- Computer Vision System on Chip
- Hardware-friendly Computer Vision Algorithm
2025. 2 Ph.D. in EE, Korea Advanced Insititue of Science and Technology (KAIST)
2022. 2 M.S. in EE, Korea Advanced Insititue of Science and Technology (KAIST)
2020. 2 B.S. in EE, Korea Advanced Insititue of Science and Technology (KAIST)
2015. 2 Changwon Science High School
- International Journal Papers
An Overview of Neural Rendering Accelerators: Challenges, Trends, and Future Directions
Junha Ryu and Hoi-Jun Yoo
IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS), Apr. 2025
NeuGPU: An Energy-Efficient Neural Graphics Processing Unit for Instant Modeling and Real-Time Rendering on Mobile Devices
Junha Ryu, Hankyul Kwon, Wonhoon Park, Zhiyong Li, Beomseok Kwon, Donghyeon Han, Dongseok Im, Sangyeob Kim, Hyungnam Joo, Minsung Kim and Hoi-Jun Yoo
IEEE Journal of Solid-State Circuits (JSSC), Sep. 2024
A 0.82 μW CIS-Based Action Recognition SoC with Self-Adjustable Frame Resolution for Always-on IoT Devices
Junha Ryu, Gwangtae Park, Dongseok Im, Ji-Hoon Kim, and Hoi-Jun Yoo
IEEE Transactions on Circuits and Systems II (TCAS-II), Mar. 2021
- International Conference Papers
NeuGPU: A Neural Graphics Processing Unit for Instant Modeling and Real-Time Rendering on Mobile AR/VR Devices
Junha Ryu, Hankyul Kwon, Wonhoon Park, Zhiyong Li, Beomseok Kwon, Donghyeon Han, Dongseok Im, Sangyeob Kim, Hyungnam Joo, Minsung Kim and Hoi-Jun Yoo
IEEE Symposium on High Performance Chips (HOT Chips), May. 2024
A Low-Power Neural Graphics System for Instant 3D Modeling and Real-Time Rendering on Mobile AR/VR Devices
Junha Ryu, Hankyul Kwon, Wonhoon Park, Zhiyong Li, Beomseok Kwon, Donghyeon Han, Dongseok Im, Sangyeob Kim, Hyungnam Joo, Minsung Kim, and Hoi-Jun Yoo
IEEE Symposium on Low-Power and High-Speed Chips (COOL Chips), Apr. 2024
NeuGPU: A 18.5 mJ/Iter Neural-Graphics Processing Unit for Instant-Modeling and Real-Time Rendering with Segmented-Hashing Architecture
AI SoCs for AR/VR User-Interaction
Junha Ryu, Dongseok Im, and Hoi-Jun Yoo
IEEE International Electron Devices Meeting (IEDM), Dec. 2021
A 0.82 μW CIS-Based Action Recognition SoC with Self-Adjustable Frame Resolution for Always-on IoT Devices
Junha Ryu, Gwangtae Park, Dongseok Im, Ji-Hoon Kim, and Hoi-Jun Yoo
IEEE International Symposium on Circuit and Systems (ISCAS), May. 2021
- Deep Learning Processor
- Machine Learning Algorithms
2026. 2 Ph.D. in EE, Korea Advanced Insititue of Science and Technology (KAIST)
2023. 2 M.S. in EE, Korea Advanced Insititue of Science and Technology (KAIST)
2021. 2 B.S. in EE, Korea Advanced Insititue of Science and Technology (KAIST)
2017. 2 Gyeonggi Science High School
- International Journal Papers
StereoGS: An Energy-Efficient 3D Gaussian Splatting Stereoscopic Rendering Processor
Seokchan Song, and Hoi-Jun Yoo
IEEE Journal on Emerging and Selected Topics in Circuits and Systems (JETCAS), July. 2026
IRIS: An Energy-Efficient Spatial Computing SoC for Real-Time Interactive Rendering and Modeling With Surface-Aware 3-D Gaussian Splatting
Seokchan Song, Seryeong Kim, Wonhoon Park, Jongjun Park, Sanghyuk An, Gwangtae Park, Minseo Kim and Hoi-Jun Yoo
IEEE Journal of Solid-State Circuits (JSSC), Oct. 2025
A 49.5 mW Multi-Scale Linear Quantized Online Learning Processor for Real-Time Adaptive Object Detection
Seokchan Song, Soyeon Kim, Gwangtae Park, Donghyeon Han, and Hoi-Jun Yoo
IEEE Transactions on Circuits and Systems II (TCAS-II), Mar. 2022
- International Conference Papers
An Energy-Efficient Spatial Computing SoC for Real-time Interactable-Rendering and Modeling with Surface-aware 3D Gaussian Splatting
Seokchan Song, Seryeong Kim, Wonhoon Park, Jongjun Park, Sanghyuk An, Gwangtae Park, Minseo Kim and Hoi-Jun Yoo
IEEE Symposium on High Performance Chips (HOT Chips), Aug. 2025
IRIS: A 8.55 mJ/frame Spatial Computing SoC for Interactable-Rendering and Surface-aware-Modeling with 3D Gaussian Splatting
GPPU: A 330.4-µJ/task Neural Path Planning Processor with Hybrid GNN Acceleration for Autonomous 3D Navigation
Seokchan Song, Donghyeon Han, Sangjin Kim, Sangyeob Kim, Gwangtae Park and Hoi-Jun Yoo
IEEE Symposium on VLSI Circuits (S. VLSI), Apr. 2023
A 49.5 mW Multi-Scale Linear Quantized Online Learning Processor for Real-Time Adaptive Object Detection
Seokchan Song, Soyeon Kim, Gwangtae Park, Donghyeon Han, and Hoi-Jun Yoo
IEEE International Symposium on Circuits and Systems (ISCAS), May. 2022
- Deep Learning Processor
- Machine Learning Algorithms
2026. 8 Ph.D. in EE, Korea Advanced Insititue of Science and Technology (KAIST)
2022. 8 M.S. in EE, Korea Advanced Insititue of Science and Technology (KAIST)
2020. 8 B.S. in EE, Korea Advanced Insititue of Science and Technology (KAIST)
2017. 2 Gyeonggi Science High School
- International Conference Papers
BROCA: A Low-power and Low-latency Conversational Agent RISC-V System-on-Chip for Voice-interactive Mobile Devices
Wooyoung Jo, Seongyon Hong, Jiwon Choi, Beomseok Kwon, Haoyang Sang, Dongseok Im, Sangyeob Kim, Sangjin Kim, Chaeyun Jeong, Yujin Moon and Hoi-Jun Yoo
IEEE Symposium on High Performance Chips (HOT Chips), Aug. 2025
BROCA: A 52.4-559.2mW Mobile Social Agent System-on-Chip with Adaptive-Bit-Truncate Unit and Acoustic-Cluster Bit-Grouping
NeRPIM: A 4.2 mJ/frame Neural Rendering Processing-in-memory Processor with Space Encoding Block-wise Mapping for Mobile Devices
Wooyoung Jo, Sangjin Kim, Juhyoung Lee, Donghyeon Han, Sangyeob Kim, Seungyoon Choi and Hoi-Jun Yoo
IEEE Symposium on VLSI Circuits (S. VLSI), Apr. 2023
A 161.6 TOPS/W Mixed-Mode Computing-in-Memory Processor for Energy-Efficient Mixed-Precision Deep Neural Networks
Wooyoung Jo, Sangjin Kim, Juhyoung Lee, Soyeon Um, Zhiyong Li, and Hoi-Jun Yoo
IEEE International Symposium on Circuits and Systems (ISCAS), May. 2022
An Energy-Efficient Deep Reinforcement Learning FPGA Accelerator for Online Fast Adaptation with Selective Mixed-Precision Re-Training
Wooyoung Jo, Juhyoung Lee, Seunghyun Park, and Hoi-Jun Yoo
Asian Solid-State Circuits Conference (ASSCC), Nov. 2021
- Processing-In-Memory (PIM)
- Memory Subsystems
- Deep Learning SoC Design
2026. 8 Ph.D. in EE, Korea Advanced Insititue of Science and Technology (KAIST)
2022. 8 M.S. in EE, Korea Advanced Insititue of Science and Technology (KAIST)
2020. 8 B.S. in EE, Korea University
2015. 2 Haedong High School
- International Journal Papers
SMoLPU: An Energy-Efficient Sparse Mixture-of-Experts-Based Speculative Decoding Language Processing Unit
Sangwoo Ha, Jingu Lee, Youngjin Moon, Sunjoo Whang, Wooyoung Jo, Gwangtae Park, Sangjin Kim, Soyeon Um, Junha Ryu, Yurim Jo, Hoi-Jun Yoo
IEEE Journal of Solid-State Circuits (JSSC), Sep. 2026
Cache-PIM: An ECC-compatible eDRAM Processing-In-Memory for Last-Level Cache with Triple-level Error Correction
Sangwoo Ha, Soyeon Um, Sangjin Kim, Kyomin Sohn, and Hoi-Jun Yoo
IEEE Journal of Solid-State Circuits (JSSC), May. 2025
A 36.2 dB High SNR and PVT/Leakage-robust eDRAM Computing-In-Memory Macro with Segmented BL and Reference Cell Array
Sangwoo Ha, Sangjin Kim, Donghyeon Han, Soyeon Um, and Hoi-Jun Yoo
IEEE Transactions on Circuits and Systems II (TCAS-II), Mar. 2022
- International Conference Papers
EdgeXpert: An Edge Device for Memory-Efficient LLM Inference with Mixture-of-Experts and Speculative Decoding
Sangwoo Ha, Hyunwoo Seo, Yurim Jo, Youngjin Moon, and Hoi-Jun Yoo
IEEE/ACM International Symposium on Microarchitecture (MICRO), Nov. 2026
An Energy-Efficient LLM Processor with Pipelined NPU-CIM
Sangwoo Ha, Jingu Lee, Youngjin Moon, Sunjoo Whang, Wooyoung Jo, Gwangtae Park, Sangjin Kim, Soyeon Um, Junha Ryu, Yurim Jo, Jongjun Park and Hoi-Jun Yoo
IEEE Symposium on Low-Power and High-Speed Chips (COOL Chips), Apr. 2026
SMoLPU: 122.1μJ/Token Sparse MoE-based Speculative Decoding Language Processing Unit with Adaptive-Offload NPU-CIM Core
Sangwoo Ha, Jingu Lee, Youngjin Moon, Sunjoo Whang, Wooyoung Jo, Gwangtae Park, Sangjin Kim, Soyeon Um, Junha Ryu, Yurim Jo, Hoi-Jun Yoo
IEEE International Solid-State Circuits Conference (ISSCC), Feb. 2026
Cache-PIM: An ECC-compatible eDRAM-PIM for Last-Level Cache with Resolution-aware Single-Cycle Voting
Sangwoo Ha, Soyeon Um, Sangjin Kim, Kyomin Sohn and Hoi-Jun Yoo
IEEE European Solid-State Electronics Research Conference (ESSERC), Sep. 2024
A 36.2 dB High SNR and PVT/Leakage-robust eDRAM Computing-In-Memory Macro with Segmented BL and Reference Cell Array
Sangwoo Ha, Sangjin Kim, Donghyeon Han, Soyeon Um, and Hoi-Jun Yoo
IEEE International Symposium on Circuits and Systems (ISCAS), May. 2022
Address#1233, School of Electrical Engineering, KAIST, 291 Daehak-ro (373-1 Guseong-dong), Yuseong-gu, Daejeon 34141, Republic of Korea
Tel +82-42-350-8068 Fax +82-42-350-3410E-mail sslmaster@kaist.ac.kr·© SSL. All Rights Reserved.·Design by NSTAR
