This paper develops low-rank operator learning methods that adaptively couple physics-informed constraints with neural operators, enabling efficient and accurate modeling of multiscale partial differential equations.
This paper applies techniques from randomized numerical linear algebra to improve the scalability and efficiency of high-dimensional embedding search, balancing mathematical rigor with practical performance in AI systems.
This paper surveys applications of AI in historical research, from text mining to network modeling, highlighting opportunities and limitations for advancing the study of civilizations and cultural evolution.
This paper introduces a hybrid framework combining semantic role labeling, rule-based systems, and structured prompts to improve systematic reasoning and compositional generalization in deep learning models.
This paper develops a comprehensive framework to measure the efficiency, scalability, and domain adaptability of RAG systems, bridging academic evaluation with enterprise deployment.