Multimodal intelligence & agents

Xurui Zhou

周绪睿

Master's student HIT (Shenzhen)

I am a Master’s student at Harbin Institute of Technology (Shenzhen), supervised by Prof. Rui Shao and Prof. Gongwei Chen.

My research focuses on GUI Agent and Hybrid Coding, with broader interests in multimodal learning and reinforcement learning. I have interned at Qwen, Alibaba Tongyi Lab and Huawei Noah’s Ark Lab.

Email GitHub Google Scholar
Open to PhD opportunities & industry positions.Let's talk

Research experience

Industry internships

Qwen

Alibaba Tongyi Lab · Foundation Models

Algorithm Intern

Worked on GUI Agent and Hybrid Coding capabilities for Qwen foundation models, spanning continued pretraining and post-training.

GUI Agent

Built verifiable data pipelines for task synthesis, environment initialization, trajectory collection, validation, and cleaning, connected to RL training and rollout.

Hybrid Coding

Unified GUI interaction and CLI programming in a shared harness, using visual feedback for development, debugging, and verification in real applications.

  • MobileWorld
  • AndroidBench
  • Design Arena

Huawei Noah's Ark Lab

Reasoning & Decision Making

Research Intern

Built GUI-agent data production and training infrastructure for mobile assistant scenarios, including Xiaoyi. Studied vision-based GUI agents with multimodal large language models.

  • Vision-based GUI Agents
  • Multimodal Learning
  • Mobile Assistants

Selected research

All publications
CVPR2026
HiconAgentFirst author

HiconAgent: History Context-aware Policy Optimization for GUI Agents

History-aware policy optimization for more effective and efficient GUI agents.

Xurui Zhou, Gongwei Chen, Yuquan Xie, Zaijing Li, Kaiwen Zhou, Shuai Wang, Shuo Yang, Zhuotao Tian, Rui Shao

Paper Code
ICCV2025Highlight
SimpAgentStudent first author

Less is More: Empowering GUI Agent with Context-Aware Simplification

Simplifying visual elements and interaction history to improve both performance and efficiency.

Gongwei Chen, Xurui Zhou, Rui Shao, Yibo Lyu, Kaiwen Zhou, Shuai Wang, Wentao Li, Yinchuan Li, Zhongang Qi, Liqiang Nie

Paper Code
ICLR2025Spotlight
SPA-Bench

SPA-Bench: A Comprehensive Benchmark for SmartPhone Agent Evaluation

A comprehensive benchmark for evaluating smartphone agents across interactive tasks.

Jingxuan Chen, Derek Yuen, Bin Xie, Yuhao Yang, Gongwei Chen, Zhihao Wu, Yixing Li, Xurui Zhou, Weiwen Liu, Shuai Wang, et al.

Paper Code

Education

Harbin Institute of Technology
Master's

M.Eng. in Electronic Information

Computer Technology

Harbin Institute of Technology (Shenzhen)

Sep 2024 – Dec 2026 (expected)

Bachelor's

B.Eng. in Computer Science and Technology

Harbin Institute of Technology (Shenzhen)

Sep 2020 – Jul 2024

GPA: 91.47 / 100 (3.7 / 4.0)

National First PrizeChina Undergraduate Mathematical Contest in Modeling

Recent updates

All updates
Feb 21, 2026 One paper about GUI Agent and RL is accepted by CVPR 2026! :sparkles:
Jun 26, 2025 One paper about GUI Agent is accepted by ICCV 2025 as Highlight! :sparkles:
Feb 11, 2025 One paper about GUI Agent Benchmark is accepted by ICLR 2025 as Spotlight! :sparkles:

Get in touch

Let's build what's next.

Research discussions, collaborations, and new opportunities.

zhouxurui1314@gmail.com