I am Kanzhi Cheng (程瞰之), a PhD student (2021.9 - ) in the NLP Group at Nanjing University, advised by Dr. Jiajun Chen & Dr. Jianbing Zhang. Previously, I worked as a research intern at Shanghai AI Lab, Tsinghua AIR, Microsoft Research, and SenseTime Research. I am deeply grateful for the opportunity to work with and learn from Dr. Shi Zong, Dr. Zhiyong Wu , Dr. Hao Zhou, Dr. Qianhui Wu, and Dr. Zheng Ma.

Currently, I am broadly interested in multimodal intelligence, with a focus on:

• (Multimodal) Autonomous Agents: particularly GUI agents capable of acting in the digital world to automate complex tasks (SeeClick, OS-Atlas, OS-Genesis, GUI-Actor, OSReward, OpenMobile, OpenMobile-2).
• Large Vision-Language Models: building multimodal systems that can understand image/video, generate text (Beyond Generic, CapArena), and perform reasoning (MM-Self-Improve).

🔥 News

• 2026.10:  🤖🤖 We release OpenMobile-2 with scalable environments and app-native tools.
• 2026.08:  🤖🤖 We release OSReward for evaluating and analyzing CUA reward models.
• 2026.04:  🤖🤖 We release OpenMobile to facilitate open mobile agent research.
• 2026.04:  🎉🎉 Two papers are accepeted by ACL 2026.
• 2026.01:  🎉🎉 One papers is accepeted by ICLR 2026.
• 2025.11:  📚📚 Started my visit to NTU, Singapore 🇸🇬. Advised by Dr. Luu Anh Tuan.
• 2025.09:  🎉🎉 GUI-Actor is accepted by NeurIPS 2025.
• 2025.07:  🏖️🏖️ See you at Vienna 🇦🇹!
• 2025.06:  🤖🤖 We release GUI-Actor to advance visual grounding for GUI Agents.
• 2025.05:  🎉🎉 Four papers are accepeted by ACL 2025.

📝 Selected Publications

Arxiv

OpenMobile-2: Building Versatile Mobile Agents with Scalable Environments and App-Native Tools
Chenyang Yan*, Yingying Zhang*, Kanzhi Cheng*†, Qiushi Sun*, Zhengyuan Pan*, Zheng Ma*†, Hang Yan, Yian Wang, Nuo Chen, Jialin Cao, Xingdong Gong, Wenpo Song, Han Chen, Zichen Ding, Fangzhi Xu, Shujian Huang, Xinyu Dai, Yichen Liu, Tiankuo Yao, Bo Wang, Ben Kao, Jianbing Zhang, Lewei Lu, Dahua Lin

* Equal contribution. † Project leads.

Code   Environment   Project Page   Models   Data    

COLM 2026

OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
Kanzhi Cheng, Zehao Li, Zheng Ma, Nuo Chen, Jialin Cao, Qiushi Sun, Zichen Ding, Fangzhi Xu, Hang Yan, Jiajun Chen, Luu Anh Tuan, Jianbing Zhang, Lewei Lu, Dahua Lin

Code   Project Page   Models   Data    

ACL 2024 (Main)

SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents
Kanzhi Cheng, Qiushi Sun, Yougang Chu, Fangzhi Xu, Yantao Li, Jianbing Zhang, Zhiyong Wu

Code   Models&Data    

Arxiv

OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
Qiushi Sun*, Kanzhi Cheng*, Yian Wang*, Bowen Yang*, Hang Yan*, Liheng Chen*, Fangzhi Xu, Zichen Ding, Nuo Chen, Jialin Cao, Xingdong Gong, Zehao Li, Kaiming Jin, Xinfeng Yuan, Zhoumianze Liu, Jingyang Gong, Zhangyue Yin, Jiahui Gao, Zhiyong Wu, Tianbao Xie, Jianbing Zhang, Ben Kao

Code   Project Page   Benchmark   Data   Models  

NeurIPS 2025 (Poster)

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
Qianhui Wu*, Kanzhi Cheng*, Rui Yang*, Chaoyun Zhang, Jianwei Yang, Huiqiang Jiang, Jian Mu, Baolin Peng, Bo Qiao, Reuben Tan, Si Qin, Lars Liden, Qingwei Lin, Huan Zhang, Tong Zhang, Jianbing Zhang, Dongmei Zhang, Jianfeng Gao

Code   Project Page   Models&Data    

ACL 2025 (Main)

OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
Qiushi Sun*, Kanzhi Cheng*, Zichen Ding*, Chuanyang Jin*, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, Ben Kao, Guohao Li, Junxian He, Yu Qiao, Zhiyong Wu

Code   Project Page   Models&Data    

NAACL 2025 (Main)

Vision-Language Models Can Self-Improve Reasoning via Reflection
Kanzhi Cheng*, Yantao Li*, Fangzhi Xu, Jianbing Zhang, Hao Zhou, Yang Liu

Code    

ACL 2025 (Findings)

CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era
Kanzhi Cheng*, Wenpo Song*, Jiaxin Fan*, Zheng Ma, Qiushi Sun, Fangzhi Xu, Chenyang Yan, Nuo Chen, Jianbing Zhang, Jiajun Chen

Code   Project Page    

• ACMMM 2023 Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model
  Kanzhi Cheng, Wenpo Song, Zheng Ma, Wenhao Zhu, Zixuan Zhu, Jianbing Zhang

• NLPCC 2022 ADS-Cap: A Framework for Accurate and Diverse Stylized Captioning with Unpaired Stylistic Corpora
  Kanzhi Cheng, Zheng Ma, Shi Zong, Jianbing Zhang, Xinyu Dai, Jiajun Chen

• ACL 2026 OS-Sentinel:Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows
  Qiushi Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie, Fangzhi Xu, Zhangyue Yin, Kanzhi Cheng, Zehao Li, Zichen Ding, Qi Liu, Zhiyong Wu, Zhuosheng Zhang, Ben Kao, Lingpeng Kong

• ACL 2026 OS-SYMPHONY: A Holistic Framework for Robust and Generalist Computer-Using Agent
  Bowen Yang, Kaiming Jin, Zhenyu Wu, Zhaoyang Liu, Qiushi Sun, Zehao Li, JingJing Xie, Zhoumianze Liu, Fangzhi Xu, Kanzhi Cheng, Qingyun Li, Yian Wang, Yu Qiao, Zun Wang, Zichen Ding

• ICLR 2026 ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows
  Qiushi Sun, Zhoumianze Liu, Chang Ma, Zichen Ding, Fangzhi Xu, Zhangyue Yin, Haiteng Zhao, Zhenyu Wu, Kanzhi Cheng, Zhaoyang Liu, Jianing Wang, Qintong Li, Xiangru Tang, Tianbao Xie, Xiachong Feng, Xiang Li, Ben Kao, Wenhai Wang, Biqing Qi, Lingpeng Kong, Zhiyong Wu

• ACL 2025 (Main) Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
  Fangzhi Xu, Hang Yan, Chang Ma, Haiteng Zhao, Qiushi Sun, Kanzhi Cheng, Junxian He, Jun Liu, Zhiyong Wu

• ACL 2025 (Main) Interative Evolution: A Neural-symbolic Self-Training Framework for Large Language Models
  Fangzhi Xu, Qiushi Sun, Kanzhi Cheng, Jun Liu, Yu Qiao, Zhiyong Wu

• ICLR 2025 (Spotlight) OS-ATLAS: A Foundation Action Model For Generalist GUI Agents
  Zhiyong Wu, Zhenyu Wu, Fangzhi Xu, Yian Wang, Qiushi Sun, Chengyou Jia, Kanzhi Cheng, Zichen Ding, Liheng Chen, Paul Pu Liang, Yu Qiao

• Preprint A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond
  Qiushi Sun, Zhirui Chen, Fangzhi Xu, Chang Ma, Kanzhi Cheng, Zhangyue Yin, Jianing Wang, Chengcheng Han, Renyu Zhu, Shuai Yuan, Pengcheng Yin, Qipeng Guo, Xipeng Qiu, Xiaoli Li, Fei Yuan, Lingpeng Kong, Xiang Li, Zhiyong Wu

🎖 Honors and Awards

• 2025.05 Excellent Graduate Student, Nanjing University
• 2024.10 First-Class Graduate Talent Scholarship, Nanjing University
• 2023.10 Outstanding Graduate Award, Nanjing University
• 2021.06 Outstanding Graduation Project, Nanjing University
• 2019.10 Guanghua Scholarship (1%), Nanjing University

📖 Educations

• 2025.11 - 2026.05, visiting Ph.D. Student at Nanyang Technological University, Singapore.
• 2021.09 - 2026 (now), Ph.D. Student at the Department of Computer Science and Technology, Nanjing University.
• 2017.09 - 2021.06, B.E. at the School of Management and Engineering, Nanjing University.

💻 Internships

• 2025.11 - 2026.07, SenseTime Research.
• 2025.04 - 2025.06, Microsoft Research.
• 2024.08 - 2025.01, Tsinghua AIR.
• 2023.08 - 2024.04, Shanghai Artificial Intelligence Laboratory.

⚽️ Personal Interests

I am an amateur football player, primarily playing as an attacking midfielder. As a player, I’ve been fortunate to win the following honors:

• Member of the Nanjing University official football team
• 🏆 Champion of the 2022–2023 Nanjing University Caigen Cup, awarded Final MVP
• 🏆 Champion of the 2018–2019 Nanjing University FA Cup

I am also a fan of Arsenal Football Club.