Zhe Gan

Principal Researcher, Apple

Joined

December 2017

Names

Zhe Gan

Emails

****@duke.edu (Confirmed)

****@microsoft.com (Confirmed)

****@gmail.com (Confirmed)

****@apple.com (Confirmed)

Personal Links

Career & Education History

Principal Researcher

Apple (apple.com)

2022 – Present

Principal Researcher

Microsoft (microsoft.com)

2018 – 2022

PhD student

Duke University (duke.edu)

2013 – 2018

Advisors, Relations & Conflicts

PhD Advisor

Lawrence Carin

2013 – 2018

Expertise

deep learning

2013 – Present

vision and language

2013 – Present

deep generative models

2013 – Present

Publications

Where did the Reasoning Go Wrong? A Benchmark of Puzzle-Based Visual Tasks with Error Detection
Yusu Qian, Cheng Wan, Chao Jia, Yinfei Yang, Qingyu Zhao, Zhe Gan
- ResponsibleFM @ NeurIPS 2025
- 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
Ferret-UI Lite: Lessons from Building Small On-Device GUI Agents
Zhen Yang, Zi-Yi Dou, Di Feng, Forrest Huang, Anh Tuan Nguyen, Keen You, Omar Attia, Yuhao Yang, Michael Feng, Haotian Zhang, Ram Ramrakhya, Chao Jia, Jeffrey Nichols, Alexander T Toshev, Yinfei Yang, Zhe Gan
- Submitted to ICLR 2026
- Readers: Everyone
UltraCUA: Scaling Computer Use Agent through GUI and Programmatic Control
Yuhao Yang, Zhen Yang, Zi-Yi Dou, Anh Tuan Nguyen, Omar Attia, Andrew Szot, Keen You, Michael Feng, Ram Ramrakhya, Alexander T Toshev, Chao Huang, Yinfei Yang, Zhe Gan
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
Where Did the Reasoning Go Wrong? A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection
Yusu Qian, Cheng Wan, Chao Jia, Yinfei Yang, Qingyu Zhao, Zhe Gan
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing
Yusu Qian, Jiasen Lu, Tsu-Jui Fu, Xinze Wang, Chen Chen, Yinfei Yang, Wenze Hu, Zhe Gan
- Submitted to ICLR 2026
- Readers: Everyone
Scaling Synthetic Task Generation for Agents via Exploration
Ram Ramrakhya, Andrew Szot, Omar Attia, Bogdan Mazoure, Anh Tuan Nguyen, Yuhao Yang, Zhe Gan, Harsh Agrawal, Alexander T Toshev
- ICLR 2026 Poster
- Readers: Everyone
DeepMMSearch-R1: Empowering Multimodal LLMs in Multi-Modal Web Search
Kartik Narayan, Yang Xu, Tian Cao, Kavya Nerella, Vishal M. Patel, Navid Shiee, Peter Grasch, Chao Jia, Yinfei Yang, Zhe Gan
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding
Mingze Xu, Mingfei Gao, Shiyu Li, Jiasen Lu, Zhe Gan, Zhengfeng Lai, Meng Cao, Kai Kang, Yinfei Yang, Afshin Dehghan
- COLM 2025
- Readers: Everyone
Contrastive Localized Language-Image Pre-Training
Hong-You Chen, Zhengfeng Lai, Haotian Zhang, Xinze Wang, Marcin Eichner, Keen You, Meng Cao, Bowen Zhang, Yinfei Yang, Zhe Gan
- ICML 2025 poster
- Readers: Everyone

View all 255 publications

Co-Authors

View all 291 co-authors