Taehong Moon
AI Researcher
KRAFTON
josephmoon2019 [AT] gmail.com
About
I am a deep learning researcher at KRAFTON, specializing in generative models for gaming applications. My work focuses on optimizing the efficient inference of generative model and designing expressive generative models that are practical for real-world scenarios. I aim to bridge the gap between cutting-edge AI research and its deployment, enabling impactful applications across diverse domains.
Publications
(*: Equal contribution)
Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
Jaehyeon Kim*, Taehong Moon*, Keon Lee, Jaewoong Cho
Preprint, 2024
Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
Dongmin Park, Sebin Kim, Taehong Moon, Minkyu Kim, Kangwook Lee, Jaewoong Cho
International Conference on Learning Representations (ICLR),2025
A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
Taehong Moon, Moonseok Choi, Eunggu Yun, Jongmin Yoon, Gayoung Lee, Jaewoong Cho, Juho Lee
International Conference on Machine Learning (ICML), 2024
HyperCLOVA X Technical Report
HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture
Early Exiting for Accelerated Inference in Diffusion Models
Taehong Moon, Moonseok Choi, Eunggu Yun, Jongmin Yoon, Gayoung Lee, Juho Lee
ICML Workshop on Structured Probabilistic Inference & Generative Modeling, 2023
Fine-tuning Diffusion Models with Limited Data
Taehong Moon, Moonseok Choi, Gayoung Lee, Jung-Woo Ha, Juho Lee
NeurIPS Workshop on Score-Based Methods, 2022
Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
Jaehyeon Kim*, Taehong Moon*, Keon Lee, Jaewoong Cho
Preprint, 2024
Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
Dongmin Park, Sebin Kim, Taehong Moon, Minkyu Kim, Kangwook Lee, Jaewoong Cho
International Conference on Learning Representations (ICLR),2025
A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
Taehong Moon, Moonseok Choi, Eunggu Yun, Jongmin Yoon, Gayoung Lee, Jaewoong Cho, Juho Lee
International Conference on Machine Learning (ICML), 2024
HyperCLOVA X Technical Report
HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture
Early Exiting for Accelerated Inference in Diffusion Models
Taehong Moon, Moonseok Choi, Eunggu Yun, Jongmin Yoon, Gayoung Lee, Juho Lee
ICML Workshop on Structured Probabilistic Inference & Generative Modeling, 2023
Fine-tuning Diffusion Models with Limited Data
Taehong Moon, Moonseok Choi, Gayoung Lee, Jung-Woo Ha, Juho Lee
NeurIPS Workshop on Score-Based Methods, 2022
Education
Korea Advanced Institute of Science and Technology (KAIST)
M.S. in Artificial IntelligenceSep. 2021 - Aug. 2023
Seoul National University (SNU)
B.S. in Industrial EngineeringMar. 2015 - Aug. 2021
Experience
KraftonNov. 2023 - Present
Deep Learning Research Engineer
Naver CloudJune. 2023 - Oct. 2023
Machine Learning Engineer Intern
HyperconnectJuly. 2020 - Aug. 2020
Machine Learning Research Intern
Seoul National University (SNU)Jan. 2020 - June. 2020
UROP program, hosted by Prof. U Kang
Academic Services
Conference Reviewer ICLR
Workshop Reviewer SPIGM@ICML