Dongsoo Lee
Scholar

Dongsoo Lee

Google Scholar ID: ALiieEkAAAAJ
NAVER Cloud
Model compressionoptimizationAI Chip Design
Google Scholar↗
Citations & Impact
All-time
Citations
1,436
 
H-index
18
 
i10-index
30
 
Publications
20
 
Co-authors
3
list available
Contact
No contact links provided.
Publications
14 items
SUN: Shared Use of Next-token Prediction for Efficient Multi-LLM Disaggregated Serving
2026
Cited
0
Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention
2026
Cited
0
PrefillShare: A Shared Prefill Module for KV Reuse in Multi-LLM Disaggregated Serving
2026
Cited
0
CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs
2025
Cited
0
AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
2025
Cited
0
Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models
2025
Cited
0
Faster Inference of LLMs using FP8 on the Intel Gaudi
2025
Cited
0
FIGLUT: An Energy-Efficient Accelerator Design for FP-INT GEMM Using Look-Up Tables
2025
Cited
0
Resume (English only)
Co-authors
3 total
Jae-Joon Kim
Jae-Joon Kim
Professor, Department of Electrical and Computer Engineering, Seoul National University
Co-author 2
Co-author 2
Co-author 3
Co-author 3