Jae-Gil Lee

Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks

References Indeed Matter? Reference-Free Preference Optimization for Conversational Query Reformulation

LLM-based Online Time Series Forecasting with Frequency-driven Pattern Recognition

Plug-and-Play Retrieval-Augmented Active Test-Time Adaptation for VLMs

Active Learning for Continual Learning: Keeping the Past Alive in the Present

Sample-Efficient Multi-Round Generative Data Augmentation for Long-Tail Instance Segmentation

RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language Models

MOUCHI: Mitigating Over-forgetting in Unlearning Copyrighted Information

Active Preference Optimization via Maximizing Learning Capacity

Mobility Networked Time-Series Forecasting Benchmark Datasets