Scientists Create a “Periodic Table” for Artificial Intelligence

Researchers have proposed a unifying mathematical framework that helps explain why many successful multimodal AI systems work ...
IEEE

LYRICEL: Knowledge Graphs Combined With Large Language Models and Machine Learning for Cross-Cultural Analysis of Lyrics—The Case of Greek Songs

Abstract: This paper presents LYRICEL, a framework integrating Knowledge Graph (KG) representation learning, Large Language Models (LLMs), and machine learning for reliable, explainable, and ...
IEEE

Task-Oriented Feature Compression for Multimodal Understanding via Device-Edge Co-Inference

Abstract: With the rapid development of large multimodal models (LMMs), multimodal understanding applications are emerging. As most LMM inference requests originate from edge devices with limited ...