• Writing Code Since 2016
• Deep Learning & Tech Lover Since 2015

Main: Multimodal LM / Human-Centric AI Eval & Application
Side: Specialty Coffee / Video Games / Drum

HiKE: Hierarchical Evaluation Framework for Korean-English Code-Switching Speech Recognition
G. Paik*, Y. Kim, S. Lee, S. Ahn†, and C. Kim†, EACL Findings 2026 (arxiv)
#STT #Benchmark #Code-Switching

Towards Truly Multilingual ASR: Generalizing Code-Switching ASR to Unseen Language Pairs
G. Paik*†, H. Shin†, S. Lee, ICML 2026 Workshop on Machine Learning for Audio (arxiv)
#STT #Code-Switching #Domain-Generalization

MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Models
G. Paik, G. Kim and J. Im*, ACL Findings 2025 (arxiv)
#VLM #Reasoning #Benchmark #LLM-as-a-judge

Improving Fine-grained Visual Understanding in VLMs through Text-Only Training
D. Choi, G. Son, S. Kim, G. Paik, and S. Hong, AAAI Workshop 2025 (arxiv)
#VLM #Alignment

(* Corresponding Author, † Equal Contribution)

• ML Research Engineer at Theta One (2025年02月17日 ~ )
• Research Intern at Vision Understanding Team, NAVER CLOUD (2024年07月15日 ~ 2025年01月10日)
• Undergrad. Researcher at Sejong Robotics and Computer Vision Lab (2023年01月03日 ~ 2024年04月05日)
• Software Specialist at ISMG, Republic of Korea Air Force (2021年03月15日 ~ 2022年12月14日)