Data Intelligence System Lab. (DISL)
Department of Industrial and Systems Engineering & Graduate School of Data Science, KAIST, South Korea
E2 #3110, 291 Daehak-ro, Yuseong-gu, Daejeon, South Korea
Welcome to the DISL Lab. We are dedicated to pioneering advancements in the field of artificial intelligence (AI). Our vision is centered on the pursuit of data-centric approaches that enhance the perofrmance of AI algorithms and systems.
The foundation role of data remains unwavering, even as AI trends evolve rapidly. Our research interests involve making innovations with cutting-edge technologies in various domains, including computer vision (CV) and natural language processing (NLP). Our research scope is expansive and adapts with the advancements in AI. Currently, our primary focus lies in tackling novel challenges in data for natural language generation. Additionally, we are actively exploring data-robust and data-efficient AI modeling, including learning with imperfect data, and AI traning and inference under real-world setup, which encompasses continual learning and online adaptation.
2024년도 2학기 대학원 진학 희망자에 대한 학부 연구생 혹은 석/박사과정 모집합니다. 관심있는 학생은 제게 CV 및 연구 관심사를 메일로 보내주시기 바랍니다.
We are actively seeking PhD and MS students for the year 2024. If you are interested in working with me (ghkswns91 at gmail dot com), please send me your CV and research interests.
News
| Oct 15, 2023 | Two research papers on ‘abstractive summarization’ and ‘early-exiting for autoregressive decoding’ accepted at EMNLP 2023. [Amazon Science Blog] |
|---|---|
| Sep 15, 2023 | A research paper on ‘data pruning under label noise’ accepted at NeurIPS 2023. |
| Jul 15, 2023 | A research paper on ‘domain adaptive prompt for continual learning’ accepted as Oral presentation at ICCV 2023. |
| Apr 15, 2023 | A research paper on ‘time series semi-supervised learning’ accepted at ICML 2023. |
| Feb 15, 2023 | A research paper on ‘federated active learning’ accepted at CVPR 2023. |
| Jan 13, 2023 | A survey paper on ‘data-centric AI’ accepted at VLDB Journal 2023 and another research paper on ‘continual learning’ accepted at ICLR 2023. |