Conference Papers
APT: Accelerating Diffusion Transformers via Attention Probability-Guided Pruning and Quantization
Sungyeob Yoo, Seeyeon Kim, Joonyong Park, Seunghee Han, Joo-Young Kim
IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2026
Picasso: A 28nm 4.96 TOPS/W End-to-End Diffusion Accelerator with Reconfigurable Hyper-Precision and Unified Non-Matrix Processing Engine
Sungyeob Yoo, Geonwoo Ko, Seri Ham, Seeyeon Kim, Yi Chen, and Joo-Young Kim
European Solid-State Electronics Research Conference(ESSERC), 2024
Picasso: An Area/Energy-Efficient End-to-End Diffusion Accelerator with Hyper-Precision Data Type
Sungyeob Yoo, Geonwoo Ko, Seri Ham, Seeyeon Kim, Yi Chen, and Joo-Young Kim
Hot Chips: A Symposium on High Performance Chips (HOTCHIPS), 2024
LightTrader: A Standalone AI-enabled High-Frequency Trading System with 16 TFLOPS / 64 TOPS Deep Learning Inference Accelerators
Sungyeob Yoo*, Hyunsung Kim*, Jinseok Kim, Sunghyun Park, Joo-Young Kim, and Jinwook Oh (*equal contribution)
IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2023
LightTrader: World’s first AI-enabled High-Frequency Trading Solution with 16 TFLOPS / 64 TOPS Deep Learning Inference Accelerators
Hyunsung Kim*, Sungyeob Yoo*, Jaewan Bae, Kyeongryeol Bong, Yoonho Boo, Karim Charfi, Hyo-Eun Kim, Hyun Suk Kim, Jinseok Kim, Byungjae Lee, Jaehwan Lee, Myeongbo Shim, Sungho Shin, Jeong Seok Woo, Joo-Young Kim, Sunghyun Park, and Jinwook Oh (*equal contribution); Rebellions Inc.
Hot Chips: A Symposium on High Performance Chips (HOTCHIPS), 2022
A Heterogeneous Vector-Array Architecture with Resource Scheduling for Multi-User/Multi-DNN Workloads
Sungyeob Yoo, Jung-Hoon Kim, Joo-Young Kim
Architecture, Compiler, and System Support for Multi-model DNN Workloads (ACSMD) Workshop 2021 (MICRO Workshop)
Journal Papers
An End-to-End Diffusion Accelerator With Reconfigurable Hyper-Precision and Unified Non-Matrix Processing Engine
Sungyeob Yoo, Seeyeon Kim, Geonwoo Ko, Seri Ham, Yi Chen, Joo-Young Kim
IEEE Transactions on Circuits and Systems I (TCAS-I), 2025
SuFP: Piecewise Bit Allocation Floating-Point for Robust Neural Network Quantization
*Geonwoo Ko, *Sungyeob Yoo, Seri Ham, Seeyeon Kim, Minkyu Kim, Joo-Young Kim (*equal contribution)
Transactions on Machine Learning Research (TMLR), 2025