Young-Jun Lee

Research Interests

• Robust Reasoning Model

• Open-domain Dialogue System (Empathetic Dialogue, Personalized Dialogue)

• Multi-Turn Interaction

• Large Language and Vision Model

Work Experience

• Amazon AGI Applied Scientist Intern (from July 7th to Oct. 10th)

Recent News

June 2025 1 paper has been accepted to ICCV 2025 🎉

Oct. 2024 2 paper has been released (IP-LLVM & Thanos)

Sep. 2024 2 papers have been accepted to EMNLP 2024 🎉

Publications (C: Conference / W: Workshop (archival) / J: Journal / P: Preprint / *: Equal Contribution)

• [P] RefineBench: Evaluating Refinement Capability in Language Models

  • Young-Jun Lee*, Seungone Kim*, Byung-Kwan Lee, Minkyeong Moon, Yechan Hwang, Jong Myoung Kim, Graham Neubig, Sean Welleck, Ho-Jin Choi

  • under review

• [C11] MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models

  • Young-Jun Lee, Byung-Kwan Lee, Jianshu Zhang, Yechan Hwang, Byungsoo Ko, Han-Gyu Kim, Dongyu Yao, Xuankun Rong, Eojin Joo, Seung-Ho Han, Bowon Ko, Ho-Jin Choi

  • ICCV 2025

• [P] Thanos: Enhancing Conversational Agents with Skill-of-Mind-Infused Large Language Model [paper] [code] [dataset] [model]

  • Young-Jun Lee, Byung-Kwan Lee, Dokyong Lee, junyoung youn, Kyeong-Jin Oh, Yechan Hwang, Ho-Jin Choi

  • Under Review

• [P] Intriguing Properties of Large Language and Vision Models [paper] [code]

  • Young-Jun Lee, Byungsoo Ko, Han-Gyu Kim, Yechan Hwang, Ho-Jin Choi

  • Under Review

• [C10] Stark: Social Long-Term Multi-Modal Conversation with Persona Commonsense Knowledge [paper] [code] [dataset] [model]

  • Young-Jun Lee, Dokyong Lee, Junyoung Youn, Kyeongjin Oh, Byungsoo Ko, Jonghwan Hyeon, Ho-Jin Choi

  • EMNLP 2024 (long, findings)

• [C9] Enhancing Arguments Recognition for Financial Mathematical Reasoning over Hybrid Data [paper] [code] [dataset]

  • Jinsu Lim, Yechan Hwang, Young-Jun Lee, Ho-Jin Choi

  • EMNLP 2024 (long, findings)

• [C8] Does Incomplete Syntax Influence Korean Language Model? Focusing on Word Order and Case Markers [paper] [code] [dataset]

  • Jong Myoung Kim, Young-Jun Lee, Yong-jin Han, Sangkeun Jung, Ho-Jin Choi

  • COLM 2024

• [C7] Large Language Models can Share Images, Too! [paper] [code] [dataset]

  • Young-Jun Lee, Dokyong Lee, Joo Won Sung, Jonghwan Hyeon, Ho-Jin Choi

  • Neural Conversational AI Workshop - What’s left to TEACH (Trustworthy, Enhanced, Adaptable, Capable and Human-centric) chatbots? on ICML 2023

  • ACL 2024 (long, findings)

• [C6] DialogCC: An Automated Pipeline for Creating High-Quality Multi-Modal Dialogue Dataset [paper] [code] [dataset]

  • Young-Jun Lee, Byungsoo Ko, Han-Gyu Kim, Jonghwan Hyeon, Ho-Jin Choi

  • NAACL 2024 (long, main)

  • Instruction Workshop @ NeurIPS 2023

• [J1] Improving speech emotion recognition by fusing self-supervised learning and spectral features via mixture of experts [paper]

  • Jonghwan Hyeon, Yung-Hwan Oh, Young-Jun Lee, Ho-Jin Choi

  • Data & Knowledge Engineering (DKE) 

• [W3] Augmentation for Context in Financial Numerical Reasoning over Textual and Tabular Data with Large-Scale Language Model

  • Yechan Hwang*, Jinsu Lim*, Young-Jun Lee, Ho-Jin Choi

  • Table Representation Learning (TRL) Workshop @ NeurIPS 2023

• [W2] Let's Put Speaker into Interlocutor's Shoes! Exploring the Impact of Zero-Shot Chain-of-Thought on Empathy

  • Young-Jun Lee, Dokyong Lee, Jihui Im, Joo Won Sung, Ho-Jin Choi

  • Instruction Workshop @ NeurIPS 2023

• [C5] A Simple Debiasing Framework for Out-of-Distribution Detection in Human Action Recognition [paper] [code] [poster]

  • Minho Sim, Young-Jun Lee, Dongkun Lee, Jongwhoa Lee, Ho-Jin Choi

  • 26th European Conference on Artificial Intelligence (ECAI 2023)

• [C4] Semantic Ambiguity Detection in Sentence Classification using Task-Specific Embeddings [paper]

  • Jong Myoung Kim, Young-Jun Lee, Sangkeun Jung, Ho-Jin Choi

  • ACL 2023 Industry Track

  • For Adot Service

• [C3] Does GPT-3 Generate Empathetic Dialogues? A Novel In-Context Example Selection Method and Automatic Evaluation Metric for Empathetic Dialogue Generation [paper] [code] [slide] [poster]

  • Young-Jun Lee, Chae-Gyun Lim, Ho-Jin-Choi

  • International Conference on Computational Linguistics (COLING) 2022

• [W1] PersonaChatGen: Generating Personalized Dialogues using GPT-3 [paper] [code] [slide] [dataset]

  • Young-Jun Lee, Chae-Gyun Lim, Yunsu Choi, Ji-Hui Lm, Ho-Jin-Choi

  • CCGPK Workshop on Computational Linguistics (COLING) 2022

  • Best Paper Award

• [C2] Korean-Specific Emotion Annotation Procedure Using N-Gram-Based Distant Supervision and Korean-Specific-Feature-Based Distant Supervision [paper] [code]

  • Young-Jun Lee, Chae-Gyun Lim, Ho-Jin-Choi

  • Language Resources and Evaluation Conference (LREC) 2020

• [C1] Deep learning based response generation using emotion feature extraction [paper]

  • Young-Jun Lee, Ho-Jin-Choi

  • IEEE International Conference on Big Data and Smart Computing (BigComp) 2020

  • Best Paper Award 1st

Honors & Awards

• Outstanding Paper Award, HCLT 2023 Oct. 2023

• Best Paper Award, CCGPK Workshop on COLING 2022 Oct. 2022

• Best Paper Award (1st), IEEE BigComp 2020 Feb. 2020

• Dean’s list scholarship for Academic Excellence, SKKU Nov. 2014

Education

• Ph.D. student, School of Computing at Korea Advanced Institute of Science & Technology (KAIST) Sep. 2019 - Present

• Master’s degree, School of Computing at Korea Advanced Institute of Science & Technology (KAIST) Aug. 2017 - Aug. 2019

• Bachelor’s degree, Software Department at Sungkyunkwan University (SKKU) Mar. 2013 - June. 2017