Xiaohua Zhai
4 papers · 22 citations
Most-cited papers
- SILC: Improving Vision Language Pretraining With Self-distillation2023 · 22 citations
- CLIP The Bias: How Useful Is Balancing Data In Multimodal Learning?2024
- Pali-3 Vision Language Models: Smaller, Faster, Stronger2023
- Three Towers: Flexible Contrastive Learning With Pretrained Image Models2023
Top co-authors
Topics