Data Science Lab
Data Science Lab
The CAU Data Science Lab develops end-to-end large scale machine learning pipelines for solving real-world problems. We solve challenging problems and make significant impacts in social media and network analysis, security, health care, and fair-AI.
대학원 (석사, 박사) 과정 및 학부연구생 모집 (26년 5월 6일~on going)
sLLM 경량화 (경량형 멀티모달 파운데이션 모델(sLLM) 기반 산업융합 서비스 기술개발을 통한 생성 AI 전문인력 양성, IITP) (5월 13일 1차 지원 마감)
LLM-Guard (기업 과제 연계, 5월 29일 지원 마감)
3D Point cloud Processing (기업 과제 연계, 5월 22일 지원 마감)
2026
[Apr] Our paper 'Capacity without Access: Reinterpreting the Mid-Depth Spectral Plateau in LLMs' has been accepted to ICML.
[Apr] Our review paper 'Conversational Recommender Systems with Large Language Models: A Review of Current Developments' has been accepted for publication.
[Apr] Our paper 'Reformulating Post-Training as Matrix Factorization for Joint Embedding Refinement' has been accepted to SIGIR.
[Jan] Our paper 'Boltzmann Exploration for Heavy-Tailed Bandits' has been accepted to AISTATS.
[Nov] Our paper 'ARROW: Adaptive Reasoning for LLM-based Recommendation with Explainability' has been accepted to WSDM (short paper track).
[Sep] Our paper 'APT : A Two-stage Image-Video Transfer Learning for Video Retrieval' has been accepted to IEEE Transactions on Multimedia.
[Sep] Jiho Park and Kiwhan Ko joined Data Science Lab!
[Aug] Our paper 'GRIT: Guided Relational Integration for Efficient Multi-Table Understanding' has been accepted to EMNLP 2025 Main.
[Aug] Our paper 'Can Personal Health Information Be Secured in LLM? Privacy Attack and Defense in the Medical Domain' has been accepted to ACM CCS 2025. Our lab's first paper in security!
[Jul] Our paper 'Rethinking Overconfidence in VAEs: Can Label Smoothing Help?' has been accepted to RecSys'25.
[Mar] Myungbin Gwak, Seora Lee joined our Data Science Lab!
[Jan] Our paper 'Leveraging Refined Negative Feedback with LLM for Recommender Systems' has been accepted to WWW'25 (short paper track).
Our paper 'Beyond Single Emotion: Multi-label Approach to Conversational Emotion Recognition' has been accepted to AAAI'25
(selected for oral presentation on March 2nd)
Our paper 'Efficient Text Augmentation in Latent Space for Video Retrieval' has been accepted to Multimedia Tools and Applications
Eunsun Kim joined our Data Science Lab!
Our paper 'Decoupled Variational Graph Autoencoder for Link Prediction' has been accepted to WWW'24
(selected for oral presentation)
Our paper 'Improving Contrastive Learning in Emotion Recognition in Conversation via Data Augmentation and Decoupled Neutral Emotion' has been accepted to EACL'24
- oral presentation on March 18th by Yujin Kang 🎉
Chanwoo Jung, Nahyun Lee, Wooseong Yun joined Data Science Lab!
Our paper 'Approaching feature matrix: To solve two issues in link prediction' has been accepted to Expert Systems With Applications (ESWA)
Our paper 'MEME:Multi-Encoder Multi-Expert Framework with Data Augmentation for Video Retrieval' has been accepted to SIGIR'23
Our paper 'Video Retrieval with Tree-based Video Segmentation' has been accepted to Database Systems for Advanced Applications (DASFAA 2023)
Our paper 'Application of fairness to healthcare, organizational justice, and finance: A survey' has been accepted to Expert Systems With Applications (ESWA)
Our paper 'Positional Obstructive Sleep Apnea in Patients with Atrial Fibrillation' has been accepted to Sleep and Breathing
Our paper 'Stochastic-Expert Variational Autoencoder for Collaborative Filtering' has been accepted to TheWebConf 2022 (WWW 2022)