Chiang Tseng — accepted AI-conference papers

2025

Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback

Yi-Lun Wu, Bo-Kai Ruan, Chiang Tseng, Hong-Han Shuai

NeurIPS 2025poster

Direct preference optimization (DPO) methods have shown strong potential in aligning text-to-image diffusion models with human preferences by training on paired comparisons. These methods improve training stability by avoiding the REINFORCE algorithm but still struggle with challenges such as accura…

Cited by 0 Source ↗code ↗Scholar ↗

2024

A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization

Chieh-Yun Chen, Chiang Tseng, Li-Wu Tsao, Hong-Han Shuai

NeurIPS 2024poster

This paper analyzes the impact of causal manner in the text encoder of text-to-image (T2I) diffusion models, which can lead to information bias and loss. Previous works have focused on addressing the issues through the denoising process. However, there is no research discussing how text embedding co…

Cited by 21 Source ↗PDF ↗code ↗Scholar ↗