Xiaohua Zhai

Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems

CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?

LocCa: Visual Pretraining with Location-aware Captioners

PaLI-3 Vision Language Models: Smaller, Faster, Stronger

No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models

SILC: Improving Vision Language Pretraining with Self-Distillation