Data Intelligence System Lab (DISLab)
Department of Industrial and Systems Engineering & Graduate School of Data Science, KAIST, South Korea
Welcome to DISLab. We are dedicated to pioneering advancements in the field of artificial intelligence (AI), with a clear focus on data-centric approaches. Rather than relying solely on model optimization, our vision is to enhance the performance, reliability, and trustworthiness of AI systems by improving the data quality, data structure, and data utilization.
Currently, at DISLab, we aim to build trustworthy Agentic AI systems capable of reasoning, acting, and adapting in complex real-world settings. Our research centers around the following key areas:
-
Human-AI Alignment: Aligning large language models (LLMs) with human intent through feedback modeling, preference learning, and evaluation-oriented data design. -
Collaborative Intelligence: Enabling AI agents to make informed decisions by accessing and utilizing external knowledge, such as in retrieval-augmented generation (RAG), with an emphasis on structured and relevant information. -
Data Quality & Robustness: Improving AI performance by focusing on learning from imperfect data, handling noisy or low-resource conditions, and enabling continual and online adaptation in real-world environments. -
Automated Evaluation: Developing scalable automatic evaluation frameworks that reflect human judgment, to assess the outputs and behaviors of generative AI models effectively.
Please refer to the "Join" tab if you are interested in applying for Intern, MS, PhD, or PostDoc positions. We encourage prospective members to complete a 3–6 month internship prior to officially joining the lab.
We are not hiring MS/PhD students for 2026, as all positions are filled. For 2027 Spring, please apply for an internship. Priority will be given to interns from our group.
You can catch up our recent research interest on our Youtube channel.
News
| Jun 26, 2025 |
A paper on Data Condensation with Noisy Labels was accepted at ICCV 2025.
|
|---|---|
| Jun 21, 2025 |
Our two MS students, Yuho Lee and Taewon Yun, successfully passed their MS dissertation defense. Congratulations to both of them!
|
| Jun 14, 2025 |
Hwanjun was nomiated as Area Chair at AAAI 2026 following NeurIPS 2025 and ICLR 2025.
|
| May 23, 2025 |
A paper on LLM-based Recommender was accepted at SIGIR 2025 (GENNEXT Workshop).
|
| May 16, 2025 |
Two paper on LLM benchmarking and RAG retreival were accepted at ACL 2025.
|
| May 16, 2025 |
A paper on a bi-modal learning for time series was accepted in the research track of KDD 2025.
|
| Mar 20, 2025 |
A paper on a time-series benchmark dataset was accepted at ICWSM 2025.
|