Efficient Computing Lab.

The Efficient Computing Laboratory (ECL) is a part of Department of AI at UST ETRI Campus. Gajeong-ro 218, Yuseong-gu, Daejoen South Korea.

ust.jpg

7-416 ETRI, Gajeong-ro 218,Yuseong-gu123, Daejeon, South Korea

Welcome to the Efficient Computing Lab. We focus on energy efficiency, system optimization, user experience, and sustainable tech solutions. Our research interests are the followings:

• Model Compression: Enhancing machine learning models’ efficiency through techniques like pruning, quantization, and knowledge distillation for better performance in resource-limited settings.
• AI Compiler: Developing optimized AI compilers to reduce computational power, energy use, and execution time, improving efficiency and sustainability.

For detailed research areas and insights into graduate life, please refer to the following slides. Students interested in pursuing graduate studies are encouraged to contact me directly after following the application instructions provided in the slides.

You can reach me at: leejaymin_at_etri_dot_re_dot_kr.

News

Jan 13, 2026 CNN Compression via Channel-Wise Variance-Based Filter Pruning was accepted at IEEE Access. Congratulations:tada:
Dec 24, 2025 Outstanding advising award – faculty advisor for sehyeon oh (ust research paper award)
Dec 23, 2025 Ust research paper award – sehyeon oh (etri representative student)
Dec 5, 2025 Sehyeon oh received the undang student paper award from kips
Nov 12, 2025 IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers was accepted at IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026! Round 2 acceptance rate was 41.1% (Round 1: 6.4%), and the overall acceptance rate reached 26.4%. Congratulations:tada:
Nov 9, 2025 Target-Aware Neural Network Execution via Compiler-Guided Pruning was accepted at IEEE Transactions on Mobile Computing (IEEE TMC). Congratulations:tada:
Sep 8, 2025 Efficient Dataflow-flexible DNN Accelerator was accepted at Future Generation Computer Systems (FGCS). Congratulations:tada:

Selected Publications

2026

  1. WACV
    IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers
    Gihwan KimJemin Lee, and Hyungshin Kim
    In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) 2026, Round 1 acceptance rate 6.4%, Round 2 acceptance rate 41.1%, Overall acceptance rate 26.4%, Feb 2026

2025

  1. Target-Aware Neural Network Execution via Compiler-Guided Pruning
    JooHyoung Cha, Taeho KimJemin Lee*Sangtae Ha, and Yongin Kwon*
    IEEE Transactions on Mobile Computing (to appear), Accepted, JCR24 IF 9.2 Top 3.29% Nov. 9, 2025, ISSN: 1536-1233, Nov 2025
  2. CASESArtifacts
    Luthier: Bridging Auto-Tuning and Vendor Libraries for Efficient Deep Learning Inference Artifacts Available Artifacts Evaluated – Functional
    Yongin Kwon, JooHyoung Cha, Sehyeon Oh, Misun YuJeman Park, and Jemin Lee*
    In ACM International Conference on Compilers, Architectures, and Synthesis for Embedded Systems (ESWEEK CASES 2025) (NRF BK21+ IF: 2, Acceptance Rate 28.2% (20 papers accepted out of 71 submitted)) and ACM Transactions on Embedded Computing Systems (TECS) Vol. 24, No. 5s, pp. 1–23 ISSN:1539-9087, September 29, 2025., Sep 2025
  3. IJCAI
    Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant
    Jemin LeeSihyeong ParkJinse Kwon, Jihun Oh, and Yongin Kwon*
    In International Joint Conferences on Artificial Intelligence (IJCAI) Aug. 22, 2025, NRF BK21+ IF: 4, Acceptance Rate 19.3% (1042 papers accepted out of 5404 submitted)., Aug 2025
  4. LCTES
    Multi-Level Machine Learning-Guided Autotuning for Efficient Code Generation on a Deep Learning Accelerator
    JooHyoung Cha, Munyoung Lee, Jinse KwonJemin Lee, and Yongin Kwon
    In The 26th ACM SIGPLAN/SIGBED International Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES) Jun. 17, 2025, To appear, NRF BK21+ IF: 2, Acceptance Rate 38% (16 papers accepted out of 42 submitted)., Jun 2025

2024

  1. IEEE IoT J.
    Q-HyViT: Post-Training Quantization for Hybrid Vision Transformer with Bridge Block Reconstruction for IoT Systems
    Jemin LeeYongin KwonMisun YuJeman Park, and Hwanjun Song
    IEEE Internet of Things Journal Vol. 11, Issue 22, pp.36384-36396, ISSN: 2327-4662, Nov. 15, 2024 (JCR24 IF: 8.9 Top 4.07%), Nov 2024
  2. IROS
    Visual Preference Inference: An Image Sequence-Based Preference Reasoning in Tabletop Object Manipulation
    Joonhyung Lee, Sangbeom Park, Yongin KwonJemin LeeMinwook Ahn, and Sungjoon Choi
    In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024), 14 Oct. 2024, Oct 2024

2022

  1. CPrune: Compiler-informed model pruning for efficient target-aware DNN execution
    T. KimYongin KwonJemin LeeTaeho Kim, and Sangtae Ha
    In European Conference on Computer Vision (ECCV), pp.651–667, Oct. 23-27, 2022, NRF BK21+ IF: 2, Acceptance Rate 28% (1,650 papers accepted out of 5,803 submitted), doi: https://doi.org/10.1007/978-3-031-20044-1_37, Oct 2022

2020

  1. PASS: Reducing redundant notifications between a smartphone and a smartwatch for energy saving
    Jemin LeeUichin Lee, and Hyungshin Kim
    IEEE Transactions on Mobile Computing,(impact factor: 5.538, JCR20: Top 17%, telecommunications rank #16 out of 91), ISSN: 1536-1233, doi: https://doi.org/10.1109/TMC.2019.2930506, Nov 2020

2019

  1. Fire in your hands: Understanding thermal behavior of smartphones
    Soowon Kang, Hyeonwoo Choi, Sooyoung Park, Chunjong ParkJemin LeeUichin Lee, and Sung-Ju Lee
    In The 25th Annual International Conference on Mobile Computing and Networking, pp. 1-16, Los Cabos, Mexico, 21-25 Oct. 2019, NRF BK21+ IF: 4, Acceptance Rate 19% (55 papers accepted out of 290 submitted)., Oct 2019