Lune

Profiles2021-2026

Hwanjun Song

Korea Advanced Institute of Science and Technology

17Papers
6Last author
24Unique co-authors
2First author
1Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers17

  1. Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR BenchmarksAuthor 7 of 7ICLR 2026 · 1 citation
  2. Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data PipelinesAuthor 1 of 1ACL Findings 2026
  3. Distilling LLM Reasoning into Dense Encoders: Bridging the Accuracy-Efficiency Gap in RecommendationAuthor 4 of 5ACL Findings 2026
  4. Distilling Long-CoT Reasoning through Collaborative Step-wise Multi-Teacher DecodingAuthor 5 of 5ACL Findings 2026
  5. Towards Multi-dimensional Evaluation of LLM Summarization across Domains and LanguagesAuthor 9 of 9ACL 2025 · 8 citations
  6. Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel IntegrationAuthor 2 of 3EMNLP Findings 2025 · 1 citation
  7. RA-TTA: Retrieval-Augmented Test-Time Adaptation for Vision-Language ModelsAuthor 5 of 7ICLR 2025
  8. Robust Dataset Condensation using Supervised Contrastive LearningAuthor 2 of 2ICCV 2025
  9. Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length ContextsAuthor 8 of 8EMNLP 2025
  10. Word2Passage: Word-level Importance Re-weighting for Query ExpansionAuthor 4 of 5ACL Findings 2025
  11. Breaking the Time-Frequency Granularity Discrepancy in Time-Series Anomaly DetectionAuthor 5 of 7WWW 2024 · 51 citations
  12. Adaptive Shortcut Debiasing for Online Continual LearningAuthor 5 of 6AAAI 2024 · 5 citations
  13. UniSumEval: Towards Unified, Fine-grained, Multi-dimensional Summarization Evaluation for LLMsAuthor 5 of 5EMNLP Findings 2024 · 4 citations
  14. Exploiting Representation Curvature for Boundary Detection in Time SeriesAuthor 3 of 7NeurIPS 2024 · 3 citations
  15. Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent EncodersAuthor 6 of 7ACL 2024
  16. FineSurE: Fine-grained Summarization Evaluation using LLMsAuthor 1 of 5ACL 2024
  17. PREMERE: Meta-Reweighting via Self-Ensembling for Point-of-Interest RecommendationAuthor 2 of 5AAAI 2021 · 15 citations
Dusk over the sea between two cliffs drawn in fine vertical lines