Gwangtae Park

39 papers A* 1C 1Journal 17Unranked 20
YearRankTypeTitle / Venue / Authors
2026 — conf
31.2 Revolver: Low-Bit GenAI Accelerator for Distilled-Model and CoT with Phase-Aware-Quantization and Rotation-Based Integer-Scaled Group Quantization.
ISSCC
Sangjin Kim, Jungjun Oh, Byeongcheol Kim, Yuseon Choi, Gwangtae Park, Hoi-Jun Yoo
2026 J jnl
EdgeDiff: Energy-Efficient Multi-Modal Few-Step Diffusion Model Accelerator Using Mixed-Precision and Reordered Group Quantization.
IEEE J. Solid State Circuits
Sangjin Kim, Jungjun Oh, Jeonggyu So, Yuseon Choi, Sangyeob Kim, Dongseok Im, Gwangtae Park, Hoi-Jun Yoo
2026 J jnl
IRIS: An Energy-Efficient Spatial Computing SoC for Real-Time Interactive Rendering and Modeling With Surface-Aware 3-D Gaussian Splatting.
IEEE J. Solid State Circuits
Seokchan Song, Seryeong Kim, Wonhoon Park, Jongjun Park, Sanghyuk An, Gwangtae Park, Minseo Kim, Hoi-Jun Yoo
2026 — conf
SMoLPU: 122.1µJ/Token Sparse MoE-Based Speculative Decoding Language Processing Unit with Adaptive-Offload NPU-CIM Core.
ISSCC
Sangwoo Ha, Jingu Lee, Youngjin Moon, Sunjoo Whang, Wooyoung Jo, Gwangtae Park, Sangjin Kim, Soyeon Um, Junha Ryu, Yurim Jo, Hoi-Jun Yoo
2025 — conf
23.3 EdgeDiff: 418.4mJ/Inference Multi-Modal Few-Step Diffusion Model Accelerator with Mixed-Precision and Reordered Group Quantization.
ISSCC
Sangjin Kim, Jungjun Oh, Jeonggyu So, Yuseon Choi, Sangyeob Kim, Dongseok Im, Gwangtae Park, Hoi-Jun Yoo
2025 — conf
EdgeDiff: Multi-modal Few-step Diffusion Model Accelerator with Mixed-Precision and Reordered Group-Quantization for On-device Generative AI Motivation.
HCS
Sangjin Kim, Jungjun Oh, Jeonggyu So, Yuseon Choi, Sangyeob Kim, Dongseo Kim, Gwangtae Park, Hoi-Jun Yoo
2025 — conf
IRIS: A 8.55 mJ/frame Spatial Computing SoC for Real-time Interactable-Rendering and Surface-aware-Modeling with 3D Gaussian Splatting.
HCS
Seokchan Song, Seryeong Kim, Wonhoon Park, Jongjun Park, Sanghyuk An, Gwangtae Park, Minseo Kim, Hoi-Jun Yoo
2025 — conf
IRIS: A 8.55mJ/frame Spatial Computing SoC for Interactable Rendering and Surface-Aware Modeling with 3D Gaussian Splatting.
ISSCC
Seokchan Song, Seryeong Kim, Wonhoon Park, Jongjun Park, Sanghyuk An, Gwangtae Park, Minseo Kim, Hoi-Jun Yoo
2025 J jnl
NeRF-Navi: An Energy-Efficient NeRF 3-D Path Planning Processor With Reconfigurable Approximate/Accurate Bit Offloading Core.
IEEE J. Solid State Circuits
Seryeong Kim, Seokchan Song, Wonhoon Park, Junha Ryu, Gwangtae Park, Sangyeob Kim, Soyeon Kim, Donghyeon Han, Hoi-Jun Yoo
2025 J jnl
SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference.
CoRR
Yuseon Choi, Sangjin Kim, Jungjun Oh, Gwangtae Park, Byeongcheol Kim, Hoi-Jun Yoo
2024 — conf
20.8 Space-Mate: A 303.5mW Real-Time Sparse Mixture-of-Experts-Based NeRF-SLAM Processor for Mobile Spatial Computing.
ISSCC
Gwangtae Park, Seokchan Song, Haoyang Sang, Dongseok Im, Donghyeon Han, Sangyeob Kim, Hongseok Lee, Hoi-Jun Yoo
2024 — conf
A 66.6 FPS High Quality Gaussian Splats Rendering FPGA Processor with Reconfigurable Computation Architecture.
A-SSCC
Hongseok Lee, Gwangtae Park, Wonhoon Park, Wooyoung Jo, Jongjun Park, Hoi-Jun Yoo
2024 J jnl
A 8.81 TFLOPS/W Deep-Reinforcement-Learning Accelerator With Delta-Based Weight Sharing and Block-Mantissa Reconfigurable PE Array.
IEEE Trans. Circuits Syst. II Express Briefs
Sanghyuk An, Junha Ryu, Gwangtae Park, Hoi-Jun Yoo
2024 — conf
A Low-power and Real-time Neural-Rendering Dense SLAM Processor with 3-Level Hierarchical Sparsity Exploitation.
COOL CHIPS
Gwangtae Park, Seokchan Song, Haoyang Sang, Dongseok Im, Donghyeon Han, Sangyeob Kim, Hongseok Lee, Hoi-Jun Yoo
2024 J jnl
An 2.31uJ/Inference Ultra-Low Power Always-on Event-Driven AI-IoT SoC With Switchable nvSRAM Compute-in-Memory Macro.
IEEE Trans. Circuits Syst. II Express Briefs
Haoyang Sang, Wenao Xie, Gwangtae Park, Hoi-Jun Yoo
2024 J jnl
An Artificial-Intelligence-Based SLAM Processor With Scene-Adaptive Sampling and Hybrid NeRF Model Training Acceleration.
IEEE Trans. Circuits Syst. Artif. Intell.
Gwangtae Park, Seokchan Song, Haoyang Sang, Dongseok Im, Donghyeon Han, Sangyeob Kim, Hongseok Lee, Hoi-Jun Yoo
2024 — conf
NeRF-Navi: A 93.6-202.9µJ/task Switchable Approximate-Accurate NeRF Path Planning Processor with Dual Attention Engine and Outlier Bit-Offloading Core.
VLSI Technology and Circuits
Seryeong Kim, Seokchan Song, Wonhoon Park, Junha Ryu, Sangyeob Kim, Gwangtae Park, Soyeon Kim, Hoi-Jun Yoo
2023 C conf
A 15.9 mW 96.5 fps Memory-Efficient 3D Reconstruction Processor with Dilation-based TSDF Fusion and Block-Projection Cache System.
ISCAS
Hankyul Kwon, Gwangtae Park, Junha Ryu, Wooyoung Jo, Hoi-Jun Yoo
2023 — conf
A 33.6 FPS Embedding based Real-time Neural Rendering Accelerator with Switchable Computation Skipping Architecture on Edge Device.
A-SSCC
Jongjun Park, Donghyeon Han, Junha Ryu, Dongseok Im, Gwangtae Park, Hoi-Jun Yoo
2023 J jnl
A Mobile 3-D Object Recognition Processor With Deep-Learning-Based Monocular Depth Estimation.
IEEE Micro
Dongseok Im, Gwangtae Park, Zhiyong Li, Junha Ryu, Sanghoon Kang, Donghyeon Han, Jinsu Lee, Wonhoon Park, Hankyul Kwon, Hoi-Jun Yoo
2023 J jnl
DSPU: An Efficient Deep Learning-Based Dense RGB-D Data Acquisition With Sensor Fusion and 3-D Perception SoC.
IEEE J. Solid State Circuits
Dongseok Im, Gwangtae Park, Junha Ryu, Zhiyong Li, Sanghoon Kang, Donghyeon Han, Jinsu Lee, Wonhoon Park, Hankyul Kwon, Hoi-Jun Yoo
2023 — conf
GPPU: A 330.4-μJ/ task Neural Path Planning Processor with Hybrid GNN Acceleration for Autonomous 3D Navigation.
VLSI Technology and Circuits
Seokchan Song, Donghyeon Han, Sangjin Kim, Sangyeob Kim, Gwangtae Park, Hoi-Jun Yoo
2023 A* conf
Sibia: Signed Bit-slice Architecture for Dense DNN Acceleration with Slice-level Sparsity Exploitation.
HPCA
Dongseok Im, Gwangtae Park, Zhiyong Li, Junha Ryu, Hoi-Jun Yoo
2022 — conf
A 0.95 mJ/frame DNN Training Processor for Robust Object Detection with Real-World Environmental Adaptation.
AICAS
Donghyeon Han, Dongseok Im, Gwangtae Park, Youngwoo Kim, Seokchan Song, Juhyoung Lee, Hoi-Jun Yoo
2022 J jnl
A 49.5 mW Multi-Scale Linear Quantized Online Learning Processor for Real-Time Adaptive Object Detection.
IEEE Trans. Circuits Syst. II Express Briefs
Seokchan Song, Soyeon Kim, Gwangtae Park, Donghyeon Han, Hoi-Jun Yoo
2022 — conf
A DNN Training Processor for Robust Object Detection with Real-World Environmental Adaptation.
AICAS
Donghyeon Han, Dongseok Im, Gwangtae Park, Youngwoo Kim, Seokchan Song, Juhyoung Lee, Hoi-Jun Yoo
2022 — conf
A Low-power and Real-time 3D Object Recognition Processor with Dense RGB-D Data Acquisition in Mobile Platforms.
COOL CHIPS
Dongseok Im, Gwangtae Park, Junha Ryu, Zhiyong Li, Sanghoon Kang, Donghyeon Han, Jinsu Lee, Wonhoon Park, Hankyul Kwon, Hoi-Jun Yoo
2022 J jnl
A Mobile DNN Training Processor With Automatic Bit Precision Search and Fine-Grained Sparsity Exploitation.
IEEE Micro
Donghyeon Han, Dongseok Im, Gwangtae Park, Youngwoo Kim, Seokchan Song, Juhyoung Lee, Hoi-Jun Yoo
2022 — conf
DSPU: A 281.6mW Real-Time Deep Learning-Based Dense RGB-D Data Acquisition with Sensor Fusion and 3D Perception System-on-Chip.
HCS
Dongseok Im, Gwangtae Park, Zhiyong Li, Junha Ryu, Sanghoon Kang, Donghyeon Han, Jinsu Lee, Wonhoon Park, Hankyul Kwon, Hoi-Jun Yoo
2022 — conf
DSPU: A 281.6mW Real-Time Depth Signal Processing Unit for Deep Learning-Based Dense RGB-D Data Acquisition with Depth Fusion and 3D Bounding Box Extraction in Mobile Platforms.
ISSCC
Dongseok Im, Gwangtae Park, Zhiyong Li, Junha Ryu, Sanghoon Kang, Donghyeon Han, Jinsu Lee, Hoi-Jun Yoo
2022 J jnl
Energy-efficient Dense DNN Acceleration with Signed Bit-slice Architecture.
CoRR
Dongseok Im, Gwangtae Park, Zhiyong Li, Junha Ryu, Hoi-Jun Yoo
2022 — conf
HNPU-V2: A 46.6 FPS DNN Training Processor for Real-World Environmental Adaptation based Robust Object Detection on Mobile Devices.
HCS
Donghyeon Han, Dongseok Im, Gwangtae Park, Youngwoo Kim, Seokchan Song, Juhyoung Lee, Hoi-Jun Yoo
2021 J jnl
A 0.82 μW CIS-Based Action Recognition SoC With Self-Adjustable Frame Resolution for Always-on IoT Devices.
IEEE Trans. Circuits Syst. II Express Briefs
Junha Ryu, Gwangtae Park, Dongseok Im, Ji-Hoon Kim, Hoi-Jun Yoo
2021 — conf
An Energy-Efficient Deep Neural Network Training Processor with Bit-Slice-Level Reconfigurability and Sparsity Exploitation.
COOL CHIPS
Donghyeon Han, Dongseok Im, Gwangtae Park, Youngwoo Kim, Seokchan Song, Juhyoung Lee, Hoi-Jun Yoo
2021 J jnl
An Overview of Sparsity Exploitation in CNNs for On-Device Intelligence With Software-Hardware Cross-Layer Optimizations.
IEEE J. Emerg. Sel. Topics Circuits Syst.
Sanghoon Kang, Gwangtae Park, Sangjin Kim, Soyeon Kim, Donghyeon Han, Hoi-Jun Yoo
2021 J jnl
HNPU: An Adaptive DNN Training Processor Utilizing Stochastic Dynamic Fixed-Point and Active Bit-Precision Searching.
IEEE J. Solid State Circuits
Donghyeon Han, Dongseok Im, Gwangtae Park, Youngwoo Kim, Seokchan Song, Juhyoung Lee, Hoi-Jun Yoo
2020 J jnl
A 1.15 TOPS/W Energy-Efficient Capsule Network Accelerator for Real-Time 3D Point Cloud Segmentation in Mobile Environment.
IEEE Trans. Circuits Syst. II Express Briefs
Gwangtae Park, Dongseok Im, Donghyeon Han, Hoi-Jun Yoo
2020 J jnl
Extension of Direct Feedback Alignment to Convolutional and Recurrent Neural Network for Bio-plausible Deep Learning.
CoRR
Donghyeon Han, Gwangtae Park, Junha Ryu, Hoi-Jun Yoo
2019 — conf
LNPU: A 25.3TFLOPS/W Sparse Deep-Neural-Network Learning Processor with Fine-Grained Mixed Precision of FP8-FP16.
ISSCC
Jinsu Lee, Juhyoung Lee, Donghyeon Han, Jinmook Lee, Gwangtae Park, Hoi-Jun Yoo