Dongkuan "DK" Xu

About

Dongkuan Xu is an assistant professor in the Department of Computer Science at NC State University, where he leads the Generative Intelligent Computing (GIC) Lab. His research spans machine learning, natural language processing, and computer vision, with a focus on building scalable, efficient, and reliable AI systems. Xu investigates inference-time optimization, test-time adaptation, and computational efficiency in large language models, diffusion models, and other generative AI frameworks. His work explores test-time training, self-refinement, model compression, conditional computation, and hardware-algorithm co-design to improve performance while minimizing energy and compute costs. He also advances trustworthy AI through uncertainty-aware learning and robust generalization, enabling adaptive systems that can learn from limited supervision in dynamic environments. His research has been applied in education, networking, robotics, agriculture, sustainability, climate, transportation, and healthcare. Xu’s work has received recognition including the AAAI Best Demonstration Award, Best Poster Award at the AAAI Spring Symposium on GenAI@Edge, NVIDIA Academic Grant, Microsoft Accelerating Foundation Models Research Award, NCSU Carla Savage Award, and best paper honors at IEEE IPCCC and ICCCN. He regularly serves as a panelist, area chair, and reviewer for the NSF and major conferences, and has chaired workshops at DAC, CVPR, AAAI, and KDD. His long-term goal is to democratize access to generative AI and enhance its reliability and usability across real-world applications.

Research Performance Summary

Last 10 Years Publication Activity

This timeline shows the professor's yearly publication activity.

Publication Venues and Collaboration

Research Impact by Period

Contact and Professional Links

Detected Research Keywords