Xiaohua Zhai

Joined

June 2018

Names

Xiaohua Zhai

Emails

****@google.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

DBLP

Career & Education History

Researcher

OpenAI (openai.com)

2025 – 2025

Researcher

Google DeepMind (google.com)

2023 – 2024

Researcher

Google Brain (google.com)

2017 – 2023

Software Engineer

Google (google.com)

2015 – 2017

PhD student

Peking University (pku.edu.cn)

2009 – 2014

Advisors, Relations & Conflicts

PhD Advisor

Yuxin Peng

2009 – 2014

Expertise

Representation learning

2016 – Present

Computer Vision

2016 – Present

Vision and Language

2016 – Present

Publications

Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems
Ibrahim Alabdulmohsin, Xiaohua Zhai
- NeurIPS 2025 poster
- Readers: Everyone
LocCa: Visual Pretraining with Location-aware Captioners
Bo Wan, Michael Tschannen, Yongqin Xian, Filip Pavetic, Ibrahim Alabdulmohsin, Xiao Wang, André Susano Pinto, Andreas Peter Steiner, Lucas Beyer, Xiaohua Zhai
- NeurIPS 2024 poster
- Readers: Everyone
No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models
Angéline Pouget, Lucas Beyer, Emanuele Bugliarello, Xiao Wang, Andreas Peter Steiner, Xiaohua Zhai, Ibrahim Alabdulmohsin
- NeurIPS 2024 poster
- Readers: Everyone
PaLI-3 Vision Language Models: Smaller, Faster, Stronger
Xi Chen, Xiao Wang, Lucas Beyer, Alexander Kolesnikov, Jialin Wu, Paul Voigtlaender, Sebastian Goodman, Basil Mustafa, Ibrahim Alabdulmohsin, Piotr Padlewski, Daniel Salz, Xi Xiong, Daniel Vlasic, Filip Pavetic, Keran Rong, Tianli Yu, Daniel Keysers, Xiaohua Zhai, Radu Soricut
- Submitted to ICLR 2024
- Readers: Everyone
CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
Ibrahim Alabdulmohsin, Xiao Wang, Andreas Peter Steiner, Priya Goyal, Alexander D'Amour, Xiaohua Zhai
- ICLR 2024 poster
- Readers: Everyone
SILC: Improving Vision Language Pretraining with Self-Distillation
Muhammad Ferjad Naeem, Yongqin Xian, Xiaohua Zhai, Lukas Hoyer, Luc Van Gool, Federico Tombari
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Three Towers: Flexible Contrastive Learning with Pretrained Image Models
Jannik Kossen, Mark Collier, Basil Mustafa, Xiao Wang, Xiaohua Zhai, Lucas Beyer, Andreas Peter Steiner, Jesse Berent, Rodolphe Jenatton, Efi Kokiopoulou
- ES-FoMO 2023 Poster
- Readers: Everyone
Image Captioners Are Scalable Vision Learners Too
Michael Tschannen, Manoj Kumar, Andreas Peter Steiner, Xiaohua Zhai, Neil Houlsby, Lucas Beyer
- NeurIPS 2023 oral
- Readers: Everyone
Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
Ibrahim Alabdulmohsin, Xiaohua Zhai, Alexander Kolesnikov, Lucas Beyer
- NeurIPS 2023 poster
- Readers: Everyone
Three Towers: Flexible Contrastive Learning with Pretrained Image Models
Jannik Kossen, Mark Collier, Basil Mustafa, Xiao Wang, Xiaohua Zhai, Lucas Beyer, Andreas Peter Steiner, Jesse Berent, Rodolphe Jenatton, Effrosyni Kokiopoulou
- NeurIPS 2023 poster
- Readers: Everyone

View all 29 publications

Co-Authors

View all 106 co-authors