Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Zhen Dong

Zhen Dong

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Software Eng.×2Vision×1AI×1

Frequent co-authors

Qiang Li2×
Xin Peng2×
Haozhen You1×
Jingjing Wang1×
Xun Zhou1×
Mingyu Ren1×

Research Timeline

2026
CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences

The paper introduces CV-Arena, a large-scale open benchmark for instructional computer vision, demonstrating that professional-grade image editing requires advanced capabilities in physical reasoning and structural control.

Industrial Practice of LLM-Based Test Case Carving and Assertion Generation (Experience Paper)

This paper presents NL2Test, a tool that generates executable API regression tests from natural-language scenario descriptions and traffic captures, achieving an 82.4% exact-match rate in industrial scenarios.

RESTOR: Automated Test Oracle Generation for RESTful APIs via Reinforcement Learning

A framework called Restor is presented, which generates executable test assertions from a single observed request-response pair in a black-box REST API setting using a fine-tuned Large Language Model.

Highlighted terms show continued research focus across papers

Papers

cs.SEEmpiricalRecentJul 27, 2026

Industrial Practice of LLM-Based Test Case Carving and Assertion Generation (Experience Paper)

Haozhen You, Zhen Dong, Jingjing Wang, Qiang Li +1 more

This paper presents NL2Test, a tool that generates executable API regression tests from natural-language scenario descriptions and traffic captures, achieving an 82.4% exact-match rate in industrial s…

View →
cs.SEEmpiricalRecent
Jul 27, 2026

RESTOR: Automated Test Oracle Generation for RESTful APIs via Reinforcement Learning

Xun Zhou, Zhen Dong, Mingyu Ren, Qiang Li +5 more

A framework called Restor is presented, which generates executable test assertions from a single observed request-response pair in a black-box REST API setting using a fine-tuned Large Language Model.

View →
cs.CVcs.AIRecentMay 30, 2026

CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences

Fangzhou Lin, Peiran Li, Lingyu Xu, Wenjing Chen +11 more

The paper introduces CV-Arena, a large-scale open benchmark for instructional computer vision, demonstrating that professional-grade image editing requires advanced capabilities in physical reasoning…

View →