Junchen Jiang - Perception-Driven Internet Systems
Abstract: Internet systems serve as vital infrastructure, but what should they optimize for? Traditional approaches optimize system performance metrics, but improvements in system performance often cannot be perceived by the actual consumers of applications. This talk introduces a paradigm shift to optimize for the perception of consumers rather than performance metrics. This new paradigm also embraces the trend that consumers themselves are increasingly ML models (vision models and large language models), which also exhibit a wide range of sensitivities to system performance. This perception-driven paradigm offers new potential to improve the user experience for a broader audience. I will explain several projects as concrete case studies of this new paradigm.
Speakers
Junchen Jiang
Junchen Jiang is an Assistant Professor of Computer Science at the University of Chicago. He received her Ph.D. degree from Carnegie Mellon University in 2017 and a bachelor’s degree from Tsinghua University (Yao Class) in 2011. His research interests are networked systems and their intersections with machine learning. He has received a Google Faculty Research Award, an NSF CAREER Award, and a CMU Computer Science Doctoral Dissertation Award. He has also received multiple best paper and best paper runner-up awards at IEEE Symposium of Edge Computing and ACM CoNEXT.
More information can be found here: https://people.cs.uchicago.edu/~junchenj/