3 papers
cs.MM2025
How Far Are We from Generating Missing Modalities with Foundation Models?
Guanzhou Ke, Bo Wang, Guoqing Chao +2
Multimodal foundation models have demonstrated impressive capabilities across diverse tasks. However, their potential as plug-and-play solutions for missing modality reconstruction…
cs.LG2025
Knowledge Bridger: Towards Training-free Missing Modality Completion
Guanzhou Ke, Shengfeng He, Xiao Li Wang +5
Previous successful approaches to missing modality completion rely on carefully designed fusion techniques and extensive pre-training on complete data, which can limit their genera…
cs.CV2024
Rethinking Multi-view Representation Learning via Distilled Disentangling
Guanzhou Ke, Bo Wang, Xiaoli Wang +1
Multi-view representation learning aims to derive robust representations that are both view-consistent and view-specific from diverse data sources. This paper presents an in-depth…