Beomseok Kwon

Researcher, Hyperscale-AI Efficiency, NAVER CLOUD

Joined

September 2020

Names

Beomseok Kwon (Preferred)

Emails

****@hanyang.ac.kr (Confirmed)

,

****@gmail.com (Confirmed)

Personal Links

Career & Education History

Researcher

Hyperscale-AI Efficiency, NAVER CLOUD (navercorp.com)

2023 – Present

Researcher

Efficient AI, NAVER (navercorp.com)

2022 – 2023

MS student

Hanyang University (hanyang.ac.kr)

2020 – 2022

Advisors, Relations & Conflicts

No relations added

Expertise

AI model compression

2020 – Present

Publications

AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
Gunho Park, Jeongin Bae, Beomseok Kwon, Byeongwook Kim, Se Jung Kwon, Dongsoo Lee
- ICLR 2026 Poster
- Readers: Everyone
FlexBCQ: Flexible Binary-coding Quantization for Large Language Models
Seungcheol Park, Byeongwook Kim, Jeongin Bae, Beomseok Kwon, Se Jung Kwon, U Kang, Dongsoo Lee
- Submitted to ICLR 2025
- Readers: Everyone
Don’t Discard, but Keep It Small: Context-Preserving KV Cache Compression with Importance-Aware Adaptive Precision
June Yong Yang, Byeongwook Kim, Jeongin Bae, Gunho Park, Beomseok Kwon, Eunho Yang, Se Jung Kwon, Dongsoo Lee
- Submitted to ICLR 2025
- Readers: Everyone
LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
Gunho Park, Baeseong park, Minsub Kim, Sungjae Lee, Jeonghoon Kim, Beomseok Kwon, Se Jung Kwon, Byeongwook Kim, Youngjoo Lee, Dongsoo Lee
- ICLR 2024 poster
- Readers: Everyone
Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models
Jung Hwan Heo, Jeonghoon Kim, Beomseok Kwon, Byeongwook Kim, Se Jung Kwon, Dongsoo Lee
- ICLR 2024 poster
- Readers: Everyone

Co-Authors