Yuseon Choi

Yuseon Choi

Master's student at KAIST Digital Accelerator

Publications

Google Scholar Profile

Conference Papers

arXiv 2026
ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving
arXiv, 2026
Yuseon Choi, Jingu Lee, Jungjun Oh, Sunjoo Whang, Byeongcheol Kim, Minsung Kim, Hoi-Jun Yoo, Sangjin Kim
DAC 2026
SliceMoE: Bit-Sliced Expert Caching under Miss-Rate Constraints for Efficient MoE Inference
63rd ACM/IEEE Design Automation Conference (DAC), 2026
Yuseon Choi, Sangjin Kim, Jungjun Oh, Gwangtae Park, Byeongcheol Kim, Hoi-Jun Yoo
ISCAS 2026
SeVeDo: A Heterogeneous Transformer Accelerator for Low-Bit Inference via Hierarchical Group Quantization and SVD-Guided Mixed Precision
IEEE International Symposium on Circuits and Systems (ISCAS), 2026
Yuseon Choi, Sangjin Kim, Jungjun Oh, Byeongcheol Kim, Hoi-Jun Yoo
ISCAS 2026
A 198.7 μJ/token Block Diffusion LLM Processor with Mask Token Similarity-Based Acitivation Reuse
IEEE International Symposium on Circuits and Systems (ISCAS), 2026
Yujin Moon, Jiwon Choi, Seryeong Kim, Wonhoon Park, Wooyoung Jo, Yuseon Choi, Sunjoo Whang and Hoi-Jun Yoo
ISSCC 2026
31.2 Revolver: Low-Bit GenAI Accelerator for Distilled-Model and CoT with Phase-Aware-Quantization and Rotation-Based Integer-Scaled Group Quant
IEEE International Solid-State Circuits Conference (ISSCC), 2026
Sangjin Kim, Jungjun Oh, Byeongcheol Kim, Yuseon Choi, Gwangtae Park, Hoi-Jun Yoo
HPCA 2026
GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM Inference
IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2026
Sangjin Kim, Yuseon Choi, Byeongcheol Kim, Jungjun Oh, Hoi-Jun Yoo
HCS 2025
EdgeDiff: Multi-modal Few-step Diffusion Model Accelerator with Mixed-Precision and Reordered Group-Quantization for On-device Generative AI Motivation
IEEE Hot Chips 37 Symposium (HCS), 2025
Sangjin Kim, Jungjun Oh, Jeonggyu So, Yuseon Choi, Sangyeob Kim, Dongseo Kim, Gwangtae Park, Hoi-Jun Yoo
ISSCC 2025
23.3 EdgeDiff: 418.4 mJ/Inference Multi-Modal Few-Step Diffusion Model Accelerator with Mixed-Precision and Reordered Group Quantization
IEEE International Solid-State Circuits Conference (ISSCC), 2025
Sangjin Kim, Jungjun Oh, Jeonggyu So, Yuseon Choi, Hoi-Jun Yoo

Journal Articles

JSSC 2025
EdgeDiff: Energy-Efficient Multi-Modal Few-Step Diffusion Model Accelerator Using Mixed-Precision and Reordered Group Quantization
IEEE Journal of Solid-State Circuits, 2025
Sangjin Kim, Jungjun Oh, Jeonggyu So, Yuseon Choi, Sangyeob Kim, Dongseok Im, Gwangtae Park, Hoi-Jun Yoo
T.VLSI 2025
An Energy-Efficient High Resolution Vision Transformer Processor Exploiting Token Similarity Beyond Token Merging
IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2025
Jungjun Oh, Sangjin Kim, Jiwon Choi, Junha Ryu, Byeongcheol Kim, Yuseon Choi, Hoi-Jun Yoo
JETCAS 2025
LightRot: A Light-weighted Rotation Scheme and Architecture for Accurate Low-bit Large Language Model Inference
IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Sangjin Kim, Yuseon Choi, Jungjun Oh, Byeongcheol Kim, Hoi-Jun Yoo