Eunhyeok Park

77 papers A* 16A 5B 1C 2Misc 1Journal 41Unranked 11
YearRankTypeTitle / Venue / Authors
2025 A* conf
AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models.
EMNLP
Sangjun Lee, Seung-taek Woo, Jungyu Jin, Changhun Lee, Eunhyeok Park
2025 J jnl
AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models.
CoRR
Sangjun Lee, Seung-taek Woo, Jungyu Jin, Changhun Lee, Eunhyeok Park
2025 J jnl
Cost-Effective Extension of DRAM-PIM for Group-Wise LLM Quantization.
IEEE Comput. Archit. Lett.
Byeori Kim, Changhun Lee, Gwangsun Kim, Eunhyeok Park
2025 J jnl
Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse.
CoRR
Jinwoo Hwang, Daeun Kim, Sangyeop Lee, Yoonsung Kim, Guseul Heo, Hojoon Kim, Yunseok Jeong, Tadiwos Meaza, Eunhyeok Park, Jeongseob Ahn, Jongse Park
2025 J jnl
Déjà Vu: Efficient Video-Language Query Engine with Learning-based Inter-Frame Computation Reuse.
Proc. VLDB Endow.
Jinwoo Hwang, Daeun Kim, Sangyeop Lee, Yoonsung Kim, Guseul Heo, Hojoon Kim, Yunseok Jeong, Tadiwos Meaza, Eunhyeok Park, Jeongseob Ahn, Jongse Park
2025 — conf
Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs.
EMNLP (Findings)
Sungjae Lee, Hoyoung Kim, Jeongyeon Hwang, Eunhyeok Park, Jungseul Ok
2025 J jnl
Efficient Latent Semantic Clustering for Scaling Test-Time Computation of LLMs.
CoRR
Sungjae Lee, Hoyoung Kim, Jeongyeon Hwang, Eunhyeok Park, Jungseul Ok
2025 J jnl
GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning.
CoRR
Yeonjoon Jung, Daehyun Ahn, Hyungjun Kim, Taesu Kim, Eunhyeok Park
2025 J jnl
Grouped Speculative Decoding for Autoregressive Image Generation.
CoRR
Junhyuk So, Juncheol Shin, Hyunho Kook, Eunhyeok Park
2025 A* conf
HOT: Hadamard-based Optimized Training.
CVPR
Seonggon Kim, Juncheol Shin, Seung-taek Woo, Eunhyeok Park
2025 J jnl
HOT: Hadamard-based Optimized Training.
CoRR
Seonggon Kim, Juncheol Shin, Seung-taek Woo, Eunhyeok Park
2025 J jnl
Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking.
CoRR
Junhyuk So, Chiwoong Lee, Shinyoung Lee, Jungseul Ok, Eunhyeok Park
2025 J jnl
MC-SJD : Maximal Coupling Speculative Jacobi Decoding for Autoregressive Visual Generation Acceleration.
CoRR
Junhyuk So, Hyunho Kook, Chaeyeon Jang, Eunhyeok Park
2025 A* conf
Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation.
ICML
Juncheol Shin, Minsang Seok, Seonggon Kim, Eunhyeok Park
2025 J jnl
Merge-Friendly Post-Training Quantization for Multi-Target Domain Adaptation.
CoRR
Juncheol Shin, Minsang Seok, Seonggon Kim, Eunhyeok Park
2025 A* conf
PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models.
CVPR
Junhyuk So, Jiwoong Shin, Chaeyeon Jang, Eunhyeok Park
2025 J jnl
PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models.
CoRR
Junhyuk So, Jiwoong Shin, Chaeyeon Jang, Eunhyeok Park
2025 A conf
PTQ4VM: Post-Training Quantization for Visual Mamba.
WACV
Younghyun Cho, Changhun Lee, Seonggon Kim, Eunhyeok Park
2025 A conf
Partial-Sum Quantization Based on Pseudo-Quantization Noise for Variation-Tolerant Analog In-Memory Computing.
ISLPED
Nameun Kang, Eunhyeok Park, Sangsu Park, Jongil Kim, Jaeyun Yi, Jae-Joon Kim
2025 A* conf
PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality.
EMNLP
Byeongho Yu, Changhun Lee, Jungyu Jin, Eunhyeok Park
2025 J jnl
PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality.
CoRR
Byeongho Yu, Changhun Lee, Jungyu Jin, Eunhyeok Park
2025 — conf
SEAL: Scaling to Emphasize Attention for Long-Context Retrieval.
ACL (1)
Changhun Lee, Minsang Seok, Jungyu Jin, Younghyun Cho, Eunhyeok Park
2025 J jnl
SEAL: Scaling to Emphasize Attention for Long-Context Retrieval.
CoRR
Changhun Lee, Jungyu Jin, Younghyun Cho, Eunhyeok Park
2025 J jnl
Stabilizing Direct Training of Spiking Neural Networks: Membrane Potential Initialization and Threshold-robust Surrogate Gradient.
CoRR
Hyunho Kook, Byeongho Yu, Jeong Min Oh, Eunhyeok Park
2025 J jnl
The Oversmoothing Fallacy: A Misguided Narrative in GNN Research.
CoRR
MoonJeong Park, Sunghyun Choi, Jaeseung Heo, Eunhyeok Park, Dongwoo Kim
2024 — conf
Diffusion Model Compression for Image-to-Image Translation.
ACCV (5)
Geonung Kim, Beomsu Kim, Eunhyeok Park, Sunghyun Cho
2024 — conf
FRDiff : Feature Reuse for Universal Training-Free Acceleration of Diffusion Models.
ECCV (73)
Junhyuk So, Jungwon Lee, Eunhyeok Park
2024 J jnl
HLQ: Fast and Efficient Backpropagation via Hadamard Low-rank Quantization.
CoRR
Seonggon Kim, Eunhyeok Park
2024 A* conf
Low-Overhead General-Purpose Near-Data Processing in CXL Memory Expanders.
MICRO
Hyungkyu Ham, Jeongmin Hong, Geonwoo Park, Yunseon Shin, Okkyun Woo, Wonhyuk Yang, Jinhoon Bae, Eunhyeok Park, Hyojin Sung, Euicheol Lim, Gwangsun Kim
2024 J jnl
Low-overhead General-purpose Near-Data Processing in CXL Memory Expanders.
CoRR
Hyungkyu Ham, Jeongmin Hong, Geonwoo Park, Yunseon Shin, Okkyun Woo, Wonhyuk Yang, Jinhoon Bae, Eunhyeok Park, Hyojin Sung, Euicheol Lim, Gwangsun Kim
2024 J jnl
Non-Invasive, Memory Access-Triggered Near-Data Processing for DNN Training Acceleration on GPUs.
IEEE Access
Hyungkyu Ham, Hyunuk Cho, Minjae Kim, Jueon Park, Jeongmin Hong, Hyojin Sung, Eunhyeok Park, Euicheol Lim, Gwangsun Kim
2024 A* conf
OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models.
AAAI
Changhun Lee, Jungyu Jin, Taesu Kim, Hyungjun Kim, Eunhyeok Park
2024 J jnl
PTQ4VM: Post-Training Quantization for Visual Mamba.
CoRR
Younghyun Cho, Changhun Lee, Seonggon Kim, Eunhyeok Park
2024 — conf
QEFT: Quantization for Efficient Fine-Tuning of LLMs.
EMNLP (Findings)
Changhun Lee, Jungyu Jin, Younghyun Cho, Eunhyeok Park
2024 J jnl
QEFT: Quantization for Efficient Fine-Tuning of LLMs.
CoRR
Changhun Lee, Jungyu Jin, Younghyun Cho, Eunhyeok Park
2024 J jnl
Task-Oriented Diffusion Model Compression.
CoRR
Geonung Kim, Beomsu Kim, Eunhyeok Park, Sunghyun Cho
2023 J jnl
FRDiff: Feature Reuse for Exquisite Zero-shot Acceleration of Diffusion Models.
CoRR
Junhyuk So, Jungwon Lee, Eunhyeok Park
2023 J jnl
Fast Performance Prediction for Efficient Distributed DNN Training.
IEEE Comput. Archit. Lett.
Yugyoung Yun, Eunhyeok Park
2023 A* conf
INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold.
ICCV
Changhun Lee, Hyungjun Kim, Eunhyeok Park, Jae-Joon Kim
2023 — conf
Multi-scale Local Implicit Keypoint Descriptor for Keypoint Matching.
CVPR Workshops
Jongmin Lee, Eunhyeok Park, Sungjoo Yoo
2023 A* conf
NIPQ: Noise proxy-based Integrated Pseudo-Quantization.
CVPR
Juncheol Shin, Junhyuk So, Sein Park, Seungyeop Kang, Sungjoo Yoo, Eunhyeok Park
2023 J jnl
OWQ: Lessons learned from activation outliers for weight quantization in large language models.
CoRR
Changhun Lee, Jungyu Jin, Taesu Kim, Hyungjun Kim, Eunhyeok Park
2023 A conf
Searching for Robust Binary Neural Networks via Bimodal Parameter Perturbation.
WACV
Daehyun Ahn, Hyungjun Kim, Taesu Kim, Eunhyeok Park, Jae-Joon Kim
2023 A* conf
Temporal Dynamic Quantization for Diffusion Models.
NeurIPS
Junhyuk So, Jungwon Lee, Daehyun Ahn, Hyungjun Kim, Eunhyeok Park
2023 J jnl
Temporal Dynamic Quantization for Diffusion Models.
CoRR
Junhyuk So, Jungwon Lee, Daehyun Ahn, Hyungjun Kim, Eunhyeok Park
2022 — conf
BASQ: Branch-wise Activation-clipping Search Quantization for Sub-4-bit Neural Networks.
ECCV (12)
Han-Byul Kim, Eunhyeok Park, Sungjoo Yoo
2022 J jnl
INSTA-BNN: Binary Neural Network with INSTAnce-aware Threshold.
CoRR
Changhun Lee, Hyungjun Kim, Eunhyeok Park, Jae-Joon Kim
2022 J jnl
NIPQ: Noise Injection Pseudo Quantization for Automated DNN Optimization.
CoRR
Sein Park, Junhyuk So, Juncheol Shin, Eunhyeok Park
2022 B conf
One-shot tuner for deep learning compilers.
CC
Jaehun Ryu, Eunhyeok Park, Hyojin Sung
2022 A* conf
Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking.
IJCAI
Ilchae Jung, Minji Kim, Eunhyeok Park, Bohyung Han
2022 J jnl
Online Hybrid Lightweight Representations Learning: Its Application to Visual Tracking.
CoRR
Ilchae Jung, Minji Kim, Eunhyeok Park, Bohyung Han
2022 — conf
Symmetry Regularization and Saturating Nonlinearity for Robust Quantization.
ECCV (11)
Sein Park, Yeongsang Jang, Eunhyeok Park
2022 J jnl
Symmetry Regularization and Saturating Nonlinearity for Robust Quantization.
CoRR
Sein Park, Yeongsang Jang, Eunhyeok Park
2021 C conf
FPGA Prototyping of Systolic Array-based Accelerator for Low-Precision Inference of Deep Neural Networks.
RSP
Soobeom Kim, Seunghwan Cho, Eunhyeok Park, Sungjoo Yoo
2021 A* conf
Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation.
ICCV
Hyunyoung Jung, Eunhyeok Park, Sungjoo Yoo
2021 J jnl
Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation.
CoRR
Hyunyoung Jung, Eunhyeok Park, Sungjoo Yoo
2021 J jnl
Near-Data Processing in Memory Expander for DNN Acceleration on GPUs.
IEEE Comput. Archit. Lett.
Hyungkyu Ham, Hyunuk Cho, Minjae Kim, Jueon Park, Jeongmin Hong, Hyojin Sung, Eunhyeok Park, Euicheol Lim, Gwangsun Kim
2021 J jnl
On the Overlooked Significance of Underutilized Contextual Features in Recent News Recommendation Models.
CoRR
Sung Min Cho, Hongjun Lim, Keunchan Park, Sungjoo Yoo, Eunhyeok Park
2020 A conf
MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation.
RecSys
Sung Min Cho, Eunhyeok Park, Sungjoo Yoo
2020 J jnl
MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation.
CoRR
Sung Min Cho, Eunhyeok Park, Sungjoo Yoo
2020 J jnl
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, Sungjoo Yoo
2020 — conf
PROFIT: A Novel Training Method for sub-4-bit MobileNet Models.
ECCV (6)
Eunhyeok Park, Sungjoo Yoo
2020 J jnl
PROFIT: A Novel Training Method for sub-4-bit MobileNet Models.
CoRR
Eunhyeok Park, Sungjoo Yoo
2019 J jnl
Low-overhead, one-cycle timing-error detection and correction technique for flip-flop based pipelines.
IEICE Electron. Express
Jongeun Koo, Eunhyeok Park, Dongyoung Kim, Junki Park, Sungju Ryu, Sungjoo Yoo, Jae-Joon Kim
2019 A* conf
Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss.
ICCV
Hyunsu Kim, Ho Young Jhoo, Eunhyeok Park, Sungjoo Yoo
2019 J jnl
Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss.
CoRR
Hyunsu Kim, Ho Young Jhoo, Eunhyeok Park, Sungjoo Yoo
2018 A* conf
Energy-Efficient Neural Network Accelerator Based on Outlier-Aware Low-Precision Computation.
ISCA
Eunhyeok Park, Dongyoung Kim, Sungjoo Yoo
2018 J jnl
McDRAM: Low Latency and Energy-Efficient Matrix Computations in DRAM.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.
Hyunsung Shin, Dongyoung Kim, Eunhyeok Park, Sungho Park, Yongsik Park, Sungjoo Yoo
2018 J jnl
Precision Highway for Ultra Low-Precision Quantization.
CoRR
Eunhyeok Park, Dongyoung Kim, Sungjoo Yoo, Peter Vajda
2018 — conf
Value-Aware Quantization for Training and Inference of Neural Networks.
ECCV (4)
Eunhyeok Park, Sungjoo Yoo, Peter Vajda
2018 J jnl
Value-aware Quantization for Training and Inference of Neural Networks.
CoRR
Eunhyeok Park, Sungjoo Yoo, Peter Vajda
2017 A* conf
Weighted-Entropy-Based Quantization for Deep Neural Networks.
CVPR
Eunhyeok Park, Junwhan Ahn, Sungjoo Yoo
2016 — conf
Area-efficient one-cycle correction scheme for timing errors in flip-flop based pipelines.
A-SSCC
Jongeun Koo, Eunwoo Song, Eunhyeok Park, Dongyoung Kim, Junki Park, Sungju Ryu, Sungjoo Yoo, Jae-Joon Kim
2016 A* conf
Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications.
ICLR (Poster)
Yong-Deok Kim, Eunhyeok Park, Sungjoo Yoo, Taelim Choi, Lu Yang, Dongjun Shin
2015 Misc conf
Big/little deep neural network for ultra low power inference.
CODES+ISSS
Eunhyeok Park, Dongyoung Kim, Soobeom Kim, Yong-Deok Kim, Gunhee Kim, Sungroh Yoon, Sungjoo Yoo
2015 C conf
Locality-aware vertex scheduling for GPU-based graph computation.
VLSI-SoC
Hyunsun Park, Junwhan Ahn, Eunhyeok Park, Sungjoo Yoo
2015 A conf
Memory fast-forward: a low cost special function unit to enhance energy efficiency in GPU for big data processing.
DATE
Eunhyeok Park, Junwhan Ahn, Sungpack Hong, Sungjoo Yoo, Sunggu Lee