Geuntaek Lim

I am a Ph.D. student in Artificial Intelligence at Sejong University, advised by Prof. Yukyung Choi. Recently, I was a research intern at NAVER Cloud.

My research centers on multimodal AI with a particular emphasis on video-centric modeling. My goal is to empower AI systems to assist humans in interpreting complex video content.

Email  /  CV  /  Google Scholar  /  LinkedIn  /  GitHub

profile photo

🎙️ News
  • Aug 21, 2026 A paper about text-video retrieval with Video-LLMs has been accepted to EMNLP 2026, Budapest
  • June 18, 2026 A paper about evaluation of Video-LLMs has been accepted to ECCV 2026, Malmö
  • Oct 27, 2025 I started a research internship at NAVER Cloud's Video Team.
  • Mar 20, 2025 I started a research internship at SNU MPR Lab.'s Video Team.
  • Dec 16, 2024 I successfully completed my Master’s degree defense. 🎓

🔬 Work Experience
Naver Cloud Logo NAVER Cloud, Research Intern
Seongnam, Korea (Oct 2025 - Apr 2026)

Worked on Evaluation of Video-LLMs. (Host: Minho Shim)
SNU Logo SNU MPR Lab., Research Intern
Gwanak-gu, Korea (Mar 2025 - Sep 2025)

Research Intern of Video Understanding (Host: Jonghyun Choi)

đź“š Publications

* indicates equal contribution; † indicates corresponding author.
HypSGG thumbnail HypSGG: Open-Vocabulary Scene Graph Generation via Hyperbolic Representation and Hierarchical Supervision
Geuntaek Lim, Juyoung Hong, Uicheol Jung, Yukyung Choi†

arXiv, 2026

paper  /  code

RTAformer thumbnail Relation-Transition-Aware Transformer for Video Scene Graph Generation
Jaeyeon Heo, Geuntaek Lim, Yukyung Choi†

Asian Conference on Computer Vision (ACCV), 2026

paper  /  code

MARS thumbnail MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval?
Uicheol Jung, Juyoung Hong, Geuntaek Lim, Yukyung Choi†

Empirical Methods in Natural Language Processing (EMNLP), 2026

paper  /  code

Video-Oasis thumbnail Video-Oasis: Rethinking Evaluation of Video Understanding
Geuntaek Lim, Sungjune Park, Jaeyun Lee, Inwoong Lee, Taeoh Kim, Dongyoon Wee, Minho Shim†, Yukyung Choi†

European Conference on Computer Vision (ECCV), 2026

paper  /  code  /  page

PVLR thumbnail Probabilistic Vision-Language Representation for Weakly Supervised Temporal Action Localization
Geuntaek Lim, Hyunwoo Kim, Joonsoo Kim, Yukyung Choi†

ACM International Conference on Multimedia (ACM MM), 2024

paper  /  code

VVS thumbnail VVS: Video-to-Video Retrieval with Irrelevant Frame Suppression
Won Jo, Geuntaek Lim, Gwangjin Lee, Hyunwoo Kim, Byungsoo Ko, Yukyung Choi†

Association for the Advancement of Artificial Intelligence (AAAI), 2024

paper  /  code

IEEE Access thumbnail Simultaneous Video Retrieval and Alignment
Won Jo, Geuntaek Lim, Yujin Hwang, Gwangjin Lee, Joonsoo Kim, Joungil Yun, Jiyoung Jung, Yukyung Choi†

IEEE Access, 2023

paper

IEEE Access CDVA thumbnail Exploring the Temporal Cues to Enhance Video Retrieval on Standardized CDVA
Won Jo, Geuntaek Lim, Joonsoo Kim, Joungil Yun, Yukyung Choi†

IEEE Access, 2022

paper  /  code

🏆 Honors and Awards
  • Doctoral Excellence Scholarship in Science and Engineering
    Korea Student Aid Foundation (KOSAF) — 2026 (US$5,400/year for approximately four years)

Website's source code is referenced from Jon Barron's.