1st year PhD student at OSI LAB of KAIST AI
<aside> 💌 itsnamgyu[at]kaist.ac.kr • Google Scholar • Twitter • LinkedIn • GitHub
</aside>
Solving problems for next generation LLMs. Published an early work on LLM distillation [C4] last year. Recently published the Block Transformer architecture [C7] that holistically optimizes inference time compute and memory costs for batch inference on the cloud. Currently pursuing broad research experience.
Last updated June 16th 2024
Sogang University (Seoul), BS in CSE (Mar 2016 – Aug 2021) 3.87/4.3 (Summa Cum Laude)
KAIST (Seoul) MS in Artificial Intelligence (Sep 2021 – Aug 2023) OSI LAB (Advisor: Se-Young Yun)
KAIST (Seoul), PhD in Artificial Intelligence (Sep 2023 – ) OSI LAB (Advisor: Se-Young Yun), XFact (Co-Advisor: James Thorne)
[C7] Block Transformer: Global-to-Local Language Modeling for Fast Inference (Under review) Namgyu Ho*, Sangmin Bae*, Taehyeon Kim, Hyunjik Jo, Yireun Kim, Tal Schuster, Adam Fisch, James Thorne, and Se-Young Yun [Paper] [Twitter] [GitHub]
[C4] Large Language Models Are Reasoning Teachers (ACL 2023) Namgyu Ho, Laura Schmid, and Se-Young Yun [Paper] [Twitter] [GitHub]
[C3] Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty (NeurIPS 2022) Jaehoon Oh*, Sungnyun Kim*, Namgyu Ho*, Jin-Hwa Kim, Hwanjun Song, and Se-Young Yun [Paper]
[C6] Carpe Diem: On the Evaluation of World Knowledge in Lifelong Language Models (NAACL 2024) Yujin Kim, Jaehong Yoon, Seonghyeon Ye, Sangmin Bae, Namgyu Ho, Sung Ju Hwang, and Se-young Yun [Paper]
[C5] HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning (EMNLP 2023 Findings) Yongjin Yang*, Joonkee Kim*, Yujin Kim*, Namgyu Ho, James Thorne, Se-Young Yun [Paper]
[C2] ReFine: Re-Randomization before Fine-Tuning for Cross-Domain Few-Shot Learning (CIKM 2022) Jaehoon Oh*, Sungnyun Kim*, Namgyu Ho*, Jin-Hwa Kim, Hwanjun Song, Se-Young Yun [Paper]
[J2] Estimation of Cardiac Short Axis Slice Levels with a Cascaded Deep Convolutional and Recurrent Neural Network Model (Tomography 8, 2023) Namgyu Ho and Yoon-Chul Kim [Paper]
[C1] Cardiac short-axis slice range classification via transfer learning: Evaluation of seven popular deep CNNs (ISMRM 2019) Namgyu Ho, Yoon-Chul Kim, Yeon Hyeon Choe **[Paper]
[J1] Evaluation of transfer learning in deep convoluional neural network models for cardiac short axis slice classification (Scientific reports 11, 2021) Namgyu Ho* and Yoon-Chul Kim* [Paper]
Research Intern @ EXAONE Lab, LG AI Research (Dec 2023 – Jun 2024) Seoul 📝 Initiated and lead a research project on the Block Transformer architecture for efficient inference [C7], involving 9 authors with stakeholders/advisors at LG and KAIST and collaboration with external co-authors at Google DeepMind.
SWE Intern / Team Lead @ ZionTech Solutions (Mar 2019 – Jan 2020) SF Bay Area 📝 Initiated and lead a major effort to migrate the entire frontend of ZionTech’s flagship cloud service “Wavity” to the Angular framework, in production as of summer 2020.
Undergraduate Researcher @ Samsung Medical Center (2018, 2020 – 2021) Seoul 📝 Application of transfer learning, deep CNNs, and recursive networks on cardiac MRI. Under the supervision of Prof. Yoon-Chul Kim.
Naver D2 Campus Fest 2019 2nd place (Jan 2019 – Feb 2019) Open-source project using Python/Django
Alpha Sigma Nu (2018 – 2019) The honor society of Jesuit colleges and universities
Contributhon (Aug – Nov 2018/2020) Korean translation of Keras, PyTorch online tutorials
Microsoft Student Partners (2018/2019) Hosted tech evangelism events at Sogang University.
Release (Student Organization) President (Mar 2017 – Aug 2018) CS student organization for software development at Sogang University. Hosted seminars, hackathons, etc.
Silicon Valley Data Science Program, Sogang University (Aug 2017) Scholarship for one-month data science program in SF Bay Area
Academic Excellence Scholarship, Sogang University (Spring 2017)