Junqiang Wu — accepted AI-conference papers

2025

MUSE: Multi-Subject Unified Synthesis via Explicit Layout Semantic Expansion

Fei Peng, Junqiang Wu, Yan Li, Tingting Gao, Di Zhang, Huiyuan Fu

ICCV 2025poster

Existing text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images guided by textual prompts. However, achieving multi-subject compositional synthesis with precise spatial control remains a significant challenge. In this work, we address the task of l…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Learning Multi-Dimensional Human Preference for Text-to-Image Generation

Sixian Zhang, Bohan Wang, Junqiang Wu, Yan Li, Tingting Gao, Di Zhang +1

CVPR 2024poster

Current metrics for text-to-image models typically rely on statistical metrics which inadequately represent the real preference of humans. Although recent work attempts to learn these preferences via human annotated images they reduce the rich tapestry of human preference to a single overall score.…

Cited by 24 Source ↗PDF ↗Scholar ↗