김예성
Kim, YeseongDepartment of Electrical Engineering and Computer Science
학력
- 2013 ~ 2020UVIV OF CALIFORNIA SAN DIEGO 박사
- 2004 ~ 2011서울대학교 학사
경력
- 2007 ~ 2010파이널데이터 / 사원(병역특례)
수상실적
- 2022 Best Paper Award / IEEE/ACM Design Automation and Test in Europe Conference (DATE)
- 2020 Best Paper Award Nominated / IEEE/ACM Design Automation and Test in Europe Conference (DATE)
연구실 소개
- Computation Efficient Learning Lab.
-
Efficient AI Technology We focus on how to redesign AI and learning technologies towards superior computing efficiency for IoT/Big Data/edge computing. We explore alternative computing solutions for future learning technology, including near data computing to push computation beyond traditional processors, and brain-inspired hyperdimensional computing that closely models the ultimate efficient processor - the human brain.
Related Keyword
- "DeepPM: Predicting Performance and Energy Consumption of Program Binaries Using Transformers", ACM Transactions on Design Automation of Electronic Systems, v.30, no.6
- "Diffusion-Based Generative System Surrogates for Scalable Learning-Driven Optimization in Virtual Playgrounds", Proceedings of the ACM on Measurement and Analysis of Computing Systems, v.9, no.2, pp.43 - 45
- "Advancing Hyperdimensional Computing Based on Trainable Encoding and Adaptive Training for Efficient and Accurate Learning", Kim, Jiseung. (2024-09). Advancing Hyperdimensional Computing Based on Trainable Encoding and Adaptive Training for Efficient and Accurate Learning. ACM Transactions on Design Automation of Electronic Systems, 29(5), 1–25. doi: 10.1145/3665891
- "OpenHD: A GPU-Powered Framework for Hyperdimensional Computing", Kang, Jaeyoung. (2022-11). OpenHD: A GPU-Powered Framework for Hyperdimensional Computing. IEEE Transactions on Computers, 71(11), 2753–2765. doi: 10.1109/TC.2022.3179226
- "EventHD: Robust and efficient hyperdimensional learning with neuromorphic sensor", Zou, Zhuowen. (2022-07). EventHD: Robust and efficient hyperdimensional learning with neuromorphic sensor. Frontiers in Neuroscience, 16. doi: 10.3389/fnins.2022.858329
- "FlexNeRFer: A Multi-Dataflow, Adaptive Sparsity-Aware Accelerator for On-Device NeRF Rendering", ACM/IEEE International Symposium on Computer Architecture, pp.1894 - 1909
- "A Diffusion-Based Framework for Configurable and Realistic Multi-Storage Trace Generation", Design Automation Conference, pp.1 - 2
- "Hyperdimensional Computing-Based Federated Learning in Mobile Robots through Synthetic Oversampling", IEEE International Conference on Robotics and Automation, pp.13406 - 13412
- "Hyperdimensional Regression with Fine-Grained and Scalable Confidence-Based Learning", Design Automation and Test in Europe Conference, pp.1 - 2
- "Dynamically Scalable Pruning for Transformer-Based Large Language Models", Design Automation and Test in Europe Conference, pp.1 - 2
연구 뉴스
- 누구나 혜택을 누릴 수 있는 기술을 꿈꿉니다 [정보통신융합전공 김예성 교수] 2021-05-03
- 인간 뇌의 계산방식을 도입한 새로운 빅데이터 처리 기술 개발 2020-12-21
- DUAL takes AI to the next level 2020-12-21
연구분야
미래유망 신기술(6T)
국가과학기술표준분류