Beomseok Kwon

Publication Activity (10 Years)

Years Active: 2022-2024
Publications (10 Years): 11

Top Topics

Image Generation

Uniform Quantization

Top Venues

IEEE Trans. Circuits Syst. II Express Briefs

Publications

Gunho Park, Baeseong Park, Minsub Kim, Sungjae Lee, Jeonghoon Kim, Beomseok Kwon, Se Jung Kwon, Byeongwook Kim, Youngjoo Lee, Dongsoo Lee
LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models. ICLR (2024)
Jung Hwan Heo, Jeonghoon Kim, Beomseok Kwon, Byeongwook Kim, Se Jung Kwon, Dongsoo Lee
Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models. ICLR (2024)
Junha Ryu, Hankyul Kwon, Wonhoon Park, Zhiyong Li, Beomseok Kwon, Donghyeon Han, Dongseok Im, Sangyeob Kim, Hyungnam Joo, Hoi-Jun Yoo
20.7 NeuGPU: A 18.5mJ/Iter Neural-Graphics Processing Unit for Instant-Modeling and Real-Time Rendering with Segmented-Hashing Architecture. ISSCC (2024)
Jiwon Choi, Wooyoung Jo, Seongyon Hong, Beomseok Kwon, Wonhoon Park, Hoi-Jun Yoo
A 28.6 mJ/iter Stable Diffusion Processor for Text-to-Image Generation with Patch Similarity-based Sparsity Augmentation and Text-based Mixed-Precision. ISCAS (2024)
Jiwon Choi, Wooyoung Jo, Seongyon Hong, Beomseok Kwon, Wonhoon Park, Hoi-Jun Yoo
A 28.6 mJ/iter Stable Diffusion Processor for Text-to-Image Generation with Patch Similarity-based Sparsity Augmentation and Text-based Mixed-Precision. CoRR (2024)
Junha Ryu, Hankyul Kwon, Wonhoon Park, Zhiyong Li, Beomseok Kwon, Donghyeon Han, Dongseok Im, Sangyeob Kim, Hyungnam Joo, Minsung Kim, Hoi-Jun Yoo
A Low-Power Neural Graphics System for Instant 3D Modeling and Real-Time Rendering on Mobile AR/VR Devices. COOL CHIPS (2024)
June Yong Yang, Byeongwook Kim, Jeongin Bae, Beomseok Kwon, Gunho Park, Eunho Yang, Se Jung Kwon, Dongsoo Lee
No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization. CoRR (2024)
Beomseok Kwon, Zhiyong Li, Sangjin Kim, Wooyoung Jo, Hoi-Jun Yoo
A 92 fps and 2.56 mJ/Frame Computing-In-Memory-Based Human Pose Estimation Accelerator With Resource-Efficient Macro for Mobile Devices. IEEE Trans. Circuits Syst. II Express Briefs 71 (6) (2024)
Jung Hwan Heo, Jeonghoon Kim, Beomseok Kwon, Byeongwook Kim, Se Jung Kwon, Dongsoo Lee
Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models. CoRR (2023)
Wenao Xie, Haoyang Sang, Beomseok Kwon, Dongseok Im, Sangjin Kim, Sangyeob Kim, Hoi-Jun Yoo
A 709.3 TOPS/W Event-Driven Smart Vision SoC with High-Linearity and Reconfigurable MRAM PIM. VLSI Technology and Circuits (2023)
Seongmin Park, Beomseok Kwon, Jieun Lim, Kyuyoung Sim, Taeho Kim, Jungwook Choi
Automatic Network Adaptation for Ultra-Low Uniform-Precision Quantization. CoRR (2022)