Publications
Refereed Journal Publications
Peak-Memory-aware Partitioning and Scheduling for Multi-tenant DNN Model
Inference
Jaeho Lee, Ju Min Lee, Haeeun Jeong, Hyunho Kwon, Youngsok
Kim, Yongjun Park, and Hanjun Kim,
in Journal of Systems Architecture, January 2026.
IF=4.1, Q1 (JCR 2025)
Refereed Conference Publications
TeMCO: Tensor Memory Compiler Optimization across Tensor Decompositions in
Deep Learning Inference
Seungbin Song, Ju Min Lee, Haeeun Jeong, Hyunho Kwon, Shinnung
Jeong, Jaeho Lee, and Hanjun Kim,
in Proceedings of the 53rd International Conference on Parallel Processing
(ICPP), August 2024.
Refereed Poster Publications
Approximation-based Inter-PE Communication-free Image Filtering for Commodity
PIM
Chan Lee, Shinnung Jeong, Heelim Choi, Jaeho Lee, Haeeun
Jeong, Hoyun Youm, Ju Min Lee, and Hanjun Kim,
in Proceedings of the 62th Annual Design Automation Conference 2025 -
(Poster) (DAC), June 2025.
Patents
Method of Filtering Image
Hanjun Kim, Chan Lee, Heelim Choi, Haeeun Jeong, Shinnung
Jeong, Ju Min Lee, Jaeho Lee, and Hoyun Youm,
KR Patent App. 10-2025-0181300, November 2025.
Electronic Device for Performing Inference by Partitioning Neural Network Model
in Multi-tenant Environment and Operating Method thereof
Hanjun Kim, Jaeho Lee, Hyunho Kwon, Ju Min Lee, and Haeeun
Jeong,
KR Patent App. 10-2025-0130051, September 2025.
Device and Method with Control of Neural Network Bit Precision
Hanjun Kim, Haeeun Jeong, Hyunho Kwon, Jaeho Lee, Ju Min Lee,
and Heelim Choi,
KR Patent App. 10-2025-0016828, February 2025.
Compile Method and Apparatus for Neural Network
Hanjun Kim, Seungbin Song, Hyunho Kwon, Jumin Lee, Haeeun
Jeong, and Jaeho Lee,
KR Patent App. 10-2024-0088419, July 2024.