and demonstrated significant learning gains with 26 university participants, alongside consistently high perceived effectiveness.

AI: Stare Non Decisis

It is argued that preserving the Enlightenment commitment to sapere aude may well require the redesign of legal and educational institutions around verification, accountability, transparency, and stewardship.

From knowledge to rules: Explainable molecular optimization with Large Language Models

Low-Latency Turn-Taking via Context-Aware Preface Generation in a Real-World Dialogue Robot

Large language model (LLM)-based dialogue systems suffer response delays because generation begins only after final speech recognition. While fixed fillers are a workaround, they become unnatural over time. We propose a two-stage incremental framework that decouples prefatory-response preparation from speech onset. Onc...