Huangji Wang — accepted AI-conference papers

2025

Accelerating Diffusion Sampling via Exploiting Local Transition Coherence

Shangwen Zhu, Han Zhang, Zhantao Yang, Qianyu Peng, Zhao Pu, Huangji Wang +1

ICCV 2025poster

Text-based diffusion models have made significant breakthroughs in generating high-quality images and videos from textual descriptions. However, the lengthy sampling time of the denoising process remains a significant bottleneck in practical applications. Previous methods either ignore the statistic…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

BACON: Improving Clarity of Image Captions via Bag-of-Concept Graphs

Zhantao Yang, Ruili Feng, Keyu Yan, Huangji Wang, Zhicai Wang, Shangwen Zhu +10

CVPR 2025poster

Advancements in large Vision-Language Models have brought precise, accurate image captioning, vital for advancing multi-modal image understanding and processing. Yet these captions often carry lengthy, intertwined contexts that are difficult to parse and frequently overlook essential cues, posing a…

Cited by 0 Source ↗PDF ↗Scholar ↗