5 papers
Let Triggers Control: Frequency-Aware Dropout for Effective Token Control
Junyoung Koh, Hoyeon Moon, Dongha Kim +3
Text-to-image models such as Stable Diffusion have achieved unprecedented levels of high-fidelity visual synthesis. As these models advance, personalization of generative models --…
Quality-Aware Translation Tagging in Multilingual RAG system
Hoyeon Moon, Byeolhee Kim, Nikhil Verma
Multilingual Retrieval-Augmented Generation (mRAG) often retrieves English documents and translates them into the query language for low-resource settings. However, poor translatio…
Test-Time Scaling in Diffusion LLMs via Hidden Semi-Autoregressive Experts
Jihoon Lee, Hoyeon Moon, Kevin Zhai +6
Diffusion-based large language models (dLLMs) are trained flexibly to model extreme dependence in the data distribution; however, how to best utilize this information at inference…
Scalp Diagnostic System With Label-Free Segmentation and Training-Free Image Translation
Youngmin Kim, Saejin Kim, Hoyeon Moon +2
Scalp disorders are highly prevalent worldwide, yet remain underdiagnosed due to limited access to expert evaluation and the high cost of annotation. Although AI-based approaches h…
Illustrious: an Open Advanced Illustration Model
Sang Hyun Park, Jun Young Koh, Junha Lee +5
In this work, we share the insights for achieving state-of-the-art quality in our text-to-image anime image generative model, called Illustrious. To achieve high resolution, dynami…