* indicates correspondence
¹ indicates co-first authors

• SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators
  • Mingi Yoo¹, Jaeyong Song¹, Jounghoo Lee, Namhyung Kim, Youngsok Kim*, and Jinho Lee*
    HPCA (Accepted), 2023
    Top Conf. Arch. AI/ML
• Slice-and-Forge: Making Better Use of Caches for Graph Convolutional Network Accelerators
  • Mingi Yoo¹, Jaeyong Song¹, Hye Yoon Lee, Jounghoo Lee, Namhyung Kim, Youngsok Kim, and Jinho Lee*
    PACT (Best Paper Award), 2022
    Top Conf. Arch. AI/ML
• ComPreEND: Computation Pruning through Predictive Early Negative Detection for ReLU in a Deep Neural Network Accelerator
  • Namhyung Kim, Hanmin Park, Dongwoo Lee, Sungbum Kang, Jinho Lee* and Kiyoung Choi
    IEEE TC, 2021 (To Appear), Preprint
    SCI Arch. AI/ML
• Making a Better Use of Caches for GCN Accelerators with Feature Slicing and Automatic Tile Morphing
  • Mingi Yoo¹, Jaeyong Song¹, Jounghoo Lee, Namhyung Kim, Youngsok Kim, and Jinho Lee*
    IEEE CAL, 2021, Paper, Video
    SCI Arch. AI/ML
• DANCE: Differentiable Accelerator/Network Co-Exploration
  • Kanghyun Choi¹, Deokki Hong¹, Hojae Yoon¹, Joonsang Yu, Youngsok Kim, Jinho Lee*
    DAC, 2021, Paper, arXiv, Slides
    Top Conf. AI/ML Arch.
• Dataflow Mirroring: Architectural Support for Highly Efficient Fine-Grained Spatial Multitasking on Systolic-Array NPUs
  • Jounghoo Lee¹, Jinwoo Choi¹, Jaeyeon Kim, Jinho Lee, Youngsok Kim
    DAC, 2021, Paper, Author Copy
    Top Conf. Arch. AI/ML
• GradPIM: A Practical Processing-in-DRAM Architecture for Gradient Descent
  • Heesu Kim, Hanmin Park, Taehyun Kim, Kwanheum Cho, Eojin Lee, Soojung Ryu, Hyuk-Jae Lee, Kiyoung Choi, Jinho Lee*
    HPCA, 2021, arXiv, Paper, Slides
    Top Conf. Arch. AI/ML
• Deep neural networks with weighted spikes
  • Jaehyun Kim, Heesu Kim, Subin Huh, Jinho Lee, Kiyoung Choi
    Neurocomputing, 2018
    SCI AI/ML Arch.