Sungwoong Yune is awarded Deputy Prime Minister’s Award at 2026 AI Semiconductor Outstanding Achievement Competition
Congratulations! Sungwoong Yune is awarded Deputy Prime Minister’s Award at 2026 AI Semiconductor Outstanding Achievement Competition
Prof. Joo-Young Kim appointed as a member of Y-KAST
Congratulations! Prof. Joo-Young Kim appointed as a member of Young Korean Academy of Science and Technology(Y-KAST). The Korean Academy of Science and Technology (KAST) has elected 29 young scientists with outstanding research achievements in science and technology as new members for 2026. Prof. Kim is among the newly elected members recognized for his exceptional achievements. […]
Jieon Yoon and Donghyuk Kim win Gold and Bronze Prizes at the 32nd Samsung Humantech Paper Award
Congratulations! Our papers won the ‘Gold Prize’ and ‘Bronze Prize’ at the 32nd Samsung Humantech Paper Award. The Gold Prize is awarded only to the first-place winner in each division. [Gold Prize] “DiSC: Resolution-Scalable Acceleration of Diffusion Models by Exploiting Sparsity and Cached Token Reuse with Hash-based Distribution” (research section: Computer Science & Engineering) [Bronze […]
Prof. Joo-Young Kim is awarded Minister of Trade, Industry and Energy Award in Startup Nation Korea 2025
Congratulations! Prof. Joo-Young Kim is awarded Minister of Trade, Industry and Energy Award in Startup Nation Korea 2025 It is based on the selection results of CEOs who have excelled in performance or made significant contributions to startup industry in Korea.
[TMLR 2025] Geonwoo Ko and Sungyeob Yoo’s paper on SuFP: Piecewise Bit Allocation Floating-Point for Robust Neural Network Quantization is accepted
Congratulations! We have a paper accepted to Transactions on Machine Learning Research (TMLR), 2025. “SuFP: Piecewise Bit Allocation Floating-Point for Robust Neural Network Quantization”
[A-SSCC 2025] Jieon Yoon and Sungwoong Yune’s paper on MoDiff: a 11.0 TOPS/W Diffusion Accelerator with Temporal Data Reuse for Real-Time Text-to-Motion Generation is accepted
Congratulations! We have a paper accepted to IEEE Asian Solid-State Circuits Conference (A-SSCC), 2025. “MoDiff: a 11.0 TOPS/W Diffusion Accelerator with Temporal Data Reuse for Real-Time Text-to-Motion Generation”
[A-SSCC 2025] Hangyeol Kim’s paper on An Efficient FPGA Accelerator with Spatiotemporal Tubelet Merging for Video Transformers is accepted
Congratulations! We have a paper accepted to IEEE Asian Solid-State Circuits Conference (A-SSCC), 2025. “An Efficient FPGA Accelerator with Spatiotemporal Tubelet Merging for Video Transformers”
[MICRO 2025] In-Jun Jung’s paper on HLX: A Unified Pipelined Architecture for Optimized Performance of Hybrid Transformer-Mamba Language Models is accepted
Congratulations! We have a paper accepted to ACM/IEEE International Symposium on Microarchitecture (MICRO), 2025 “HLX: A Unified Pipelined Architecture for Optimized Performance of Hybrid Transformer-Mamba Language Models”
[ESSERC 2025] Donghyuk Kim and In-Jun Jung’s paper on D3TA: 38.9TOPS/W Transformer Accelerator with Dual-Port 3T-eDRAM Digital Compute-In-Memory Using HyperAttention and Triple-Sparsity-Handling is accepted
Congratulations! We have a paper accepted to Symposium on European Solid-State Electronics Research Conference(ESSERC), 2025 “D3TA: 38.9TOPS/W Transformer Accelerator with Dual-Port 3T-eDRAM Digital Compute-In-Memory Using HyperAttention and Triple-Sparsity-Handling”
[TC 2025] Wontak Han’s paper on SAL-PIM: A Subarray-level Processing-in-Memory Architecture with LUT-based Linear Interpolation for Transformer-based Text Generation is accepted
Congratulations! We have a paper accepted to IEEE Transactions on Computers (TC), 2025 “SAL-PIM: A Subarray-level Processing-in-Memory Architecture with LUT-based Linear Interpolation for Transformer-based Text Generation”