Ruichao Liu — accepted AI-conference papers

2025

FreeAlign: Superior Text-Image Alignment by Modulating Prompt Attention

Yibo Zhang, Dahua Gao, Feng Xie, Minxi Yang, Wenlong Wang, Ruichao Liu

ICASSP 2025accepted

In recent years, Text-to-Image (T2I) models have made remarkable advancements, yet accurate accurate association of attributes remains a key challenge. This paper presents FreeAlign, a novel training-free framework designed to enhance attribute alignment in T2I generation. By modulating attention an…

Cited by 0 Source ↗Scholar ↗

2025

Stable Control Visual AutoRegressive Model: Precise and Efficient Image Generation via Scale Alignment

Feng Xie, Dahua Gao, Ruichao Liu, Minxi Yang, Yibo Zhang, Wenlong Wang

ICASSP 2025accepted

Although diffusion models advance condition-based visual generation, they suffer from speed and cost issues, unlike faster AutoRegressive methods that are limited in performance. To address these, we introduce the Stable Control Visual AutoRegressive Model (SCVAR). SCVAR ensures stable control by al…

Cited by 0 Source ↗Scholar ↗