Zirui Wang

Research Scientist, Google Deepmind

Joined

September 2019

Names

Zirui Wang (Preferred)

Emails

****@cs.cmu.edu (Confirmed)

****@google.com (Confirmed)

****@gmail.com (Confirmed)

****@apple.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

Research Scientist

Google Deepmind (google.com)

2025 – Present

Member of Technical Staff

xAI (x.ai)

2024 – 2025

Research Scientist

Apple AI/ML (apple.com)

2023 – 2024

Research Scientist

Google Brain (google.com)

2021 – 2023

PhD student

School of Computer Science, Carnegie Mellon University (cs.cmu.edu)

2017 – 2021

Advisors, Relations & Conflicts

PhD Advisor

Yulia Tsvetkov

2020 – 2021

PhD Advisor

Jaime Carbonell

2017 – 2021

Expertise

Natural Language Processing

Present

Deep Learning

Present

Representation Learning

Present

Publications

OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
Yanqing Liu, Xianhang Li, Letian Zhang, Zirui Wang, Zeyu Zheng, Yuyin Zhou, Cihang Xie
- OpenReview Archive Direct Upload
- Readers: Everyone
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Yanghao Li, Rui Qian, Bowen Pan, Haotian Zhang, Haoshuo Huang, Bowen Zhang, Jialing Tong, Haoxuan You, Xianzhi Du, Zhe Gan, Hyunjik Kim, Chao Jia, Zhenbang Wang, Yinfei Yang, Mingfei Gao, Zi-Yi Dou, Wenze Hu, Chang Gao, Dongxu Li, Philipp Dufter et al. (7 additional authors not shown)
- ICLR 2026 Poster
- Readers: Everyone
MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use
Zijian Wu, Xiangyan Liu, xinyuan zhang, Lingjun Chen, Fanqing Meng, Lingxiao Du, Yiran Zhao, Fanshi Zhang, Yaoqi Ye, Jiawei Wang, Zirui Wang, Jinjie Ni, Yufan Yang, Arvin Xu, Michael Qizhe Shieh
- ICLR 2026 Poster
- Readers: Everyone
Learning to Reason as Action Abstractions with Scalable Mid-Training RL
Shenao Zhang, Donghan Yu, Yihao Feng, Bowen Jin, Zhaoran Wang, John Peebles, Zirui Wang
- ICLR 2026 Poster
- Readers: Everyone
Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization
Jiawei Mao, Xiaoke Huang, Yunfei Xie, Yuanqi Chang, Mude Hui, Bingjie Xu, Zeyu Zheng, Zirui Wang, Cihang Xie, Yuyin Zhou
- ICLR 2026 Poster
- Readers: Everyone
COMPASS: A Multi-Turn Benchmark for Tool-Mediated Planning & Preference Optimization
Tian Qin, Haoping Bai, Ting-Yao Hu, Raviteja Vemulapalli, Hema Swetha Koppula, Bowen Jin, Zhiyang Xu, Mert Cemri, Jiarui Lu, Zirui Wang, Meng Cao
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
Haotian Zhang, Mingfei Gao, Zhe Gan, Philipp Dufter, Nina Wenzel, Forrest Huang, Dhruti Shah, Xianzhi Du, Bowen Zhang, Yanghao Li, Sam Dodge, Keen You, Zhen Yang, Aleksei Timofeev, Mingze Xu, Hong-You Chen, Jean-Philippe Fauconnier, Zhengfeng Lai, Haoxuan You, Zirui Wang et al. (3 additional authors not shown)
- ICLR 2025 Poster
- Readers: Everyone
Understanding Alignment in Multimodal LLMs: A Comprehensive Study
Elmira Amirloo, Jean-Philippe Fauconnier, Christoph Roesmann, Christian Kerl, Rinu Boney, Yusu Qian, Zirui Wang, Afshin Dehghan, Yinfei Yang, Zhe Gan, Peter Grasch
- Submitted to ICLR 2025
- Readers: Everyone
Ferret: Refer and Ground Anything Anywhere at Any Granularity
Haoxuan You, Haotian Zhang, Zhe Gan, Xianzhi Du, Bowen Zhang, Zirui Wang, Liangliang Cao, Shih-Fu Chang, Yinfei Yang
- ICLR 2024 spotlight
- Readers: Everyone
Exploiting Category Names for Few-Shot Classification with Vision-Language Models
Taihong Xiao, Zirui Wang, Liangliang Cao, Jiahui Yu, Shengyang Dai, Ming-Hsuan Yang
- Published: 06 Mar 2023, Last Modified: 15 Feb 2026
- MRL 2023
- Readers: Everyone

View all 27 publications

Co-Authors

View all 568 co-authors