Jaekang Shin

14 papers A* 4A 3Journal 7
YearRankTypeTitle / Venue / Authors
2025 J jnl
AToM: Adaptive Token Merging for Efficient Acceleration of Vision Transformer.
IEEE Trans. Computers
Jaekang Shin, Myeonggu Kang, Yunki Han, Junyoung Park, Lee-Sup Kim
2024 J jnl
Accelerating Deep Reinforcement Learning via Phase-Level Parallelism for Robotics Applications.
IEEE Comput. Archit. Lett.
Yanggon Kim, Yunki Han, Jaekang Shin, Junkyum Kim, Lee-Sup Kim
2024 A conf
CoCoA: Algorithm-Hardware Co-Design for Large-Scale GNN Training using Compressed Graph.
ICCAD
Yunki Han, Jaekang Shin, Gunhee Park, Lee-Sup Kim
2024 J jnl
ToEx: Accelerating Generation Stage of Transformer-Based Language Models via Token-Adaptive Early Exit.
IEEE Trans. Computers
Myeonggu Kang, Junyoung Park, Hyein Shin, Jaekang Shin, Lee-Sup Kim
2024 A* conf
Token-Picker: Accelerating Attention in Text Generation with Minimized Memory Transfer via Probability Estimation.
DAC
Junyoung Park, Myeonggu Kang, Yunki Han, Yanggon Kim, Jaekang Shin, Lee-Sup Kim
2024 J jnl
Token-Picker: Accelerating Attention in Text Generation with Minimized Memory Transfer via Probability Estimation.
CoRR
Junyoung Park, Myeonggu Kang, Yunki Han, Yanggon Kim, Jaekang Shin, Lee-Sup Kim
2023 J jnl
Accelerating On-Device DNN Training Workloads via Runtime Convergence Monitor.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.
Seungkyu Choi, Jaekang Shin, Lee-Sup Kim
2023 J jnl
Energy-Efficient CNN Personalized Training by Adaptive Data Reformation.
IEEE Trans. Comput. Aided Des. Integr. Circuits Syst.
Youngbeom Jung, Hyeonuk Kim, Seungkyu Choi, Jaekang Shin, Lee-Sup Kim
2022 J jnl
A Deep Neural Network Training Architecture With Inference-Aware Heterogeneous Data-Type.
IEEE Trans. Computers
Seungkyu Choi, Jaekang Shin, Lee-Sup Kim
2022 A* conf
Algorithm/architecture co-design for energy-efficient acceleration of multi-task DNN.
DAC
Jaekang Shin, Seungkyu Choi, Jongwoo Ra, Lee-Sup Kim
2021 A conf
A Convergence Monitoring Method for DNN Training of On-Device Task Adaptation.
ICCAD
Seungkyu Choi, Jaekang Shin, Lee-Sup Kim
2021 A conf
A Framework for Area-efficient Multi-task BERT Execution on ReRAM-based Accelerators.
ICCAD
Myeonggu Kang, Hyein Shin, Jaekang Shin, Lee-Sup Kim
2020 A* conf
A Pragmatic Approach to On-device Incremental Learning System with Selective Weight Updates.
DAC
Jaekang Shin, Seungkyu Choi, Yeongjae Choi, Lee-Sup Kim
2019 A* conf
An Optimized Design Technique of Low-bit Neural Network Training for Personalization on IoT Devices.
DAC
Seungkyu Choi, Jaekang Shin, Yeongjae Choi, Lee-Sup Kim