people
members of the lab or group
555 your office number
123 your address street
Your City, State 12345
layout: about title: About permalink: / subtitle: Ewha Womans University, Seoul, South Korea images: slider: true lightbox2: true photoswipe: true spotlight: true
profile: align: right image: prof_pic.jpg image_circular: false # crops the image to make it circular # more_info: > # <p>555 your office number</p> # <p>123 your address street</p> # <p>Your City, State 12345</p>
selected_papers: true # includes a list of papers marked as “selected={true}” social: true # includes social icons at the bottom of the page
announcements: enabled: true # includes a list of news items scrollable: true # adds a vertical scroll bar if there are more than 3 news items limit: 5 # leave blank to include all the news in the _news folder
latest_posts: enabled: false scrollable: true # adds a vertical scroll bar if there are more than 3 new posts items limit: 3 # leave blank to include all the blog posts —
Hello! Catherine Jeon here. 👋
I am a 2nd-year graduate student at Ewha Womans University in Seoul, pursuing a Master’s degree in Computer Science and Engineering. Currently, I work as a graduate research assistant under the supervision of Prof. S.E. Oh, and as a part-time researcher with Prof. N. Kim at Purdue University. Previously, I worked as an undergraduate research assistant with Prof. S.E. Oh at Ewha Womans University and as a visiting researcher with Prof. M.S. Rahman at the University of Texas at El Paso.
Broadly, I’m dedicated to advancing AI agents that can address real-world challenges and ultimately enhance human life. To achieve this goal, I focus on two core missions:
(1) Developing reliable agents that remain robust and effective under real-world conditions. It is well known that even frontier models can fail dramatically in noisy, out-of-distribution, or concept-drifted environments. This creates the need for AI agents that are not only effective on benchmark datasets, but also robust and dependable in real-world deployment. To this end, I use methodologies such as contrastive learning, metric learning, feature embedding networks, data augmentation, and normalization.
(2) Building practical systems that reduce the computational and data requirements while addressing domain-specific problems. In an era where AI technologies are rapidly scaling up, we often face substantial memory, compute, and data costs, which form a major bottleneck to the accessibility of AI. We can address this problem across the entire AI stack and pipeline, from hardware to software and from dataset construction to model inference. In this line of work, I have explored techniques such as continual learning, generative replay, few-shot learning, and data-efficient learning methods, and have published multiple papers.
Building on my background, I am currently deeply interested in (1) developing (1) developing versatile and robust models and (2) designing efficient models that can simulate our complex, physical real-world.
A few moments of my life! 👩🎓 🏃♀️
555 your office number
123 your address street
Your City, State 12345
layout: about title: About permalink: / subtitle: Ewha Womans University, Seoul, South Korea images: slider: true lightbox2: true photoswipe: true spotlight: true
profile: align: right image: prof_pic.jpg image_circular: false # crops the image to make it circular # more_info: > # <p>555 your office number</p> # <p>123 your address street</p> # <p>Your City, State 12345</p>
selected_papers: true # includes a list of papers marked as “selected={true}” social: true # includes social icons at the bottom of the page
announcements: enabled: true # includes a list of news items scrollable: true # adds a vertical scroll bar if there are more than 3 news items limit: 5 # leave blank to include all the news in the _news folder
latest_posts: enabled: false scrollable: true # adds a vertical scroll bar if there are more than 3 new posts items limit: 3 # leave blank to include all the blog posts —
Hello! Catherine Jeon here. 👋
I am a 2nd-year graduate student at Ewha Womans University in Seoul, pursuing a Master’s degree in Computer Science and Engineering. Currently, I work as a graduate research assistant under the supervision of Prof. S.E. Oh, and as a part-time researcher with Prof. N. Kim at Purdue University. Previously, I worked as an undergraduate research assistant with Prof. S.E. Oh at Ewha Womans University and as a visiting researcher with Prof. M.S. Rahman at the University of Texas at El Paso.
Broadly, I’m dedicated to advancing AI agents that can address real-world challenges and ultimately enhance human life. To achieve this goal, I focus on two core missions:
(1) Developing reliable agents that remain robust and effective under real-world conditions. It is well known that even frontier models can fail dramatically in noisy, out-of-distribution, or concept-drifted environments. This creates the need for AI agents that are not only effective on benchmark datasets, but also robust and dependable in real-world deployment. To this end, I use methodologies such as contrastive learning, metric learning, feature embedding networks, data augmentation, and normalization.
(2) Building practical systems that reduce the computational and data requirements while addressing domain-specific problems. In an era where AI technologies are rapidly scaling up, we often face substantial memory, compute, and data costs, which form a major bottleneck to the accessibility of AI. We can address this problem across the entire AI stack and pipeline, from hardware to software and from dataset construction to model inference. In this line of work, I have explored techniques such as continual learning, generative replay, few-shot learning, and data-efficient learning methods, and have published multiple papers.
Building on my background, I am currently deeply interested in (1) developing (1) developing versatile and robust models and (2) designing efficient models that can simulate our complex, physical real-world.