AI Computing Platform Laboratory

Department of Computer Science and Engineering, Artificial Intelligence Convergence, Ewha Womans University

main2.jpg

As AI models continue to grow in size, they require vast amounts of energy, making sustainable AI unfeasible if current trends persist. Consequently, the importance of robust computing HW/SW infrastructure underpinning AI will become critical.

Our main research goal is to computing AI model in a faster and energy-efficient way through HW/SW co-design. Specifically, our research interests include:

  • Neural Processing Unit (NPU), domain-specific hardware, FPGA
  • Quantization, pruning, and knowledge distillation
  • Hardware-aware neural architecture search (HW-Aware NAS) and neural architecture accelerator search (NAAS)
  • Processing-in-memory (PIM)
  • Efficient LLM serving including KV Caching and other optimizations
  • On-Device AI

현재 연구실 구성원 모집 정보 및 연구실 합류 희망자 안내

news

Sep 15, 2025 Eunseo Ko has joined our group as an undergraduate intern. Welcome!
Sep 01, 2025 Jihyo Han has joined our group as a Master student. Welcome!
Sep 01, 2025 Jihee Choi, Hyun Young Kim, Wonjung Moon, Ingyeong Yang, Eunseo Shin, and Aria Yeonju Park have joined our group as an undergraduate intern. Welcome!
Aug 08, 2025 Our lab has two papers accepted for presentation at 22st International SoC Design Conference (ISOCC).
Jul 01, 2025 Jihyun Lee, Yoon Ji Choi, Nadam Park, and Jaelin Lee have joined our group as an undergraduate intern. Welcome!

latest publications

  1. Accepted
    LoRA-PIM: In-Memory Delta-Weight Injection for Multi-Adapter LLM Serving
    Soeun Choi, and Jaehyeong Sim
    In 2025 22st International SoC Design Conference (ISOCC)
  2. Accepted
    GATHER: A Gated-Attention Accelerator for Efficient LLM Inference
    Eunjin Lee, Eunseo Kim, Eunjoung Yoo, and Jaehyeong Sim
    In 2025 22st International SoC Design Conference (ISOCC)
  3. 학부생 성과
    메모리 용량 제약 하에서 하드웨어 최적화 트랜스포머 설계를 위한 HPO-NAS 통합 프레임워크
    Minseo Kim, Suhyeon Kim, Jiyeon Ha, and Jaehyeong Sim
    In 2025년도 대한전자공학회 하계학술대회
  4. ViT-Slim: Genetic Alorighm-based NAS Framework for Efficient Vision Transformer Design
    Eunjoung Yoo, and Jaehyeong Sim
    In 2025 IEEE International Conference on Artificial Intelligence (CAI)