Deokjae Lee

I am a fourth-year Ph.D. student in Computer Science and Engineering at Seoul National University, advised by Hyun Oh Song. I previously graduated from Seoul National University in 2020 with a B.S. in Mathematical Science. My research interests are combinatorial optimization and efficient machine learning. Also, I’m interested in natural language processing (NLP) and reinforcement learning (RL). I am visiting Prof. Kyunghyun Cho's group at New York University (NYU) from 2023/09 to 2024/02, working on active learning algorithms for combinatorial problems.

Email  /  Google Scholar  /  Github

profile photo
Efficient Latency-Aware CNN Depth Compression via Two-Stage Dynamic Programming
Jinuk Kim*, Yeonwoo Jeong*, Deokjae Lee, Hyun Oh Song
International Conference on Machine Learning (ICML), 2023
paper / code / bibtex

We propose a subset selection optimization problem for depth compression which can be efficiently solved via two-stage dynamic programming.

Query-Efficient Black-Box Red Teaming via Bayesian Optimization
Deokjae Lee, JunYeong Lee, Jung-Woo Ha, Jin-Hwa Kim, Sang-Woo Lee, Hwaran Lee, Hyun Oh Song
Annual Meeting of the Association for Computational Linguistics (ACL), 2023
paper / poster / code / bibtex

We propose a novel query-efficient red teaming method, namely Bayesian red teaming (BRT), which identifies failures of black-box generative models by choosing and editing user inputs with GP surrogate models.

Query-Efficient and Scalable Black-Box Adversarial Attacks on Discrete Sequential Data via Bayesian Optimization
Deokjae Lee, Seungyong Moon, Junhyeok Lee, Hyun Oh Song
International Conference on Machine Learning (ICML), 2022
paper / poster / code / bibtex

Crafting adversarial examples against language models is challenging due to its discrete nature and dynamic input size. We tackle these problems using Bayesian optimization and develop a query-efficient black-bax adversarial attack against various types of models.

Optimal channel selection with discrete QCQP
Yeonwoo Jeong*, Deokjae Lee*, Gaon An, Changyong Son, Hyun Oh Song
International Conference on Artificial Intelligence and Statistics (AISTATS), 2022
paper / code / bibtex

We propose a novel channel selection method that optimally selects channels via discrete QCQP, which provably prevents any inactive weights and guarantees to meet the resource constraints tightly in terms of FLOPs, memory usage, and network size.

Work Experience
  • Research Intern, DeepMetrics, Jul 2023 - Sep 2023
Teaching Experience
  • Teaching Assistant, Introduction to Deep Learning (M2177.0043), Spring 2023
  • Teaching Assistant, Machine Learning (4190.666), Fall 2020
  • Undergraduate Student Instructor, Basic Calculus 2 (033.017), Fall 2017
  • Undergraduate Student Instructor, Basic Calculus 1 (033.016), Spring 2017
Honors and Awards
  • Yulchon AI Star Scholarship, 2023
  • University Mathematics Competition, Field 1 Silver medal, from Korean (2019)
  • National Science & Technology Scholarship, (2018. 03. - 2020. 02.)
Academic Services
  • Conference Reviewer: NeurIPS (2022, 2023), ICML (2023), ACL (2023), EMNLP (2023), ICLR (2024)

This website is modified from here.