Publications

Conference

OWQ: Lessons learned from activation outliers for weight quantization in large language models

Association for the Advancement of Artificial Intelligence (AAAI 2024, Oral), Changhun Lee*, Jungyu Jin*, Taesu Kim, Hyungjun Kim, and Eunhyeok Park

Conference

Temporal Dynamic Quantizatin for Diffusion Models

Neural Information Processing Systems (NeurIPS 2023), Junhyuk So*, Jungwon Lee*, Daehyun Ahn, Hyungjun Kim, and Eunhyeok Park

NIPQ: Noise proxy-based Integrated Pseudo-Quantization

Computer Vision and Pattern Recognition (CVPR 2023), Juncheol Shin*, Junhyuk So*, Sein Park, Seungyeop Kang, Sungjoo Yoo and Eunhyeok Park

Multi-Scale Local Implicit Keypoint Descriptor for Keypoint Matching

Computer Vision and Pattern Recognition (CVPR 2023), Jongmin Lee, Eunhyeok Park and Sungjoo Yoo

Searching for Robust Binary Neural Networks via Bimodal Parameter Perturbation

Winter Conference on Applications of Computer Vision (WACV 2023), Daehyun Ahn, Hyungjun Kim, Taesu Kim, Eunhyeok Park, and Jae-Joon Kim

Journal

Fast Performance Prediction for Efficient Distributed DNN Training

IEEE Computer Architecture Letters, Yugyeong Yun and Eunhyeok Park

Conference

Symmetry Regularization and Saturating Nonlinearity for Robust Quantization

European Conference on Computer Vision (ECCV 2022), Sein Park*, Yeongsang Jang*, and Eunhyeok Park 

BASQ: Branch-wise Activation-clipping Search Quantization for Sub-4-bit Neural Networks

European Conference on Computer Vision (ECCV 2022), Han-Byul Kim, Eunhyeok Park, and Sungjoo Yoo

Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking

International Joint Conference on Artificial Intelligence Organization (IJCAI 2022), Ilchae Jung, Minji Kim, Eunhyeok Park, and Bohyung Han

One-Shot Tuner for Deep Learning Compilers

Compiler Construction (CC 2022), Jaehun Ryu, Eunhyeok Park, and Hyojin Sung

Conference

Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimaion

International Conference on Computer Vision (ICCV 2021, Oral), Hyunyoung Jung, Eunhyeok Park, Sungjoo Yoo

FPGA Prototyping of Systolic Array-based Accelerator for Low-Precision Inference of Deep Neural Networks

IEEE International Workshop on Rapid System Prototyping (RSP), Soobeom Kim, Seunghwan Cho, Eunhyeok Park, Sungjoo Yoo

On the Overlooked Significance of Underutilized Contextual Features in Recent News Recommendation Models

arXiv preprint, Sungmin Cho, Hongjun Lim, Keunchan Park, Sungjoo Yoo, and Eunhyeok Park

Journal

Near-Data Processing in Memory Expander for DNN Acceleration on GPUs

IEEE Computer Architecture Letters (CAL), Hyungkyu Ham, Hyunuk Cho, Minjae Kim, Jueon Park, Jeongmin Hong, Hyojin Sung, Eunhyeok Park, Euicheol Lim, and Gwangsun Kim

Conference

MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation

Recommender Systems (ReSys 2020), Sung Min Cho, Eunhyeok Park, and Sungjoo Yoo

Profit, A Novel Training Method for Sub-4bit Mobilenet Models

European Conference on Computer Vision (ECCV 2020), Eunhyeok Park, and Sungjoo Yoo

Journal

McDRAM v2: In-Dynamic Random Access Memory Systolic Array Accelerator to Address the Large Model Problem in Deep Neural Networks on the Edge

IEEE Access, Seunghwan Cho, Haerang Choi, Eunhyeok Park, Hyunsung Shin, and Sungjoo Yoo

Conference

Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss

International Conference on Computer Vision (ICCV 2019), Hyunsu Kim, Ho Young Jhoo, Eunhyeok Park, and Sungjoo Yoo

Journal

Low-Overhead, One-Cycle Timing-Error Detection and Correction Technique for Flip-Flop Based Pipelines

IEICE Electronics Express, Jongeun Koo, Eunhyeok Park, Dongyoung Kim, Junki Park, Sungju Ryu, Sungjoo Yoo, and Jae-Joon Kim 

Conference

Energy-efficient Neural Network Acceleator based on Outlier-aware Low-precision Computation

International Symposium on Computer Architecture (ISCA), Eunhyeok Park, Dongyoung Kim, and Sungjoo Yoo

Value-aware Quantization for Training and Inference of Neural Networks

European Conference on Computer Vision (ECCV), Eunhyeok Park, Sungjoo Yoo, and Peter Vajda

Precision Highway for Ultra Low-precision Quantiziaton

arXiv preprint, Eunhyeok Park, Dongyoung Kim, Sungjoo Yoo, and Peter Vajda

Journal

McDRAM: Low Latency and Energy-efficient Matrix Computation in DRAM

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Hyunsung Shin, Dongyoung Kim, Eunhyeok Park, Sungho Park, Yongsik Park, and Sungjoo Yoo

Conference

Weighted-Entropy-based Quantization for Deep Neural Networks

Computer Vision and Pattern Recognition (CVPR),  Eunhyeok Park, Junwhan Ahn, and Sungjoo Yoo

Conference

Area-Efficient One-Cycle Correction Scheme for Timing Errors in Flip-Flop based Pipelines

IEEE Asian Solid-State Circuits Conference (A-SSCC), Jongeun Koo, Eunwoo Song, Eunhyeok Park, Dongyoung Kim, Junki Park, Sungju Ryu, Sungjoo Yoo, and Jae-Joon Kim

Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications

International Conference on Machine Learning (ICLR 2015), Yong-Deok Kim, Eunhyeok Park, Sungjoo Yoo, Taelim Choi, Lu Yang, and Dongjun Shin

Conference

Locality-aware Vertex Scheduling for GPU-based Graph Computation

IEEE International Conference on Very Large Scale Integration (VLSI-SoC), Hyunsun Park, Junwhan Ahn, Eunhyeok Park, and Sungjoo Yoo 

Big/Litte Deep Neural Network for Ultra Low Power Inference

ESWEEK (CODES+ISSS) 2015, Eunhyeok Park, Dongyoung Kim, Soobeom Kim, Yong-Deok Kim, Gunhee Kim, Sungroh Yoon, and Sungjoo Yoo

Memory Fast-forward: A Low Cost Special Function Unit to Enhance Energy Efficiency in GPU for Big Data Processing

Design, Automation & Test in Europe (DATE 2015), Eunhyeok Park, Junwhan Ahn, Sungpack Hong, Sungjoo Yoo, and Sunggu Lee

Conference

Accelerating graph computation with racetrack memory and pointer-assisted graph representation

Design, Automation & Test in Europe Conference & Exhibition (DATE 2014), Eunhyeok Park, Sungjoo Yoo, Sunggu Lee, and Helen Li