activity
20242026
collaborators

5 papers

cs.CV2026

TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Models

Teng-Fang Hsiao, Bo-Kai Ruan, Yi-Lun Wu +2

Text-and-Image-To-Image (TI2I), an extension of Text-To-Image (T2I), integrates image inputs with textual instructions to enhance image generation. Existing methods often partially…

cs.AI2026

HyCE-RAG: Hypergraph Chain-of-Evidence Retrieval-Augmented Generation for Explainable Multi-hop Question Answering

Hong-Yu An, Yun-Jian Zhang, Chen-Wei Liang +7

Multi-hop question answering requires systems to retrieve evidence from multiple documents and connect scattered facts into a coherent reasoning process. Standard retrieval-augment…

cs.CV2025

PromptMoG: Enhancing Diversity in Long-Prompt Image Generation via Prompt Embedding Mixture-of-Gaussian Sampling

Bo-Kai Ruan, Teng-Fang Hsiao, Ling Lo +2

Recent advances in text-to-image (T2I) generation have achieved remarkable visual outcomes through large-scale rectified flow models. However, how these models behave under long pr…

cs.CV2025

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

Yi-Lun Wu, Bo-Kai Ruan, Chiang Tseng +1

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…

cs.CV2024

FreeCond: Free Lunch in the Input Conditions of Text-Guided Inpainting

Teng-Fang Hsiao, Bo-Kai Ruan, Sung-Lin Tsai +2

In this study, we aim to determine and solve the deficiency of Stable Diffusion Inpainting (SDI) in following the instruction of both prompt and mask. Due to the training bias from…