Advanced Intelligent Computing Architecture Laboratory
AI Optimization Β· Memory Systems Β· Computer Architecture
Research Interests
μ°κ΅¬ λΆμΌ
Edge AI System Design & Optimization
Edge AI μμ€ν μ€κ³ λ° μ΅μ ν
Developing lightweight AI models and optimization techniques for resource-constrained edge devices, including pruning, quantization, knowledge distillation, and PIM/CIM-based acceleration.
Robust Memory Systems
κ°κ±΄ν λ©λͺ¨λ¦¬ μμ€ν
Designing innovative error correction codes (ECC) for HBM and DRAM systems, optimizing refresh mechanisms for energy-efficient DNN inference.
Next-Generation Memory Architecture
μ°¨μΈλ λ©λͺ¨λ¦¬ μν€ν μ²
Exploring monolithic 3D integration, hybrid SRAM/MRAM memories, Processing-in-Memory (PIM), Computing-in-Memory (CIM), and emerging non-volatile memory technologies for advanced computing systems.
Thermal-Aware System Optimization
λ°μ΄μ κ³ λ €ν μμ€ν μ΅μ ν
Developing thermal modeling methodologies and thermal-aware microarchitecture designs for mobile processors and 3D stacked systems.
Latest News
μ΅κ·Ό μμ
Our project proposal has been chosen for funding by the 2026 NRF Core Research Program
ν΅μ¬μ°κ΅¬(λμ½ν) μ°κ΅¬κ³Όμ μ μ μ λμμ΅λλ€.
One paper accepted to IEEE Computer Architecture Letters
IEEE CALμ λ Όλ¬Έμ΄ μ±νλμμ΅λλ€.
Awards at KSC2025: Seok-Hwan Kim (Outstanding Paper Award), Sang-Jun Moon (Undergraduate Junior Paper Competition Award)
KSC2025μμ κΉμν νμμ΄ μ°μλ Όλ¬Έμ, λ¬Έμμ€ νμμ΄ νλΆμμ£Όλμ΄λ Όλ¬Έκ²½μ§λν μμμ λ°μμ΅λλ€.
Two papers accepted to KSC2025
KSC2025μ 2νΈμ λ Όλ¬Έμ΄ μ±νλμμ΅λλ€.
Ye-Bin Kwon (M.S.) joins DeepX. SQUAD paper accepted to IEEE Access.
κΆμλΉ μμ¬κ° DeepXμ μ μ¬νμμ΅λλ€. SQUAD λ Όλ¬Έμ΄ IEEE Accessμ κ²μ¬ μΉμΈλμμ΅λλ€.
Selected Publications
μ£Όμ λ Όλ¬Έ
Exploring Heterogeneity-Aware Optimizations for Resource Efficient Edge Recommendation
Yerin Lee, Gyudong Kim, Eunjin Lee, Jeff Zhang, Young-Ho Gong, Young Geun Kim, Carole-Jean Wu
Design, Automation and Test in Europe Conference (DATE), Verona, Italy, Apr. 2026
DAWN: Efficient Distribution of Attention Workload in PIM-Enabled Systems for LLM Inference
Jaehoon Chung, Jinho Han, Young-Ho Gong, Sung Woo Chung
IEEE Computer Architecture Letters, 2026
SQUAD: A Scalable Quantization Accelerator Toward Energy-Efficient On-Device Quantization-aware Training
Ye-Bin Kwon, Young Seo Lee, Young-Ho Gong
IEEE Access, vol. 13, pp. 159487-159498, Sep. 2025
κ³μΈ΅λ³ λ―Όκ°λλ₯Ό κ³ λ €ν Binary-Ternary νμ΄λΈλ¦¬λ μμν κΈ°λ° μ£μ§ κ°μ²΄ κ°μ§ λͺ¨λΈ μ΅μ ν
Seok-Hwan Kim, Young-Ho Gong
νκ΅μννΈμ¨μ΄μ’ ν©νμ λν (KSC2025), μ¬μ, Dec. 2025
κ°κ±΄λ κΈ°λ° κ°μ§μΉκΈ° λ° μμνλ₯Ό ν΅ν Vision Transformer μ΅μ ν
Sang-Jun Moon, Young-Ho Gong
νκ΅μννΈμ¨μ΄μ’ ν©νμ λν (KSC2025), μ¬μ, Dec. 2025