drumpt Goto Github PK

I am a machine learning researcher at AITRICS, a healthcare AI startup in South Korea, where I am completing my alternative military service working with Prof. Eunho Yang. Before joining AITRICS, I earned my master’s degree in artificial intelligence from KAIST where I was fortunate to be guided by Prof. Eunho Yang. I also completed my bachelor’s degree in computer science and mathematics at KAIST.

My long-term research goal is to enhance the out-of-distribution generalization capability of machine learning models, thereby creating trustworthy AI systems that can be reliably deployed in new environments. This goal is multidimensional, encompassing ensuring robustness under data distribution shifts (domain adaptation and generalization), handling unseen labels (zero-shot learning), and managing unseen tasks (meta-learning). To this end, during my master’s program, I focused on test-time adaptation to distribution shifts across various tasks, such as 3D point cloud classification, zero-shot classification of vision-language models, automatic speech recognition, and tabular/time series classification. These experiences also enabled myself to adapt quickly to new modalities and tasks, leading to my interest in multimodal learning.

Currently, at AITRICS, my research primarily aims to enhance the generalizability of early prediction models for severe diseases. I am also interested in parameter- and data-efficient adaptation of foundation models, such as diffusion models and multimodal large language models, to downstream tasks. To achieve these goals, I focus on developing practical algorithms that are either empirically well-motivated or theoretically provable. Additionally, I am deeply interested in providing theoretical insights into machine learning models through the lens of probabilistic (Bayesian inference) and statistical (generalization bounds) frameworks.

• Out-of-Distribution Generalization
• Deep Generative Models
• Statistical Learning Theory

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea

• M.S. in Artificial Intelligence, Mar. 2022 – Feb. 2024
• B.S. in Computer Science and Mathematics, Mar. 2017 – Feb. 2022

AITRICS, Seoul, South Korea

• Machine Learning Researcher, Nov. 2023 – Present

KAIST Machine Learning and Intelligence Lab, Daejeon, South Korea

• Master's Student Researcher, Mar. 2022 – Feb. 2024
• Undergraduate Researcher, Jun. 2021 – Feb. 2022

KAIST Applied Artificial Intelligence Lab, Daejeon, South Korea

• Undergraduate Researcher, Nov. 2021 – Jan. 2022

DeepNatural, Seoul, South Korea

• Machine Learning Engineer, Sept. 2020 – Feb. 2021

KAIST Vehicular Intelligence Lab, Daejeon, South Korea

• Undergraduate Researcher, Oct. 2019 – Aug. 2020

Netmarble, Seoul, South Korea

• Data Engineer, Jun. 2019 – Aug. 2019

• Email: [email protected]
• Homepage: https://changhun.kim