EECS and AI Department @ DGIST
We design the future learning technology and platform.
3 papers accepted : DiTTO, a novel diffusion-based framework for generating realistic, configurable, and diverse multi-device storage traces(DAC 2025); FlexNeRFer, an energy-efficient NeRF accelerator (ISCA 2025); a diffusion-based generative-AI surrogate
Continue ReadingAccepted Paper at DAC 2025, ISCA 2025, SIGMETRICS 2025
3 papers accepted: Reserach on a dynamic-encoding, oversampling HD federated learning framework for mobile robots (ICRA 2025); an HD framework designed with fine-grained feature encoding and a robust training scheme
Hojeong Kim, Selim An, Jaewoo Gwak, Sehyeon Park , Minsang Kim joined CELL in the first semester of 2025. Welcome!
We advance state-of-the-art Generative AI by developing sophisticated models, including LLM and Diffusion, and applying them to emerging fields such as system optimization and performance evaluation. Our work emphasizes the development of techniques for model optimization and knowledge compression, facilitating efficient deployment across diverse application domains and driving innovation in modern system design.
Hyperdimensional (HD) computing is an alternative computing method that processes cognitive tasks in a lightweight and error-torrent way based on theoretical neuroscience. We work on developing neuro-symbolic AI to support various learning tasks such as supervised, unsupervised, and reinforcement learning based on HD computing.
We rethink the role of machine learning in various alternative computing. We explore diverse system-level solutions to seamlessly accelerate AI applications on next-generation computer architectures such as near-data computing, in-memory computing, and CXL (Compute Express Link). We also develop ML-driven system software to enhance the capability of traditional computers.
E3 Building Room 613, 333, Techno jungang-daero, Hyeonpung-myeon Dalseong-gun, Daegu, 42988, REPUBLIC OF KOREA
yeseongkim(AT)dgist.ac.kr
(+82) 053-785-6332