Picture for Ziping Ma

Ziping Ma

M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining

Add code
Feb 04, 2024
Viaarxiv icon

SyCoCa: Symmetrizing Contrastive Captioners with Attentive Masking for Multimodal Alignment

Add code
Jan 04, 2024
Viaarxiv icon