AI Computing Platform Laboratory
Department of Computer Science and Engineering, Artificial Intelligence Convergence, Ewha Womans University

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
news
Sep 26, 2025 | Miyeon Lee has joined our group as a Master student. Welcome! |
---|---|
Sep 22, 2025 | Seunghee Song has joined our group as an undergraduate intern. Welcome! |
Sep 19, 2025 | Our lab has two papers accepted for presentation at 2025 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI). |
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! |
latest publications
-
AcceptedMAGNETO: A Genetic Algorithm-Based Power-Aware Mapping Optimization Framework for Mobile NPUsIn 2025 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)
-
AcceptedDS-CAE: a Dual-Stream Cross-Attentive Autoencoder for Robust and Cluster-Aware Retrieval-Augmented GenerationIn 2025 International Conference on Communications, Computing, Cybersecurity, and Informatics (CCCI)
-
AcceptedLoRA-PIM: In-Memory Delta-Weight Injection for Multi-Adapter LLM ServingIn 2025 22st International SoC Design Conference (ISOCC)
-
AcceptedGATHER: A Gated-Attention Accelerator for Efficient LLM InferenceIn 2025 22st International SoC Design Conference (ISOCC)