• Lightweight AI algorithms for energy-efficient inference/training HW accelerators

• Hardware implementation and compression algorithms for physical AI / robotics

• Architecture using emerging memory technologies (HBM, HBF, PIM) for agentic AI workloads

• Energy-efficient hardware accelerator for scientific computing

• Spike-driven neural network design and its hardware implementation

Broader research interests include efficient AI algorithms, digital IC design, and accelerator/computer architecture. We look forward to working with highly motivated students. Please send me an e-mail if you are interested in pursuing a PhD or an integrated MS-PhD program.

• Our recent work on the hybrid digital-and-analog SRAM PIM for highly robust and efficient AI inference has been accepted for publication at IEEE TCAS-I. Congrats to Sangwoo Jung and Hojin Lee!

• Our recent work on proactive tile-aware partial sum quantization (PsumQuant) for efficient NPU inference has been accepted at ICML'26 as a regular paper. Congrats to Dr. Sangwoo Hwang!

• Our recent work on developing an automated hardware optimization framework for finding the optimal systolic tensor array (STA) configuration has been accepted for publication at IEEE TVLSI. Congrats to Jooyeon Lee!

• Our recent work on the efficient data packing method for balancing data reuse maximization and flush overhead minimization on DSP-less MCUs  has been accepted at IEEE/ACM ICCAD'26. Congrats to Dahoon Park!

• Multi-institutional collaboration on a review paper about reliable and efficient physical AI systems has been accepted for publication at Nature Reviews Computing. Kudos to all the collaborators!

• Our recent work on a universal block-wise scaling data format that safely supports both LLM inference and training has been accepted for publication at IEEE JETCAS. Congrats to Dahoon Park!

E-mail

Principal Investigator – Jaeha Kung (jhkung@korea.ac.kr)

Lab Representative – Donghun Lee (dhleeids@korea.ac.kr) 

Lab Coordinator – Junsang Park (jshparksh@dgist.ac.kr) 

Please contact "Lab Coordinator" for inquiries about 'Lab Internship, Information about IDS Lab, etc'.

Location

서울특별시 성북구 안암로 145, 신공학관 512호 (교수님 연구실) / 501호 (학생 연구실)

145 Anam-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea,

New Engineering Hall Room 512 (Professor Lab) / Room 501 (Student Lab)