4 papers
FairT2I: Mitigating Social Bias in Text-to-Image Generation via Large Language Model-Assisted Detection and Attribute Rebalancing
Jinya Sakurai, Yuki Koyama, Issei Sato
Text-to-image (T2I) models have advanced creative content generation, yet their reliance on large uncurated datasets often reproduces societal biases. We present FairT2I, a trainin…
LAPPI: Interactive Optimization with LLM-Assisted Preference-Based Problem Instantiation
So Kuroki, Manami Nakagawa, Shigeo Yoshida +2
Many real-world tasks, such as trip planning or meal planning, can be formulated as combinatorial optimization problems. However, using optimization solvers is difficult for end us…
Constrained Preferential Bayesian Optimization and Its Application in Banner Ad Design
Koki Iwai, Yusuke Kumagae, Yuki Koyama +2
Preferential Bayesian optimization (PBO) is a variant of Bayesian optimization that observes relative preferences (e.g., pairwise comparisons) instead of direct objective values, m…
FontCraft: Multimodal Font Design Using Interactive Bayesian Optimization
Yuki Tatsukawa, I-Chao Shen, Mustafa Doga Dogan +4
Creating new fonts requires a lot of human effort and professional typographic knowledge. Despite the rapid advancements of automatic font generation models, existing methods requi…