Yanhao Zhang
Hello! I am Yanhao Zhang. I currently lead the Multimodal Interaction Algorithm team at OPPO’s AI Center, where I have worked since July 2022, developing multimodal foundation models and AI agents for system-level AI products.
My research interests focus on multimodal understanding and generation, AI agents, and on-device–cloud collaborative intelligence, with a particular interest in how models perceive context, reason across modalities, and use tools to accomplish tasks in real-world environments.
My current work focuses on building multimodal agentic systems for everyday interactions, connecting model development with practical product needs. I work on cloud-based mixture-of-experts models and on-device agent models, with an emphasis on agent harnesses, reinforcement learning, and on-device–cloud coordination to improve end-to-end task success and response efficiency. These efforts support core experiences in OPPO’s Xiaobu Assistant, including contextual assistance, screen understanding, visual question answering, and image generation.
Before joining OPPO, I was an Algorithm Expert at Alibaba DAMO Academy, working on image retrieval and recognition, video understanding, and their applications across Taobao and Alibaba Cloud. I also conducted postdoctoral research through the Zhejiang University–Alibaba joint postdoctoral program. I received my Ph.D. in Computer Application Technology from Harbin Institute of Technology, advised by Prof. Qingming Huang, and was a visiting scholar at Brown University. I have published more than 30 papers at leading international conferences, including CVPR, ICCV, ECCV, NeurIPS, and AAAI, and have filed more than 30 patent applications.
Email: zyhhog@163.com · WordPress · Original homepage
News
[2026.5]. Our paper MergeTok is available on arXiv. Thanks to all my collaborators!
[2026]. Our paper OASIS was accepted to CVPR 2026. Code. Thanks to all my collaborators!
[2026]. Our paper Thinking in Streaming Video was accepted to ECCV 2026. Code and project. Thanks to all my collaborators!
[2026]. Our papers Mobile-Agent-RAG and OwlCap were accepted to AAAI 2026. Mobile-Agent-RAG project · Mobile-Agent-RAG code · OwlCap code. Thanks to all my collaborators!
[2022.7]. Joined OPPO AI Center to work on multimodal models and AI agents.
Select Recent Publication
Full publication list on Google Scholar
Mobile-Agent-RAG: Driving Smart Multi-Agent Coordination with Contextual Knowledge Empowerment for Long-Horizon Mobile Automation
Yuxiang Zhou, Jichang Li, Yanhao Zhang, Haonan Lu, Guanbin Li
AAAI 2026
Paper · PDF · Code · Project Page
AndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model
Zhiwei Jin, Xiaohui Song, Nan Wang, Yafei Liu, Chao Li, Xin Li, Ruichen Wang, Zhihao Li, Qi Qi, Long Cheng, Dongze Hao, Quanlong Zheng, Yanhao Zhang, et al.
arXiv 2025
Paper · PDF · Evaluation Code
HEIE: MLLM-Based Hierarchical Explainable AIGC Image Implausibility Evaluator
Fan Yang, Ru Zhen, Jianing Wang, Yanhao Zhang, Haoxiang Chen, Haonan Lu, Sicheng Zhao, Guiguang Ding
CVPR 2025
Paper · PDF · Project Page
Selected Honors
- 2016 National Development Bank Innovation Team
- 2015 National Scholarship
- 2015 Huawei Scholarship
Academic Service
- Conference Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, AAAI, IJCAI, ACL, WWW.
- Journal Reviewer: IEEE Transactions on Circuits and Systems for Video Technology (TCSVT); IEEE Transactions on Multimedia (TMM); IEEE Transactions on Image Processing (TIP); IEEE Transactions on Cybernetics (TCYB); IEEE Transactions on Knowledge and Data Engineering (TKDE); ACM Transactions on Intelligent Systems and Technology (TIST); IET Computer Vision; PLOS ONE; Neurocomputing.









