Trustworthy AI Lab at Korea University
We conduct foundational research to bring AI closer to society
Who we are
The Trustworthy AI Lab at Korea University (or TAIL for short) is a research group led by Prof. Jongheon Jeong in the Department of Artificial Intelligence. Our mission is to make recent developments in AI not only powerful but also trustworthy and reliable, so that they can be more beneficial when integrated with society.
Open positions: I am looking for self-motivated, curiosity-driven graduate students and undergraduate interns to join our lab. Please reach out to me via email with your CV and transcript if you are interested.
What we do
We conduct research on broad areas of AI Safety, especially focusing on ideas and algorithms that are (a) generalizable in the context of out-of-distribution scenarios, and (b) scalable in modern AI systems, such as large language models. Several research questions we address include, but are not limited to, the following:
Robustness: How can a model remain resilient to out-of-distribution, e.g., to unusual events and adversarial attacks?
Monitoring: Is it possible for a model to be sensitive to out-of-distribution, allowing for its detection through the model itself?
Alignment: Can a model be aligned with human expectations in the face of out-of-distribution?
Not only for these topics, we are also broadly interested in advancing foundational areas such as generative modeling and self-supervised learning, as well as other interesting areas in machine learning and deep learning at large.
News
Feb 2024: Our lab's website has just been launched!