Hwanjun Song

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

Quantile-Free Uncertainty Quantification in Graph Neural Networks

Quality of Rejections Matters: Preference Data Construction for Faithful Summarization

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

Reasoning-to-Encoder Distillation for Recommendation

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

ReFeed: Multi-dimensional Summarization Refinement with Reflective Reasoning on Feedback

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

Mobility Networked Time-Series Forecasting Benchmark Datasets