Wonyong Sung

Publication Activity (10 Years)

Years Active: 1980-2024
Publications (10 Years): 76

Top Venues

CoRR

ICASSP

SiPS

INTERSPEECH

Publications

Minsoo Kim, Sihwa Lee, Wonyong Sung, Jungwook Choi
RA-LoRA: Rank-Adaptive Parameter-Efficient Fine-Tuning for Accurate 2-bit Quantized Large Language Models. ACL (Findings) (2024)
Minsoo Kim, Kyuhong Shim, Seongmin Park, Wonyong Sung, Jungwook Choi
Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers. EACL (2023)
Iksoo Choi, Wonyong Sung
Sleep Model - A Sequence Model for Predicting the Next Sleep Stage. CoRR (2023)
Kyuhong Shim, Hyewon Bae, Wonyong Sung
Korean Tokenization for Beam Search Rescoring in Speech Recognition. ICEIC (2023)
Iksoo Choi, Wonyong Sung
Sleep Model: A Sequence Model for Predicting the Next Sleep Stage. BioCAS (2023)
Kyuhong Shim, Jungwook Choi, Wonyong Sung
Exploring Attention Map Reuse for Efficient Transformer Neural Networks. CoRR (2023)
Iksoo Choi, Wonyong Sung
Single-Channel Ecg-Based Sleep Stage Classification With End-To-End Trainable Deep Neural Networks. EMBC (2023)
Janghwan Lee, Minsoo Kim, Seungcheol Baek, Seok Joong Hwang, Wonyong Sung, Jungwook Choi
Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization. EMNLP (2023)
Minsoo Kim, Kyuhong Shim, Seongmin Park, Wonyong Sung, Jungwook Choi
Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers. CoRR (2023)
Minsoo Kim, Sihwa Lee, Janghwan Lee, Sukjin Hong, Du-Seong Chang, Wonyong Sung, Jungwook Choi
Token-Scaled Logit Distillation for Ternary Weight Generative Language Models. CoRR (2023)
Janghwan Lee, Minsoo Kim, Seungcheol Baek, Seok Joong Hwang, Wonyong Sung, Jungwook Choi
Enhancing Computation Efficiency in Large Language Models through Weight and Activation Quantization. CoRR (2023)
Minsoo Kim, Sihwa Lee, Janghwan Lee, Sukjin Hong, Du-Seong Chang, Wonyong Sung, Jungwook Choi
Token-Scaled Logit Distillation for Ternary Weight Generative Language Models. NeurIPS (2023)
Seokhyeon Choi, Kyuhong Shim, Jungwook Choi, Wonyong Sung, Byonghyo Shim
Optimization of General Matrix Multiply Library for Ternary Weight for Fast DNN Inference. J. Signal Process. Syst. 94 (10) (2022)
Chanwoo Kim, Sathish Indurti, Jinhwan Park, Wonyong Sung
Macro-block dropout for improved regularization in training end-to-end speech recognition models. CoRR (2022)
Kyuhong Shim, Wonyong Sung
Similarity and Content-based Phonetic Self Attention for Speech Recognition. INTERSPEECH (2022)
Kyuhong Shim, Jungwook Choi, Wonyong Sung
Understanding the Role of Self Attention for Efficient Speech Recognition. ICLR (2022)
Seongmin Park, Wonyong Sung, Jungwook Choi
Regularizing Activation Distribution for Ultra Low-bit Quantization-Aware Training of MobileNets. SiPS (2022)
Iksoo Choi, Wonyong Sung
Performance Assessment of Automatic Sleep Stage Classification Using Only Partial PSG Sensors. BioCAS (2022)
Kyuhong Shim, Wonyong Sung
Similarity and Content-based Phonetic Self Attention for Speech Recognition. CoRR (2022)
Kyuhong Shim, Hyewon Bae, Wonyong Sung
Korean Tokenization for Beam Search Rescoring in Speech Recognition. CoRR (2022)
Chanwoo Kim, Sathish Indurti, Jinhwan Park, Wonyong Sung
Macro-Block Dropout for Improved Regularization in Training End-to-End Speech Recognition Models. SLT (2022)
Kyuhong Shim, Wonyong Sung
A Comparison of Transformer, Convolutional, and Recurrent Neural Networks on Phoneme Recognition. CoRR (2022)
Kyuhong Shim, Iksoo Choi, Wonyong Sung, Jungwook Choi
Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling. CoRR (2021)
Yoonho Boo, Sungho Shin, Jungwook Choi, Wonyong Sung
Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks. AAAI (2021)
Seokhyeon Choi, Kyuhong Shim, Jungwook Choi, Wonyong Sung, Byonghyo Shim
TernGEMM: GEneral Matrix Multiply Library with Ternary Weights for Fast DNN Inference. SiPS (2021)
Sungho Shin, Yoonho Boo, Wonyong Sung
SQWA: Stochastic Quantized Weight Averaging For Improving The Generalization Capability Of Low-Precision Deep Neural Networks. ICASSP (2021)
Kyuhong Shim, Iksoo Choi, Wonyong Sung, Jungwook Choi
Layer-wise Pruning of Transformer Attention Heads for Efficient Language Modeling. ISOCC (2021)
Jinhwan Park, Chanwoo Kim, Wonyong Sung
Convolution-Based Attention Model With Positional Encoding For Streaming Speech Recognition On Embedded Devices. SLT (2021)
Yoonho Boo, Sungho Shin, Wonyong Sung
Quantized Neural Networks: Characterization and Holistic Optimization. CoRR (2020)
Jinhwan Park, Xue Qian, Youngmin Jo, Wonyong Sung
Low-Latency Lightweight Streaming Speech Recognition with 8-Bit Quantized Simple Gated Convolutional Neural Networks. ICASSP (2020)
Wonyong Sung, Iksoo Choi, Jinhwan Park, Seokhyun Choi, Sungho Shin
S-SGD: Symmetrical Stochastic Gradient Descent with Weight Noise Injection for Reaching Flat Minima. CoRR (2020)
Jinhwan Park, Wonyong Sung
Effect of Adding Positional Information on Convolutional Neural Networks for End-to-End Speech Recognition. INTERSPEECH (2020)
Sungho Shin, Yoonho Boo, Wonyong Sung
Knowledge Distillation for Optimization of Quantized Deep Neural Networks. SiPS (2020)
Sungho Shin, Jinhwan Park, Yoonho Boo, Wonyong Sung
HLHLp: Quantized Neural Networks Training for Reaching Flat Minima in Loss Surface. AAAI (2020)
Yoonho Boo, Sungho Shin, Wonyong Sung
Quantized Neural Networks: Characterization and Holistic Optimization. SiPS (2020)
Yoonho Boo, Wonyong Sung
Fixed-Point Optimization of Transformer Neural Network. ICASSP (2020)
Yoonho Boo, Sungho Shin, Jungwook Choi, Wonyong Sung
Stochastic Precision Ensemble: Self-Knowledge Distillation for Quantized Deep Neural Networks. CoRR (2020)
Sungho Shin, Yoonho Boo, Wonyong Sung
SQWA: Stochastic Quantized Weight Averaging for Improving the Generalization Capability of Low-Precision Deep Neural Networks. CoRR (2020)
Yoonho Boo, Sungho Shin, Wonyong Sung
Memorization Capacity of Deep Neural Networks under Parameter Quantization. ICASSP (2019)
Lukas Lee, Jinhwan Park, Wonyong Sung
Simple Gated Convnet for Small Footprint Acoustic Modeling. ASRU (2019)
Sungho Shin, Youngmin Jo, Jungwook Choi, Swagath Venkataramani, Vijayalakshmi Srinivasan, Wonyong Sung
Workload-aware Automatic Parallelization for Multi-GPU DNN Training. ICASSP (2019)
Yoonho Boo, Wonyong Sung
Compression of Deep Neural Networks with Structured Sparse Ternary Coding. J. Signal Process. Syst. 91 (9) (2019)
Wonyong Sung, Lukas Lee, Jinhwan Park
Exploration of On-device End-to-End Acoustic Modeling with Neural Networks. SiPS (2019)
Sungho Shin, Yoonho Boo, Wonyong Sung
Empirical Analysis of Knowledge Distillation Technique for Optimization of Quantized Deep Neural Networks. CoRR (2019)
Wonyong Sung, Dong-hwan Lee, Kyuyeon Hwang
Massively parallel computation of linear recurrence equations with graphics processing units. SAMOS (2018)
Iksoo Choi, Jinhwan Park, Wonyong Sung
Character-level Language Modeling with Gated Hierarchical Recurrent Neural Networks. INTERSPEECH (2018)
Yoonho Boo, Jinhwan Park, Lukas Lee, Wonyong Sung
On-Device End-to-end Speech Recognition with Multi-Step Parallel Rnns. SLT (2018)
Jinhwan Park, Yoonho Boo, Iksoo Choi, Sungho Shin, Wonyong Sung
Fully Neural Network Based Speech Recognition on Mobile and Embedded Devices. NeurIPS (2018)
Wonyong Sung, Jinhwan Park
Single Stream Parallelization of Recurrent Neural Networks for Low Power and Fast Inference. CoRR (2018)
Jinhwan Park, Iksoo Choi, Yoonho Boo, Wonyong Sung
Hierarchical Recurrent Neural Networks for Acoustic Modeling. INTERSPEECH (2018)
Sungho Shin, Youngmin Jo, Jungwook Choi, Swagath Venkataramani, Vijayalakshmi Srinivasan, Wonyong Sung
Workload-aware Automatic Parallelization for Multi-GPU DNN Training. CoRR (2018)
Yoonho Boo, Wonyong Sung
Structured sparse ternary weight coding of deep neural networks for efficient hardware implementations. SiPS (2017)
Sungho Shin, Yoonho Boo, Wonyong Sung
Fixed-point optimization of deep neural networks with adaptive step size retraining. CoRR (2017)
Junhee Cho, Wonyong Sung
High-throughput decoding of block turbo codes on graphics processing units. SiPS (2017)
Kyuhong Shim, Minjae Lee, Iksoo Choi, Yoonho Boo, Wonyong Sung
SVD-Softmax: Fast Softmax Approximation on Large Vocabulary Neural Networks. NIPS (2017)
Sajid Anwar, Kyuyeon Hwang, Wonyong Sung
Structured Pruning of Deep Convolutional Neural Networks. ACM J. Emerg. Technol. Comput. Syst. 13 (3) (2017)
Kyuyeon Hwang, Wonyong Sung
Character-level language modeling with hierarchical recurrent neural networks. ICASSP (2017)
Sungho Shin, Yoonho Boo, Wonyong Sung
Fixed-point optimization of deep neural networks with adaptive step size retraining. ICASSP (2017)
Yoonho Boo, Wonyong Sung
Structured Sparse Ternary Weight Coding of Deep Neural Networks for Efficient Hardware Implementations. CoRR (2017)
Sungho Shin, Kyuyeon Hwang, Wonyong Sung
Quantized neural network design under weight capacity constraint. CoRR (2016)
Sungho Shin, Kyuyeon Hwang, Wonyong Sung
Fixed-point performance analysis of recurrent neural networks. ICASSP (2016)
Minjae Lee, Kyuyeon Hwang, Jinhwan Park, Sungwook Choi, Sungho Shin, Wonyong Sung
FPGA-Based Low-Power Speech Recognition with Recurrent Neural Networks. CoRR (2016)
Kyuyeon Hwang, Wonyong Sung
Character-level incremental speech recognition with recurrent neural networks. ICASSP (2016)
Sajid Anwar, Kyuyeon Hwang, Wonyong Sung
Learning separable fixed-point kernels for deep convolutional neural networks. ICASSP (2016)
Junhee Cho, Wonyong Sung
Evaluation of block turbo codes for long-haul optical networks. APCC (2016)
Sungho Shin, Kyuyeon Hwang, Wonyong Sung
Generative Transfer Learning between Recurrent Neural Networks. CoRR (2016)
Kyuyeon Hwang, Wonyong Sung
Sequence to Sequence Training of CTC-RNNs with Partial Windowing. ICML (2016)
Wonyong Sung, Jinhwan Park
Architecture exploration of a programmable neural network processor for embedded systems. SAMOS (2016)
Kyuyeon Hwang, Wonyong Sung
Character-Level Language Modeling with Hierarchical Recurrent Neural Networks. CoRR (2016)
Sungho Shin, Wonyong Sung
Dynamic hand gesture recognition for wearable devices with low complexity recurrent neural networks. ISCAS (2016)
Kyuyeon Hwang, Wonyong Sung
Character-Level Incremental Speech Recognition with Recurrent Neural Networks. CoRR (2016)
Jinhwan Park, Wonyong Sung
Fpga Based Implementation of Deep Neural Networks Using On-chip Memory Only. CoRR (2016)
Sungho Shin, Wonyong Sung
Dynamic Hand Gesture Recognition for Wearable Devices with Low Complexity Recurrent Neural Networks. CoRR (2016)
Sajid Anwar, Wonyong Sung
Compact Deep Convolutional Neural Networks With Coarse Pruning. CoRR (2016)
Jinhwan Park, Wonyong Sung
FPGA based implementation of deep neural networks using on-chip memory only. ICASSP (2016)
Minjae Lee, Kyuyeon Hwang, Jinhwan Park, Sungwook Choi, Sungho Shin, Wonyong Sung
FPGA-Based Low-Power Speech Recognition with Recurrent Neural Networks. SiPS (2016)
Kyuyeon Hwang, Wonyong Sung
Single stream parallelization of generalized LSTM-like RNNs on a GPU. ICASSP (2015)
Kyuyeon Hwang, Minjae Lee, Wonyong Sung
Online Keyword Spotting with a Character-Level Recurrent Neural Network. CoRR (2015)
Kyuyeon Hwang, Wonyong Sung
Single stream parallelization of generalized LSTM-like RNNs on a GPU. CoRR (2015)
Dong-hwan Lee, Jonghong Kim, Wonyong Sung
Low Energy Signal Processing Techniques for Reliability Improvement of High-Density NAND Flash Memory. J. Signal Process. Syst. 78 (1) (2015)
Wonyong Sung, Sungho Shin, Kyuyeon Hwang
Resiliency of Deep Neural Networks under Quantization. CoRR (2015)
Sungho Shin, Kyuyeon Hwang, Wonyong Sung
Fixed Point Performance Analysis of Recurrent Neural Networks. CoRR (2015)
Kyuyeon Hwang, Wonyong Sung
Online Sequence Training of Recurrent Neural Networks with Connectionist Temporal Classification. CoRR (2015)
Sajid Anwar, Kyuyeon Hwang, Wonyong Sung
Structured Pruning of Deep Convolutional Neural Networks. CoRR (2015)
Sajid Anwar, Kyuyeon Hwang, Wonyong Sung
Fixed point optimization of deep convolutional neural networks for object recognition. ICASSP (2015)
Junho Cho, Jonghong Kim, Wonyong Sung
Area-Efficient Parallel Syndrome Generators for Linear Block Codes. J. Signal Process. Syst. 77 (3) (2014)
Minjae Lee, Kyuyeon Hwang, Wonyong Sung
Fault tolerance analysis of digital feed-forward deep neural networks. ICASSP (2014)
Dong-hwan Lee, Wonyong Sung
Direct and indirect measurement of inter-cell capacitance in NAND flash memory. SiPS (2014)
Dong-hwan Lee, Wonyong Sung
Decision Directed Estimation of Threshold Voltage Distribution in NAND Flash Memory. IEEE Trans. Signal Process. 62 (4) (2014)
Kyuyeon Hwang, Wonyong Sung
Fixed-point feedforward deep neural network design using weights +1, 0, and -1. SiPS (2014)
Jieun Lim, Nagesh B. Lakshminarayana, Hyesoon Kim, William J. Song, Sudhakar Yalamanchili, Wonyong Sung
Power Modeling for GPU Architectures Using McPAT. ACM Trans. Design Autom. Electr. Syst. 19 (3) (2014)
Jonghong Kim, Wonyong Sung
Rate-0.96 LDPC Decoding VLSI for Soft-Decision Error Correction of NAND Flash Memory. IEEE Trans. Very Large Scale Integr. Syst. 22 (5) (2014)
Jonghong Kim, Kyuyeon Hwang, Wonyong Sung
X1000 real-time phoneme recognition VLSI using feed-forward deep neural networks. ICASSP (2014)
Dong-hwan Lee, Wonyong Sung
GPU based implementation of recursive digital filtering algorithms. ICASSP (2013)
Dong-hwan Lee, Wonyong Sung
Least Squares Based Coupling Cancelation for MLC NAND Flash Memory with a Small Number of Voltage Sensing Operations. J. Signal Process. Syst. 71 (3) (2013)
Seungyeol Lee, Wonyong Sung
DRAM access reduction in GPUs by thread-block scheduling for overlapped data reuse. ISCAS (2013)
Jarmo Takala, Warren J. Gross, Wonyong Sung
Guest Editors' Introduction to Special Issue on Advances in DSP System Design. J. Signal Process. Syst. 71 (3) (2013)
Dong-hwan Lee, Wonyong Sung
Soft-decision decoding with cell to cell interference removed signal in nand flash memory. ICASSP (2013)
Junhee Cho, Wonyong Sung
Soft-Decision Error Correction of NAND Flash Memory with a Turbo Product Code. J. Signal Process. Syst. 70 (2) (2013)
Kyuyeon Hwang, Wonyong Sung
Load Balanced Resampling for Real-Time Particle Filtering on Graphics Processing Units. IEEE Trans. Signal Process. 61 (2) (2013)

Wonyong Sung.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Wonyong Sung