I’m a third-year Ph.D. student in GSAI (Graduate School of Artificial Intelligence) at POSTECH Efficient Learning Lab (EffL), advised by Prof. Jaeho Lee. Before joining POSTECH, I completed my B.S. degree in software convergence from KyungHee University (KHU).
I am broadly interested in evaluation and benchmarking for multimodal AI systems, particularly in understanding how language models reason about knowledge grounded in other modalities. My recent work focuses on building diagnostic benchmarks that reveal capability gaps in modern models, as well as developing efficient benchmark selection methods that preserve evaluation while reducing dataset scale.
(* means ‘equal contribution’)
TempCore: Are Video QA Benchmarks Temporally Grounded? A Frame Selection Sensitivity Analysis and Benchmark
Hyunjong Ok, Jaeho Lee
EMNLP, 2026
Speculative End-Turn Detector for Efficient Speech Chatbot Assistant
Hyunjong Ok, Suho Yoo, Jaeho Lee
ACL, 2026
Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models
Hyunjong Ok, Jaeho Lee
ACL Findings, 2026
AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?
Hyunjong Ok*, Suho Yoo*, Hyeonjun Kim, Jaeho Lee
ICASSP (Oral), 2026
Decoding with Limited Teacher Supervision Requires Understanding When to Trust the Teacher
Hyunjong Ok, Jegwang Ryu, Jaeho Lee
EMNLP, 2024
SCANNER: Knowledge-Enhanced Approach for Robust Multi-modal Named Entity Recognition of Unseen Entities
Hyunjong Ok, Taeho Kil, Sukmin Seo, Jaeho Lee
NAACL, 2024
Hierarchical Compression of Vision-Language Model Benchmarks
Hyunjong Ok, Seunggu Kang, Jaeho Lee
arXiv preprint, 2026
OmniKVQuant: KV Cache Quantization for Omni-LLMs
Suho Yoo*, Hyunjong Ok*, Jongmin Choi, Jihoo Jung, Joon Son Chung
arXiv preprint, 2026
TempCore: Are Video QA Benchmarks Temporally Grounded? A Frame Selection Sensitivity Analysis and Benchmark
Hyunjong Ok, Jaeho Lee
EMNLP, 2026
Speculative End-Turn Detector for Efficient Speech Chatbot Assistant
Hyunjong Ok, Suho Yoo, Jaeho Lee
ACL, 2026
Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models
Hyunjong Ok, Jaeho Lee
ACL Findings, 2026
AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?
Hyunjong Ok*, Suho Yoo*, Hyeonjun Kim, Jaeho Lee
ICASSP (Oral), 2026
Understanding the Effects of Distractors on Reasoning Vision-Language Models
Jiyun Bae, Hyunjong Ok, Sangwoo Mo, Jaeho Lee
EMNLP, 2026
S2Cap: A Benchmark and a Baseline for Singing Style Captioning
Hyunjong Ok, Jaeho Lee
CIKM (Resource Paper), 2025
Imagine to Hear: Auditory Knowledge Generation Can Be an Effective Assistant for Language Models
Suho Yoo*, Hyunjong Ok*, Jaeho Lee
ACL Findings, 2025
AudioBERT: Audio Knowledge Augmented Language Model
Hyunjong Ok*, Suho Yoo*, Jaeho Lee
ICASSP, 2025
Decoding with Limited Teacher Supervision Requires Understanding When to Trust the Teacher
Hyunjong Ok, Jegwang Ryu, Jaeho Lee
EMNLP, 2024
SCANNER: Knowledge-Enhanced Approach for Robust Multi-modal Named Entity Recognition of Unseen Entities
Hyunjong Ok, Taeho Kil, Sukmin Seo, Jaeho Lee
NAACL, 2024
Post-Trained Language Model Adaptive to Extractive Summarization of Long Spoken Documents
Hyunjong Ok, Seong-Bae Park
ICASSP (Grand Challenge), 2023
FinTree: Financial Dataset Pretrain Transformer Encoder for Relation Extraction
Hyunjong Ok
SIGIR Workshop on Knowledge Discovery from Unstructured Data in Financial Services, 2023
AI Research Engineer Intern, Upstage, Dec 2025 – May 2026
Data-efficient VLM evaluation methods that preserve model rankings while substantially reducing benchmark scale.
AI Research Engineer Intern, Naver Cloud, Mar 2023 – Sep 2023
OCR post-processing for document-AI pipelines and knowledge-enhanced multimodal NER (SCANNER, NAACL 2024).
Undergraduate Researcher, NLP Lab, Kyung Hee University, Mar 2022 – Feb 2023
Data Engineer Intern, Ingkle, Nov 2021 – Feb 2022
Soseon Sharing Fund Scholarship (Science and Technology), Community Chest of Korea, Daegu Branch, Sep 2026
3·1 Scholarship, The 3·1 Foundation, Aug 2026
Ph.D. Excellence Scholarship (Science and Engineering), Korea Student Aid Foundation, Jun 2026
ICASSP 2023 MUG Grand Challenge, Track 2: Extractive Text Summarization (1st Place)
Alibaba Cloud, Feb 2023
SIGIR 2023 KDF Workshop Shared Task: Relation Extraction (2nd Place)
J.P. Morgan AI Research, Jun 2023
Kaggle Competitions (two Silver medals and one Bronze medal)
Feedback Prize – Evaluating Student Writing (Silver, Mar 2022); CommonLit – Evaluate Student Summaries (Silver, Oct 2023); KORE 2022 (Bronze, Jul 2022)
The 12th Conference of the Korean Artificial Intelligence Association, CKAIA (Outstanding Paper Award)
Korean Artificial Intelligence Association, Aug 2025
The 11th Joint Conference of the Korean Artificial Intelligence Association, JKAIA (Outstanding Paper Award)
Korean Artificial Intelligence Association, Nov 2024
National Defense AI Challenge (4th Place)
Korea Ministry of National Defense, Dec 2023
Korean AI Challenge: ASR Track (4th Place)
Korea Ministry of Science and ICT, Nov 2023
Korean AI Challenge: ASR Track (1st Place: Minister’s Award)
Korea Ministry of Science and ICT, Oct 2022
Legal Judgment Prediction Challenge: Text Classification (1st Place)
Law & Company, Dec 2022
Genome EC Number Classification AI Challenge (2nd Place)
Infoboss, Dec 2022
Sentence Type Classification AI Challenge (4th Place)
Sungkyunkwan University, Dec 2022
Suho Yoo, M.S. student at KAIST, Aug 2024 – Sep 2025
Research mentoring leading to publications at ICASSP 2025 and ACL Findings 2025.
Conference Reviewer: ACL Rolling Review (ARR), NeurIPS, CIKM