Hoseung Kim

According to our database, Hoseung Kim authored at least 13 papers between 2019 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of five.

2026

ICaRus: Identical Cache Reuse for Efficient Multi Model Inference.

Sunghyeon Woo, Jaeeun Kil, Hoseung Kim, Minsub Kim, Joonghoon Kim, Ahreum Seo, Sungjae Lee, Minjung Jo, Jiwon Ryu, Baeseong Park, Se Jung Kwon, Dongsoo Lee

CoRR, March, 2026

PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving.

Sunghyeon Woo, Hoseung Kim, Sunghwan Shim, Minjung Jo, Hyunjoon Jeong, Jeongtae Lee, Joonghoon Kim, Sungjae Lee, Baeseong Park, Se Jung Kwon, Dongsoo Lee

CoRR, February, 2026

2025

CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs.

Gunho Park, Jeongin Bae, Byeongwook Kim, Baeseong Park, Jiwon Ryu, Hoseung Kim, Se Jung Kwon, Dongsoo Lee

CoRR, December, 2025

2024

Need Text Data Augmentation? Just One Insertion Is Enough.

Hoseung Kim, Jee-Hyong Lee

Int. J. Fuzzy Log. Intell. Syst., 2024

Classification of PRPD Pattern in Cast- Resin Transformers Using CNN and Implementation of Explainable AI (XAI) With Grad-CAM.

Hoseung Kim, Jiho Jung, Ryul Hwang, Seong-Chan Park, Seung-Jae Lee, Gyu-Tae Kim, Bang Wook Lee

IEEE Access, 2024

An Autonomous Parallelization of Transformer Model Inference on Heterogeneous Edge Devices.

Juhyeon Lee, Insung Bahk, Hoseung Kim, Sinjin Jeong, Suyeon Lee, Donghyun Min

Proceedings of the 38th ACM International Conference on Supercomputing, 2024

STAGE: Simple Text Data Augmentation by Graph Exploration.

Hoseung Kim, YongHoon Kang, Jee-Hyong Lee

Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024

2023

Area-Ware Adaptive Image Compression.

Hoseung Kim, Minho Park, Seunghu Hong, Chang-Sung Jeong

IEEE Access, 2023

2022

Reducing computational cost in federated ensemble learning via rank-one matrix.

YongHoon Kang, Hoseung Kim, Jee-Hyong Lee

Proceedings of the Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems, 2022

2021

Location-Based Saliency Maps from a Fully Connected Layer using Multi-Shapes.

Hoseung Kim, Seong-Soo Han, Chang-Sung Jeong

KSII Trans. Internet Inf. Syst., 2021

Filter-Wise Quantization of Deep Neural Networks for IoT Devices.

Hoseung Kim, Geunhye Jo, Hayun Lee, Dongkun Shin

Proceedings of the IEEE International Conference on Consumer Electronics, 2021

2020

Flexible Group-Level Pruning of Deep Neural Networks for On-Device Machine Learning.

Kwangbae Lee, Hoseung Kim, Hayun Lee, Dongkun Shin

Proceedings of the 2020 Design, Automation & Test in Europe Conference & Exhibition, 2020

2019

Flexible Group-Level Pruning of Deep Neural Networks for Fast Inference on Mobile GPUs.

Kwangbae Lee, Hoseung Kim, Hayun Lee, Dongkun Shin

Proceedings of the 2019 International Conference on Compliers, 2019