Welcome to the Data Systems Lab (Big Data Lab) at the POSTECH. Our data systems lab focuses on STAR (namely, Systems, Theory, and ARtificial intelligence) supported by major grants such as Star Lab. We have been endeavoring to solve challenging and real problems in computer/data science.
[Big News] Our lab has been awarded over $6 million USD for the Global AI Frontier Lab between Korea and NYU. I am the director of this international program, which includes 8 additional professors from KAIST and Sungkyunkwan University. Many of our students will be dispatched to NYU each year to collaborate with world-leading researchers.
We work at the intersection of data systems and natural language processing (NLP), with a team spanning systems researchers, AI scientists and AI engineers.
● Data AI & Multi-Modal RAG
We develop data-centric and knowledge-graph-based techniques and apply large multi-modal models across text, tabular, image, and other data types.
Short term: advanced analytics/processing systems and a fast, trustworthy multi-modal RAG stack.
Long term: a cost-efficient, data-centric platform that steadily progresses toward AGI-level capabilities.
● AI Database & Semantic Predicates
We design and implement AI-native databases that treat semantic predicates, vector search, and knowledge-graph reasoning as first-class query operators across text, tabular, time-series, image, and log data, while addressing ambiguity, reliability, and cost-modeling challenges.
Short term: robust semantic filtering and multi-modal query processing with clear performance guarantees and explainable behavior.
Long term: a self-optimizing, AI-native data platform where learned operators, RAG, and agents are deeply integrated into storage, indexing, and query processing on the path toward AGI-level data systems.
● Natural Language Interfaces to Data
We’re building conversational database interfaces, letting users query and reason over data using natural language—marrying robust data-system backends with cutting-edge NLP.
● Self-Optimizing Data Systems
Our systems auto-adapt to workload and data distribution, delivering top performance without manual tuning, via AI-driven optimization and continuous feedback.
We are currently hiring interns (연구 참여학생 모집). This is an amazing opportunity for undergrads to experience world-class research in Big Data and prepare for possible graduate school applications. You could be a rising-STAR of the future if you stand out in our field.
We are proud of strong publication records in top database venues such as having presented 24 papers at SIGMOD/VLDB/PODS/ICDE between 2019 and 2024, significantly contributing to make the Korean database community one of the strongest communities worldwide. Many of our alumni work for top notch companies including Facebook, Oracle, SAP, Microsoft, and Amazon. We have been closely collaborating with Oracle Labs and SAP for many years.
We heartily welcome Sunho Cha to our lab. He graduated with the highest distinction from POSTECH.
November 16, 2025Announcing 2025 winter intern recruitment for KG-based What-If Analysis, AI Scientists, Graph RAG, and Multi-Modal Data QA.
September 1, 2025We heartily welcome Jueun Kim to our lab. She graduated with the highest distinction from POSTECH.
August 21, 2025All three submissions to EMNLP 2025 have been accepted to the main conference (1 oral presentation, 2 posters).
July 18, 2025Professor Han has been named a POSTECH Distinguished Professor at POSTECH in recognition of his groundbreaking work on large-scale graph database technologies, a distinction that extends his tenure eligibility to the age of 70.
May 16, 2025Our first submission to ACL is accepted. HELIOS achieves SOTA performance in RAG.
HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text Retrieval
Our alumnus, Dr. Doyup Lee, is a key contributor to Runway’s Gen-4 model, leading advancements in AI-driven media generation with consistent and controllable video synthesis.
https://runwayml.com/research/
introducing-runway-gen-4
Professor Han will serve as a general co-chair for SIGMOD 2028, marking the first time SIGMOD will be hosted in Seoul, Korea!
October 16, 2024One paper is accepted to VLDB 2025.
