Janghwan Lee

25 papers A* 6B 2Misc 1Journal 11Unranked 5
YearRankTypeTitle / Venue / Authors
2025 — conf
AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference.
ACL (Findings)
Janghwan Lee, Jiwoong Park, Jinseok Kim, Yongjik Kim, Jungju Oh, Jinwook Oh, Jungwook Choi
2025 J jnl
Patch-aware Vector Quantized Codebook Learning for Unsupervised Visual Defect Detection.
CoRR
Qisen Cheng, Shuhui Qu, Janghwan Lee
2025 A* conf
RILQ: Rank-Insensitive LoRA-Based Quantization Error Compensation for Boosting 2-Bit Large Language Model Accuracy.
AAAI
Geonho Lee, Janghwan Lee, Sukjin Hong, Minsoo Kim, Euijai Ahn, Du-Seong Chang, Jungwook Choi
2024 J jnl
AMXFP4: Taming Activation Outliers with Asymmetric Microscaling Floating-Point for 4-bit LLM Inference.
CoRR
Janghwan Lee, Jiwoong Park, Jinseok Kim, Yongjik Kim, Jungju Oh, Jinwook Oh, Jungwook Choi
2024 J jnl
Efficient Generation of Molecular Clusters with Dual-Scale Equivariant Flow Matching.
CoRR
Akshay Subramanian, Shuhui Qu, Cheol Woo Park, Sulin Liu, Janghwan Lee, Rafael Gómez-Bombarelli
2024 — conf
ISP2DLA: Automated Deep Learning Accelerator Design for On-Sensor Image Signal Processing.
ASAP
Dong-eon Won, Yeeun Kim, Janghwan Lee, Minjae Lee, Jonghyun Bae, Jongjoo Park, Jeongyong Song, Jungwook Choi
2024 — conf
Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment.
ACL (1)
Janghwan Lee, Seongmin Park, Sukjin Hong, Minsoo Kim, Du-Seong Chang, Jungwook Choi
2024 J jnl
Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment.
CoRR
Janghwan Lee, Seongmin Park, Sukjin Hong, Minsoo Kim, Du-Seong Chang, Jungwook Choi
2024 B conf
Patch-aware Vector Quantized Codebook Learning for Unsupervised Visual Defect Detection.
ICTAI
Qisen Cheng, Shuhui Qu, Janghwan Lee
2024 J jnl
RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy.
CoRR
Geonho Lee, Janghwan Lee, Sukjin Hong, Minsoo Kim, Euijai Ahn, Du-Seong Chang, Jungwook Choi
2024 A* conf
SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving.
HPCA
Minjae Lee, Seongmin Park, Hyungmin Kim, Minyong Yoon, Janghwan Lee, Jun Won Choi, Nam Sung Kim, Mingu Kang, Jungwook Choi
2024 — conf
Searching Optimal Floating-Point Format for Sub-8-Bit Large Language Model Inference.
ICEIC
Youngdeok Hwang, Janghwan Lee, Jiwoong Park, Jieun Lim, Jungwook Choi
2023 A* conf
Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization.
EMNLP
Janghwan Lee, Minsoo Kim, Seungcheol Baek, Seok Joong Hwang, Wonyong Sung, Jungwook Choi
2023 J jnl
Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization.
CoRR
Janghwan Lee, Minsoo Kim, Seungcheol Baek, Seok Joong Hwang, Wonyong Sung, Jungwook Choi
2023 Misc conf
Finding Optimal Numerical Format for Sub-8-Bit Post-Training Quantization of Vision Transformers.
ICASSP
Janghwan Lee, Youngdeok Hwang, Jungwook Choi
2023 J jnl
PillarAcc: Sparse PointPillars Accelerator for Real-Time Point Cloud 3D Object Detection on Edge Devices.
CoRR
Minjae Lee, Hyungmin Kim, Seongmin Park, Minyong Yoon, Janghwan Lee, Junwon Choi, Mingu Kang, Jungwook Choi
2023 A* conf
Range-Invariant Approximation of Non-Linear Operations for Efficient BERT Fine-Tuning.
DAC
Janghyeon Kim, Janghwan Lee, Jungwook Choi, Jeongho Han, Sangheon Lee
2023 J jnl
SHAPNN: Shapley Value Regularized Tabular Neural Network.
CoRR
Qisen Cheng, Shuhui Qu, Janghwan Lee
2023 A* conf
Token-Scaled Logit Distillation for Ternary Weight Generative Language Models.
NeurIPS
Minsoo Kim, Sihwa Lee, Janghwan Lee, Sukjin Hong, Du-Seong Chang, Wonyong Sung, Jungwook Choi
2023 J jnl
Token-Scaled Logit Distillation for Ternary Weight Generative Language Models.
CoRR
Minsoo Kim, Sihwa Lee, Janghwan Lee, Sukjin Hong, Du-Seong Chang, Wonyong Sung, Jungwook Choi
2022 — conf
Optimizing Exponent Bias for Sub-8bit Floating-Point Inference of Fine-tuned Transformers.
AICAS
Janghwan Lee, Jungwook Choi
2021 A* conf
Efficient Multi-Modal Fusion with Diversity Analysis.
ACM Multimedia
Shuhui Qu, Yan Kang, Janghwan Lee
2010 J jnl
Distributed Fair Scheduling for Wireless Mesh Networks Using IEEE 802.11.
IEEE Trans. Veh. Technol.
Janghwan Lee, Hyunsoo Yoon, Ikjun Yeom
2008 B conf
Achieving throughput fairness in Wireless Mesh Networks based on IEEE 802.11.
MASS
Janghwan Lee, Ikjun Yeom
2006 J jnl
A video browser based on closed cap.
IEEE Trans. Consumer Electron.
Janghwan Lee