이슬기

Lee, Seulki

직위

학위

Ph.D.(2021) University of North Carolina at Chapel Hill

대표업적

“Bayesian Code Diffusion for Efficient Automatic Deep Learning Program Optimization”, OSDI 2025
“CAFO: Feature-Centric Explanation on Time Series Classification”, KDD 2024
“Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks”, NeurIPS 2023
“On-NAS: On-Device Neural Architecture Search on Memory-Constrained Intelligent Embedded Systems”, SenSys 2023
“Fast and Scalable In-memory Deep Multitask Learning via Neural Weight Virtualization”, MobiSys 2020