Jaeyoon Jung

About

Hi, I'm an undergraduate student at Soongsil University and works at MAUM.AI as a senior AI research scientist with a broad interest in artificial intelligence. My current research focuses on several key areas:

Multimodal models capable of handling diverse inputs and outputs (including video, image, text, audio, and action)
Fact-checking using large language and vision-language models
Adapting instruction-following capabilities of English-based large language models to Korean and other languages

Publications

(*: Equal contribution, C: Conferences, J: Journal, W: Workshop, P: Preprint).

2026

[P3][W6] Is a Picture Worth Thousands of Words? Adaptive Agentic Multimodal Fact-Checking with Visual Evidence Necessity

Jaeyoon Jung, Yejun Yoon, Kunwoo Park

Submitted to WWW 2026

Workshop on Human-Centric AI at CIKM, 2025

[P2] Scaling Vision-Action Pretraining on Desktop Data for Transfer to Embodied AI

Suhwan Choi*, Jaeyoon Jung*, Haebin Seong*, Minchan Kim, Minyeong Kim, Yongjun Cho, Yoonshik Kim, Park Yu Been, Youngjae Yu, and Yunsung Lee

Submitted to ICLR 2026

Arxiv Website Code

[P1] Exploring Fine-Tuning of Large Audio Language Models for Spoken Language Understanding under Limited Speech Data

Youngwon Choi, Jaeyoon Jung, Hyeonyu Kim, Huu-Kim Nguyen, Hwayeon Kim

Submitted to ICASSP 2026

Arxiv

2025

[W5] Team HUMANE at AVeriTeC 2025: HerO 2 for Efficient Fact Verification

Yejun Yoon, Jaeyoon Jung, Seunghyun Yoon, Kunwoo Park

Eighth Workshop on Fact Extraction and VERification (FEVER) at ACL, 2025

Arxiv Code

[C3] Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion

Yejun Yoon, Jaeyoon Jung, Seunghyun Yoon, Kunwoo Park

Findings of the Association for Computational Linguistics (ACL Findings), 2025

Arxiv

[W4] KOFFVQA: An Objectively Evaluated Free-form VQA Benchmark for Large Vision-Language Models in the Korean Language

Yoonshik Kim*, Jaeyoon Jung*

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025

Arxiv Website Code Data

[C2][W3] CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction

Suhwan Choi*, Yongjun Cho*, Minchan Kim*, Jaeyoon Jung*, Myunchul Joe, Yubeen Park, Minseo Kim, Sungwoong Kim, Sungjae Lee, Hwiseong Park, Jiwan Chung, Youngjae Yu

International Conference on Robotics and Automation (ICRA), 2025

Workshop on Open-World Agents at NeurIPS, 2024, (Oral, Outstanding Paper Award (3/97 = 3.1%))

Arxiv Website Code Data

2024

[W2] The Herd of Open LLMs for Verifying Real-World Claims

Yejun Yoon*, Jaeyoon Jung*, Seunghyun Yoon, Kunwoo Park

Seventh Workshop on Fact Extraction and VERification (FEVER) at EMNLP, 2024, (Oral)

Arxiv Code

[W1] EnCLAP++: Analyzing the EnCLAP Framework for Optimizing Automated Audio Captioning Performance

Jaeyeon Kim, Minjeon Jeon, Jaeyoon Jung, Sang Hoon Woo, Jinjoo Lee

Detection and Classification of Acoustic Scenes and Events (DCASE) Workshop, 2024

Arxiv

[C1] EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning

Jaeyeon Kim, Jaeyoon Jung, Jinjoo Lee, Sang Hoon Woo

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024

Arxiv Code

Education

Soongsil University Mar. 2020 - Feb. 2026

B.S. in Artificial Intelligence GPA: 4.19/4.5, currently 2nd/100

includes a 2-year mandatory alternative military service at MAUM.AI

Awards

AVeriTeC shared task hosted by the eight FEVER workshop at ACL 2025, 2nd Place May 2025

AVeriTeC shared task hosted by the seventh FEVER workshop at EMNLP 2024, 2nd Place August 2024

Detection and Classification of Acoustic Scenes and Events 2024 Challenge, 2nd Place June 2024

NeurIPS 2024 - Open World Agent Workshop, Outstanding Paper Award December 2024

LG Display Product Quality Classification (LG Aimers 2), 1st Place March 2023

Samsung AI Challenge (3D Metrology), 1st Place October 2022

LG Innotek Radar Performance Prediction (LG Aimers 1), 2nd Place September 2022

Vitæ

Full Resume in PDF.

HUMANE LAB @ SSU AI June 2023 - now

Research Student (Advised by Prof. Kunwoo Park)
Work for building automated fact-checking for both using only text and multi-modal
MAUM.AI Dec. 2024 - now

Senior AI Research Scientist
Working on WoRV team to build a End-to-End Vision-Language Action model to drive or act like human.
Collaborating with SNU PI Lab, led by Prof. Youngjae Yu.
MAUM.AI Apr. 2023 - Nov. 2024

AI Research Scientist
Worked on transferring instruction-following capabilities from English to Korean in open-source large language models. This work aims to facilitate the development of high-quality Korean language models at a low cost.
Soongsil University Mar. 2020 - Feb. 2026

B.S. in Artificial Intelligence