🧑‍🔬 Kanzhi Cheng

🏛️ Affiliations

🎓Nanjing UniversityNanjing · China2022–2026 · 21 paperscurrent🎓Fudan UniversityShanghai · China2025–2026 · 3 paperscurrent🎓University of Hong KongPok Fu Lam · China2025–2026 · 3 paperscurrent🔬Shanghai Artificial Intelligence LaboratoryShanghai · China2024–2025 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents (2024 · 135 citations)
   Most GUI agents for phones, desktops and websites operate on structured representations such as HTML, DOM or Android view hierarchies.
2. OS-ATLAS: A Foundation Action Model for Generalist GUI Agents (2024 · 67 citations)
   GUI agents that operate directly on screenshots usually depend on proprietary vision-language models such as GPT-4o.
3. OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis (2025 · 48 citations)
   Training GUI agents built on Vision-Language Models requires full interaction trajectories: an overall goal, step instructions, actions, and screen states.
4. Vision-Language Models Can Self-Improve Reasoning via Reflection (2025 · 35 citations)
   Open multimodal LLMs reason poorly with chain-of-thought (CoT), and annotated multimodal rationales are expensive to collect at scale.
5. Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models (2025 · 15 citations)
   Large language models increasingly solve tasks by writing symbolic intermediate forms, such as programs, logic forms, or web actions, which an external environment then executes.
6. Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning (2025 · 8 citations)
   Genius tackles the problem of improving LLM reasoning after pre-training without any external supervision.
7. OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic Workflows (2026 · 2 citations)
   Mobile GUI agents built on Vision-Language Models can carry out tasks on phones, but they may also behave unsafely, for example by leaking private data, posting offensive content or tampering with the system.

All works

9 works of theirs in our library, the most cited first; 7 with a page here, the others link their original until we summarise them.

1. SeeClick: Harnessing GUI Grounding for Advanced Visual GUI AgentsarXiv:2401.10935Kanzhi Cheng, Qiushi Sun, Yougang Chu, et al.2024 · 135 citations
2. OS-ATLAS: A Foundation Action Model for Generalist GUI AgentsarXiv:2410.23218Zhiyong Wu, Zhenyu Wu, Fangzhi Xu, et al.2024 · 67 citations
3. OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task SynthesisAnnual Meeting of the Association for Computational Linguistics (ACL)Qiushi Sun, Kanzhi Cheng, Zichen Ding, et al.2025 · 48 citations
4. Vision-Language Models Can Self-Improve Reasoning via ReflectionConference of the North American Chapter of the Association for Computational Linguistics (NAACL)Kanzhi Cheng, Li YanTao, Fangzhi Xu, et al.2025 · 35 citations
5. Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Fangzhi Xu, Qiushi Sun, Kanzhi Cheng, et al.2025 · 15 citations
6. ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows ↗arXiv:2505.19897 · no summary yetQiushi Sun et al.2025 · 11 citations
7. Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Fangzhi Xu, Hang Yan, Chang Ma, et al.2025 · 8 citations
8. OS-Sentinel: Towards Safety-Enhanced Mobile GUI Agents via Hybrid Validation in Realistic WorkflowsAnnual Meeting of the Association for Computational Linguistics (ACL)Qiushi Sun, Mukai Li, Zhoumianze Liu, et al.2026 · 2 citations
9. OS-Symphony: A Holistic Framework for Robust and Generalist Computer-Using Agents ↗Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetBowen Yang et al.2026

🤝 Co-authors here

12 of 25 co-authors with a page, the most papers together first.

• Fangzhi Xu ×7
• Qiushi Sun ×6
• Zhiyong Wu ×5
• Zichen Ding ×3
• Chengyou Jia ×2
• Jianbing Zhang ×2
• Jun Liu ×2
• Liheng Chen ×2
• Yian Wang ×2
• Yu Qiao ×2
• Zhenyu Wu ×2
• Zhoumianze Liu ×2

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Annual Meeting of the Association for Computational Linguistics (ACL) ×5: ACL 2026, ACL 2025 ×3
• Conference of the North American Chapter of the Association for Computational Linguistics (NAACL): NAACL 2025

🔗 Cited by

Papers of our library cite their works 300 times (of the 149,439 papers whose bibliographies we read); 71 citing papers with a page here →.

Updated 31 October 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/kanzhi-cheng/