“Beyond Scaling: Adaptive Sensing for Neural Networks in the Physical World”

Recent advances in AI have been driven largely by scaling—bigger models trained on ever-larger datasets—to achieve generalization and robustness. While successful, this paradigm is increasingly costly and brittle, especially in the era of physical AI, where models must operate on data shaped by real-world sensors and complex, shifting environments. In contrast, biological sensory systems adapt dynamically at the input—adjusting pupil size, refocusing gaze, or reallocating attention—rather than relying solely on ever more powerful downstream processing. Motivated by this perspective, I will argue that adaptive sensing should be treated as a first-class principle in AI systems. By proactively modulating sensor parameters (e.g., exposure, sensitivity, and multimodal configurations) and closing the loop between perception and data acquisition, we can substantially mitigate covariate shifts, improve robustness, and reduce computational and energy costs. In this talk, I will present a series of our recent works that instantiate this vision.

Hyung-Sin Kim received the B.S. degree in Electrical Engineering and the M.S. and Ph.D. degrees in Electrical Engineering and Computer Science (EECS) from Seoul National University (SNU), Seoul, South Korea, in 2009, 2011, and 2016, respectively, all with outstanding thesis awards. He was a Postdoctoral Scholar at Network Laboratory (NETLAB), SNU, until August 2016 and Real-time, Intelligent, Secure, Explainable systems (RISELab), University of California, Berkeley, until August 2019, and a Software Engineer at Google Nest until February 2020. He received the Qualcomm Fellowship in 2011 and the National Research Foundation (NRF) Global Ph.D. Fellowship and Postdoctoral Fellowship in 2011 and 2016, respectively. He has published 80 papers and won paper or poster awards at ACM MobiSys, MobiCom, and SenSys. He is currently an Associate Professor in the Graduate School of Data Science at SNU since 2020. His current research interests include physical AI, efficient AI and healthcare.