← Search

Xinlong Jiang

2 accepted papers

2025

Mitigating Pervasive Modality Absence Through Multimodal Generalization and Refinement

AAAI 2025technical

The performance of multimodal models often deteriorates when modality absence occurs. The absence disrupts the learned inter-modal correlations, resulting in biased multimodal representations. This challenge is especially pronounced when the absence is pervasive, affecting both the training and infe…

Cited by 0SourcePDFScholar
2025

VersaFusion: A Versatile Diffusion-Based Framework for Fine-Grained Image Editing and Enhancement

AAAI 2025technical

Text-to-image (T2I) diffusion models have achieved remarkable progress in generating realistic images from textual descriptions. However, ensuring consistent high-quality image generation with complete backgrounds, object appearance, and optimal texture rendering remains challenging. This paper pres…