Publications
Publications and patents
International Publications
2026
- ACCESS
QubitCache: Quantum-Inspired Probabilistic Attention Preservation for KV-Cache Compression
Jieui Kang, Jaeyoung Choi, Wonhui Roh, Jaehyeong Sim
IEEE Access.
AcceptedQ2 - ACCESS
SHARP: Structured Hierarchical Attention Rank Projection for Efficient Language Model Distillation
Jieui Kang, Eunjoung Yoo, Soeun Choi, Yeonhui Kim, Jaehyeong Sim
IEEE Access, 2026.
Q2DOI
2025
- CCCI
DS-CAE: a Dual-Stream Cross-Attentive Autoencoder for Robust and Cluster-Aware Retrieval-Augmented Generation
Soeun Choi, Yejin Lee, Juhee Kim, Minji Kim, Jaehyeong Sim
International Conference on Communications, Computing, Cybersecurity, and Informatics, 2025.
- ISOCC
GATHER: A Gated-Attention Accelerator for Efficient LLM Inference
Eunjin Lee, Eunseo Kim, Eunjoung Yoo, Jaehyeong Sim
International SoC Design Conference, 2025.
- ISOCC
LoRA-PIM: In-Memory Delta-Weight Injection for Multi-Adapter LLM Serving
Soeun Choi, Jaehyeong Sim
International SoC Design Conference, 2025.
- CCCI
MAGNETO: A Genetic Algorithm-Based Power-Aware Mapping Optimization Framework for Mobile NPUs
Eunjin Lee, Jiho Lee, Hayoung Lim, Jaehyeong Sim
International Conference on Communications, Computing, Cybersecurity, and Informatics, 2025.
- CAI
ViT-Slim: A Genetic Algorithm-based NAS Framework for Efficient Vision Transformer Design
Eunjoung Yoo, Jaehyeong Sim
IEEE Conference on Artificial Intelligence, 2025.
- BigComp
Enhancing Gender Prediction Model Performance through Automatic Individual Entity Extraction and Class Balance
Chaeyun Kim, Eunseo Kim, Yeonhee Kim, Jaehyeong Sim, Jonkil Kim
IEEE International Conference on Big Data and Smart Computing, 2025.
- ACCESS
PRISM-Med: Parameter-efficient Robust Interdomain Specialty Model for Medical Language Tasks
Jieui Kang, Hyungon Ryu, Jaehyeong Sim
IEEE Access, vol. 13, no. 0, pp. 4957-4965, 2025.
Q2DOI
2024
- ACCESS
SpDRAM: Efficient In-DRAM Acceleration of Sparse Matrix-Vector Multiplication
Jieui Kang, Soeun Choi, Eunjin Lee, Jaehyeong Sim
IEEE Access, vol. 12, no. 0, pp. 176009-176021, 2024.
Q2DOI - CCCI
AutoCaps-Zero: Searching for Hardware-Efficient Squash Function in Capsule Networks
Jieui Kang, Sooyoung Kwon, Hyojin Kim, Jaehyeong Sim
International Conference on Communications, Computing, Cybersecurity, and Informatics, 2024.
- CCCI
OCW: Enhancing Few-Shot Learning with Optimized Class-Weighting Methods
Jieui Kang, Subean Lee, Eunseo Kim, Soeun Choi, Jaehyeong Sim
International Conference on Communications, Computing, Cybersecurity, and Informatics, 2024.
- ISOCC
An Energy-Efficient Hardware Accelerator for On-Device Inference of YOLOX
Kyungmi Kim, Soeun Choi, Eunkyeol Hong, Yoonseo Jang, Jaehyeong Sim
International SoC Design Conference, 2024.
- ISOCC
BS2: Bit-Serial Architecture Exploiting Weight Bit Sparsity for Efficient Deep Learning Acceleration
Eunseo Kim, Subean Lee, Chaeyun Kim, Hayoung Lim, Jimin Nam, Jaehyeong Sim
International SoC Design Conference, 2024.
- ISOCC
AlphaAccelerator: An Automatic Neural FPGA Accelerator Design Framework Based on GNNs
Jiho Lee, Jieui Kang, Eunjin Lee, Yejin Lee, Jaehyeong Sim
International SoC Design Conference, 2024.
- ACCESS
Q-LAtte: An Efficient and Versatile LSTM Model for Quantized Attention-Based Time Series Forecasting in Building Energy Applications
Jieui Kang, Jihye Park, Soeun Choi, Jaehyeong Sim
IEEE Access, vol. 12, no. 0, pp. 69325-69341, 2024.
Q2DOI
2023
- ISOCC
TD-NAAS: Template-Based Differentiable Neural Architecture Accelerator Search
Hayoung Lim, Yeseo Jang, Juyeon Kim, Jaehyeong Sim
International SoC Design Conference, 2023.
- CCCI
Optimization of the Modified Gaussian Filter for Mobile GPU Usage in Game Workloads
Jieui Kang, Jaehyeong Sim, Hyokyung Bahn
International Conference on Communications, Computing, Cybersecurity, and Informatics, 2023.
2022
- TC
S-FLASH: A NAND Flash-based Deep Neural Network Accelerator Exploiting Bit-Level Sparsity
Myeonggu Kang, Hyeonuk Kim, Hyein Shin, Jaehyeong Sim, Kyeonghan Kim, Lee-Sup Kim
IEEE Transactions on Computers, vol. 71, no. 6, pp. 1291-1304, 2022.
Q2DOI
2020
- TCAS-II
CREMON: Cryptography Embedded on the Convolutional Neural Network Accelerator
Yeongjae Choi, Jaehyeong Sim, Lee-Sup Kim
IEEE Transactions on Circuits and Systems II - Express Briefs, vol. 67, no. 12, pp. 3337-3341, 2020.
Q1DOI - JSSC
An Energy-Efficient Deep Convolutional Neural Network Training Accelerator for In Situ Personalization on Smart Devices
Seungkyu Choi, Jaehyeong Sim, Myeonggu Kang, Yeongjae Choi, Hyeonuk Kim, Lee-Sup Kim
IEEE Journal of Solid-State Circuits, vol. 55, no. 10, pp. 2691-2702, 2020.
Q1DOI
2019
- ICCAD
A PVT-Robust Customized 4T Embedded DRAM Cell Array for Accelerating Binary Neural Networks
Hyein Shin, Jaehyeong Sim, Daewoong Lee, Lee-Sup Kim
IEEE/ACM International Conference on Computer-Aided Design, 2019.
우수DOI - ICCAD
eSRCNN: A Framework for Optimizing Super-Resolution Tasks on Diverse Embedded CNN Accelerators
Youngbeom Jung, Yeongjae Choi, Jaehyeong Sim, Lee-Sup Kim
IEEE/ACM International Conference on Computer-Aided Design, 2019.
우수DOI - ICCAD
An Energy-Efficient Processing-in-Memory Architecture for Long Short Term Memory in Spin Orbit Torque MRAM
Kyeonghan Kim, Hyein Shin, Jaehyeong Sim, Myeonggu Kang, Lee-Sup Kim
IEEE/ACM International Conference on Computer-Aided Design, 2019.
우수DOI - A-SSCC
A 47.4 uJ/epoch Trainable Deep Convolutional Neural Network Accelerator for In-Situ Personalization on Smart Devices
Seungkyu Choi, Jaehyeong Sim, Myeonggu Kang, Yeongjae Choi, Hyeonuk Kim, Lee-Sup Kim
IEEE Asian Solid-State Circuits Conference, 2019.
- HPCA
NAND-Net: Minimizing Computational Complexity of In-Memory Processing for Binary Neural Networks
Hyeonuk Kim, Jaehyeong Sim, Yeongjae Choi, Lee-Sup Kim
IEEE International Symposium on High Performance Computer Architecture, 2019.
- TVLSI
An Energy-Efficient Deep Convolutional Neural Network Inference Processor with Enhanced Output Stationary Dataflow in 65-nm CMOS
Jaehyeong Sim, Somin Lee, Lee-Sup Kim
IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 28, no. 1, pp. 87-100, 2019.
2018
- ICCAD
NID: Processing Binary Convolutional Neural Network in Commodity DRAM
Jaehyeong Sim, Hoseok Seol, Lee-Sup Kim
IEEE/ACM International Conference on Computer-Aided Design, 2018.
우수DOI - ISLPED
TrainWare: A Memory Optimized Weight Update Architecture for On-Device Convolutional Neural Network Training
Seungkyu Choi, Jaehyeong Sim, Myeonggu Kang, Lee-Sup Kim
IEEE International Symposium on Low-Power Electronics and Design, 2018.
우수DOI
2017
- TCAS-II
Energy-Efficient Design of Processing Element for Convolutional Neural Network
Yeongjae Choi, Dongmyung Bae, Jaehyeong Sim, Seungkyu Choi, Minhye Kim, Lee-Sup Kim
IEEE Transactions on Circuits and Systems II - Express Briefs, vol. 64, no. 11, pp. 1332-1336, 2017.
Q1DOI - ISLPED
SENIN: An Energy-Efficient Sparse Neuromorphic System with On-Chip Learning
Myung-Hoon Choi, Seungkyu Choi, Jaehyeong Sim, Lee-Sup Kim
IEEE International Symposium on Low-Power Electronics and Design, 2017.
우수DOI - DAC
A Kernel Decomposition Architecture for Binary-Weight Convolutional Neural Networks
Hyeonuk Kim, Jaehyeong Sim, Yeongjae Choi, Lee-Sup Kim
IEEE/ACM Design Automation Conference, 2017.
최우수DOI
2016
- ISSCC
A 1.42 TOPS/W Deep Convolutional Neural Network Recognition Processor for Intelligent IoE Systems
Jaehyeong Sim, Jun-Seok Park, Minhye Kim, Dongmyung Bae, Yeongjae Choi, Lee-Sup Kim
IEEE International Solid-State Circuits Conference, 2016.
2015
- TVLSI
A 5-Gb/s 2.67-mW/Gb/s Digital Clock and Data Recovery with Hybrid Dithering Using a Time-Dithered Delta-Sigma Modulator
Taeho Lee, Yong-Hun Kim, Jaehyeong Sim, Jun-Seok Park, Lee-Sup Kim
IEEE Transactions on Very Large Scale Integration (VLSI) Systems, vol. 24, no. 4, pp. 1450-1459, 2015.
Q2DOI
2014
- ICCD
Timing Error Masking by Exploiting Operand Value Locality in SIMD Architecture
Jaehyeong Sim, Jun-Seok Park, Seungwook Paek, Lee-Sup Kim
IEEE International Conference on Computer Design, 2014.
우수DOI
2013
- TCAD
PowerField: A Probabilistic Approach for Temperature-to-Power Conversion Based on Markov Random Field Theory
Seungwook Paek, Wongyu Shin, Jaehyeong Sim, Lee-Sup Kim
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, vol. 32, no. 10, pp. 1509-1519, 2013.
Q2DOI
2012
- DAC
PowerField: A Transient Temperature-to-Power Technique Based on Markov Random Field Theory
Seungwook Paek, Seok-Hwan Moon, Wongyu Shin, Jaehyeong Sim, Lee-Sup Kim
IEEE/ACM Design Automation Conference, 2012.
최우수DOI
Domestic Publications
2025
- KSC
- IEIE-Summer
2024
- IEIE-Autumn
T-FLIP: 어텐션 가중치 기반 지식 증류를 통한 안면 위조 방지 모델 경량화
류이정, 박지원, 소예림, 최종원, 심재형
대한전자공학회 추계학술대회, 2024.
2023
- IEIE-Autumn
QTNAAS: 템플릿 기반 양자화된 신경망 구조 및 가속기 탐색 프레임워크
임하영, 김경미, 장예서, 김주연, 심재형
대한전자공학회 추계학술대회, 2023.
- IEIE-Autumn
2022
- KCC
게임 워크로드에 최적화된 모바일 GPU 설계방안 연구
강지의, 심재형, 반효경
한국소프트웨어종합학술대회, 2022.
- KICS
딥러닝 기반의 MBTI 성격유형 분류 연구
김정민, 박지민, 이로운, 조서원, 심재형
한국통신학회 하계종합학술발표회, 2022.
Patents (29)
- KR
서버리스 기반의 대규모 언어 모델 서빙 시스템 및 방법
심재형, 이주원, 박나담, 이나경
No. 10-2025-0194750 (2025)
Filed - KR
대규모 언어모델의 키-값 캐시를 압축하기 위한 확률적 어텐션 보존 기반의 캐시 압축 시스템 및 방법
심재형, 강지의, 노원희, 최재영
No. 10-2025-0179129 (2025)
Filed - KR
사용자 맞춤형 공간 제어가 가능한 인공지능 기반 실내 인테리어 변환 시스템 및 방법
심재형, 최장환, 홍은결, 이서정, 조현지
No. 10-2025-0168914 (2025)
Filed - KR
검색 증강 지식 응답 생성 장치 및 방법
심재형, 김주희, 이민지, 이예진, 최소은
No. 10-2025-0159362 (2025)
Filed - Intl
계층적 주의 랭크 투영에 기반한 언어모델 지식 증류 장치 및 방법
심재형, 강지의, 최소은, 유은정, 김연희
No. PCT/KR2025/017383 (2025)
Filed - KR
딥러닝 기반 이미지 처리 장치 및 방법
심재형, 유은정
No. 10-2025-0105299 (2025)
Filed - KR
클러스터링 기반 문장 가지치기를 활용한 문장 기반 지식 증류 장치 및 동작 방법
심재형, 강지의, 김연희, 유은정, 최소은
No. 10-2025-0099179 (2025)
Filed - KR
동적 토큰 선택 및 동적 토큰 통합에 기반하여 태스크 인지 기반 지식 증류를 수행하는 태스크 인지 기반 지식 증류 장치 및 방법
심재형, 김종길, 강지의, 최소은, 김연희, 유은정
No. 10-2025-0069129 (2025)
Filed - KR
계층적 주의 랭크 투영에 기반한 언어모델 지식 증류 장치 및 방법
심재형, 강지의, 최소은, 유은정, 김연희
No. 10-2025-0052980 (2025)
Filed - Intl
토큰 병합을 이용한 비전 트랜스포머 장치 및 방법
심재형, 권민서, 권수영, 김효진
No. PCT/KR2024/018690 (2024)
Filed - KR
가중치 매트릭스를 이용한 메모리 연산 처리 장치 및 방법
심재형, 강지의, 김경미, 이수빈, 이은진, 이지호, 최소은
No. 10-2024-0114013 (2024)
Filed - KR
그래프 신경망을 이용하여 하드웨어 구조의 설계를 가속하는 하드웨어 구조 설계 장치 및 하드웨어 구조 설계 방법
심재형, 강지의, 이예진, 이은진, 이지호
No. 10-2024-0108145 (2024)
GrantedReg. 10-2897328 - KR
비트 직렬 연산 처리 장치 및 방법
심재형, 김은서, 김채윤, 남지민, 이수빈, 임하영
No. 10-2024-0108146 (2024)
GrantedReg. 10-2940812 - KR
도메인 적응형 언어모델 처리 장치 및 방법
심재형, 강지의
No. 10-2024-0094108 (2024)
Filed - KR
토큰 병합을 이용한 비전 트랜스포머 장치 및 방법
심재형, 권민서, 권수영, 김효진
No. 10-2024-0065166 (2024)
Filed - Intl
정확도 정보 및 유사도 정보를 이용한 양자화 인공지능 학습 처리 장치 및 방법
심재형, 강지의, 박지혜, 최소은
No. PCT/KR2024/006433 (2024)
Filed - KR
인공지능 기반의 스마트 윈도우 제어 시스템 및 제어 방법
송승영, 박지혜, 심재형, 이수진, 강지의, 최소은
No. 10-2024-0057005 (2024)
GrantedReg. 10-2853870 - Intl
템플릿에 기반하는 신경 구조 탐색장치 및 그 방법
심재형, 임하영, 김주연, 장예서
No. PCT/KR2024/005651 (2024)
Filed - Intl
캡슐 네트워크의 스쿼시 함수 탐색장치 및 그 방법
심재형, 강지의, 권수영, 김효진
No. PCT/KR2024/003896 (2024)
Filed - KR
최적화된 클래스 가중치를 이용한 인공지능 학습 처리 장치 및 방법
심재형, 강지의, 김은서, 이수빈, 최소은
No. 10-2024-0031351 (2024)
Filed - KR
정확도 정보 및 유사도 정보를 이용한 양자화 인공지능 학습 처리 장치 및 방법
심재형, 강지의, 박지혜, 최소은
No. 10-2023-0194206 (2023)
Filed - KR
템플릿에 기반하는 신경 구조 탐색장치 및 그 방법
심재형, 임하영, 김주연, 장예서
No. 10-2023-0178909 (2023)
Filed - KR
가우시안 플러스 필터에 기반하는 이미지 처리장치 및 그 방법
심재형, 강지의, 김경미, 반효경
No. 10-2023-0157656 (2023)
GrantedReg. 10-2820700 - KR
캡슐 네트워크의 스쿼시 함수 탐색장치 및 그 방법
심재형, 강지의
No. 10-2023-0121855 (2023)
Filed - Intl
Method and apparatus with deep learning operations with adder tree structure
Jaehyeong Sim
No. US20220164164 (2021)
GrantedReg. US12423057 - Intl
Computing device and method for allocating resources using cost matrix
Jaehyeong Sim
No. US20220083390 (2021)
GrantedReg. US12175299 - Intl
Accelerator, method of operating an accelerator, and electronic device including an accelerator
Jaehyeong Sim
(2021)
GrantedReg. US12130756 - KR
Method and apparatus for performing convolution operation in neural network
Jaehyeong Sim
(2020)
GrantedReg. KR10-2452951 - Intl
Neural network method and apparatus
Jaehyeong Sim, Lee-Sup Kim
(2018)
GrantedReg. US10699160