Abstract:  With generative AI rapidly transforming content creation, programming and knowledge discovery, improving its efficiency has become increasingly urgent. Traditional approaches such as quantization and sparsity are no longer sufficient for today’s complex and diverse models. This talk presents a holistic framework for building efficient and autonomous generative AI through innovations in algorithms, system design and real-world deployment. We explore how understanding intrinsic reasoning in LLMs and diffusion models can reveal critical computational paths, inspire new agent communication paradigms and enhance real-world performance while ensuring safety and scalability. Finally, we outline key challenges and opportunities toward making generative AI both intelligent and sustainable in practice.

Bio: Yiran Chen is the John Cocke Distinguished Professor of Electrical and Computer Engineering at Duke University. He serves as the principal investigator and director of the NSF AI Institute for Edge Computing Leveraging Next Generation Networks (Athena) and co-director of the Duke Center for Computational Evolutionary Intelligence (DCEI). His research group focuses on innovations in emerging memory and storage systems, machine learning and neuromorphic computing, and edge computing. Chen has authored over 700 publications and holds 96 U.S. patents. His work has received widespread recognition, including two Test-of-Time Awards and 14 Best Paper/Poster Awards. He is the recipient of the IEEE Circuits and Systems Society’s Charles A. Desoer Technical Achievement Award and the IEEE Computer Society’s Edward J. McCluskey Technical Achievement Award. He also serves as the inaugural editor-in-chief of the IEEE Transactions on Circuits and Systems for Artificial Intelligence (TCASAI) and the founding chair of the IEEE Circuits and Systems Society’s Machine Learning Circuits and Systems (MLCAS) Technical Committee. Chen is a fellow of the AAAS, ACM, IEEE and NAI, and a member of the European Academy of Sciences and Arts.