Yongin Kwon

34 papers A* 3A 1B 2C 1Misc 1Journal 21Unranked 5
YearRankTypeTitle / Venue / Authors
2026 J jnl
Target-Aware Neural Network Execution via Compiler-Guided Pruning.
IEEE Trans. Mob. Comput.
JooHyoung Cha, Taeho Kim, Jemin Lee, Sangtae Ha, Yongin Kwon
2026 J jnl
Towards an efficient dataflow-flexible accelerator by finding optimal dataflows of DNNs.
Future Gener. Comput. Syst.
Hyunjun Kim, Whoi Ree Ha, Yongseok Lee, Dongju Lee, Jongwon Lee, Deumji Woo, Jonghee Yoon, Jemin Lee, Yongin Kwon, Yunheung Paek
2025 — conf
Design Practices and Lessons from Deploying On-device Vision-Language Interaction in Robotic Guide Dogs.
ICCVW
Jinse Kwon, Jemin Lee, Yongin Kwon
2025 A* conf
Exploring the Trade-Offs: Quantization Methods, Task Difficulty, and Model Size in Large Language Models From Edge to Giant.
IJCAI
Jemin Lee, Sihyeong Park, Jinse Kwon, Jihun Oh, Yongin Kwon
2025 C conf
Flexible Uber Fetch Shader Architecture for Fluid Gaming Experience.
ICCE
Junmo Park, Zhenhong Liu, Sangwon Park, Yongin Kwon, Wilson Fung, Donghee Han
2025 J jnl
Luthier: Bridging Auto-Tuning and Vendor Libraries for Efficient Deep Learning Inference.
ACM Trans. Embed. Comput. Syst.
Yongin Kwon, JooHyoung Cha, Sehyeon Oh, Misun Yu, Jeman Park, Jemin Lee
2025 B conf
Multi-level Machine Learning-Guided Autotuning for Efficient Code Generation on a Deep Learning Accelerator.
LCTES
JooHyoung Cha, Munyoung Lee, Jinse Kwon, Jemin Lee, Yongin Kwon
2025 J jnl
QuantuneV2: Compiler-Based Local Metric-Driven Mixed Precision Quantization for Practical Embedded AI Applications.
CoRR
Jeongseok Kim, Jemin Lee, Yongin Kwon, Daeyoung Kim
2025 J jnl
QuantuneV2: Compiler-based local metric-driven mixed precision quantization for practical embedded AI applications.
Future Gener. Comput. Syst.
Jeongseok Kim, Jemin Lee, Yongin Kwon, Daeyoung Kim
2025 — conf
TriPlanNet: Triangle Path Planning Network for A Variable Truss Robot with Deep Learning.
ICCVW
Choonghan Lee, Leah Harris, Sehyun Oh, JooHyoung Cha, Jemin Lee, Yongin Kwon, Andrew Jang-ho Bae
2025 Misc conf
Work-in-Progress: I-FlashAttention: Fully Integer Fused Attention for Efficient Vision Transformers.
CASES
Sehyeon Oh, Yongin Kwon, Jemin Lee
2024 J jnl
A Comprehensive Evaluation of Quantized Instruction-Tuned Large Language Models: An Experimental Analysis up to 405B.
CoRR
Jemin Lee, Sihyeong Park, Jinse Kwon, Jihun Oh, Yongin Kwon
2024 A* conf
LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMs.
IJCAI
Taeho Kim, Yanming Wang, Vatshank Chaturvedi, Lokesh Gupta, Seyeon Kim, Yongin Kwon, Sangtae Ha
2024 J jnl
LLMem: Estimating GPU Memory Usage for Fine-Tuning Pre-Trained LLMs.
CoRR
Taeho Kim, Yanming Wang, Vatshank Chaturvedi, Lokesh Gupta, Seyeon Kim, Yongin Kwon, Sangtae Ha
2024 J jnl
ML
CoRR
JooHyoung Cha, Munyoung Lee, Jinse Kwon, Jubin Lee, Jemin Lee, Yongin Kwon
2024 — conf
Mixed Non-linear Quantization for Vision Transformers.
ECCV Workshops (11)
Gihwan Kim, Jemin Lee, Sihyeong Park, Yongin Kwon, Hyungshin Kim
2024 J jnl
Mixed Non-linear Quantization for Vision Transformers.
CoRR
Gihwan Kim, Jemin Lee, Sihyeong Park, Yongin Kwon, Hyungshin Kim
2024 J jnl
Q-HyViT: Post-Training Quantization of Hybrid Vision Transformers With Bridge Block Reconstruction for IoT Systems.
IEEE Internet Things J.
Jemin Lee, Yongin Kwon, Sihyeong Park, Misun Yu, Jeman Park, Hwanjun Song
2024 A conf
Visual Preference Inference: An Image Sequence-Based Preference Reasoning in Tabletop Object Manipulation.
IROS
Joonhyung Lee, Sangbeom Park, Yongin Kwon, Jemin Lee, Minwook Ahn, Sungjoon Choi
2024 J jnl
Visual Preference Inference: An Image Sequence-Based Preference Reasoning in Tabletop Object Manipulation.
CoRR
Joonhyung Lee, Sangbeom Park, Yongin Kwon, Jemin Lee, Minwook Ahn, Sungjoon Choi
2023 J jnl
Q-HyViT: Post-Training Quantization for Hybrid Vision Transformer with Bridge Block Reconstruction.
CoRR
Jemin Lee, Yongin Kwon, Jeman Park, Misun Yu, Hwanjun Song
2023 J jnl
Tensor Slicing and Optimization for Multicore NPUs.
CoRR
Rafael C. F. Sousa, Márcio Machado Pereira, Yongin Kwon, Taeho Kim, Namsoon Jung, Chang Soo Kim, Michael Frank, Guido Araujo
2023 J jnl
Tensor slicing and optimization for multicore NPUs.
J. Parallel Distributed Comput.
Rafael C. F. Sousa, Márcio Machado Pereira, Yongin Kwon, Taeho Kim, Namsoon Jung, Chang Soo Kim, Michael Frank, Guido Araujo
2022 — conf
CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution.
ECCV (20)
Taeho Kim, Yongin Kwon, Jemin Lee, Taeho Kim, Sangtae Ha
2022 J jnl
CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN Execution.
CoRR
Taeho Kim, Yongin Kwon, Jemin Lee, Taeho Kim, Sangtae Ha
2022 J jnl
Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment.
CoRR
Jemin Lee, Misun Yu, Yongin Kwon, Taeho Kim
2022 J jnl
Quantune: Post-training quantization of convolutional neural networks using extreme gradient boosting for fast deployment.
Future Gener. Comput. Syst.
Jemin Lee, Misun Yu, Yongin Kwon, Taeho Kim
2019 J jnl
Microarchitecture-Aware Code Generation for Deep Learning on Single-ISA Heterogeneous Multi-Core Mobile Processors.
IEEE Access
Junmo Park, Yongin Kwon, Yongjun Park, Dongsuk Jeon
2016 J jnl
Precise execution offloading for applications with dynamic behavior in mobile cloud computing.
Pervasive Mob. Comput.
Yongin Kwon, Hayoon Yi, Donghyun Kwon, Seungjun Yang, Yeongpil Cho, Yunheung Paek
2015 J jnl
Mantis: Efficient Predictions of Execution Time, Energy Usage, Memory Usage and Network Usage on Smart Mobile Devices.
IEEE Trans. Mob. Comput.
Yongin Kwon, Sangmin Lee, Hayoon Yi, Donghyun Kwon, Seungjun Yang, Byung-Gon Chun, Ling Huang, Petros Maniatis, Mayur Naik, Yunheung Paek
2014 B conf
CMcloud: Cloud Platform for Cost-Effective Offloading of Mobile Applications.
CCGRID
Dongju Chae, Jihun Kim, Jangwoo Kim, Jong Kim, Seungjun Yang, Yeongpil Cho, Yongin Kwon, Yunheung Paek
2014 J jnl
Techniques to Minimize State Transfer Costs for Dynamic Execution Offloading in Mobile Cloud Computing.
IEEE Trans. Mob. Comput.
Seungjun Yang, Donghyun Kwon, Hayoon Yi, Yeongpil Cho, Yongin Kwon, Yunheung Paek
2013 A* conf
Fast dynamic execution offloading for efficient mobile cloud computing.
PerCom
Seungjun Yang, Yongin Kwon, Yeongpil Cho, Hayoon Yi, Donghyun Kwon, Jonghee M. Youn, Yunheung Paek
2013 — conf
Mantis: Automatic Performance Prediction for Smartphone Applications.
USENIX ATC
Yongin Kwon, Sangmin Lee, Hayoon Yi, Donghyun Kwon, Seungjun Yang, Byung-Gon Chun, Ling Huang, Petros Maniatis, Mayur Naik, Yunheung Paek