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

Zheng Ge

3 indexed papers

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

Publications per year

3
26

Top categories

AI×2ML×1NLP×1Distributed×1Vision×1

Frequent co-authors

Daxin Jiang3×
Kangheng Lin2×
En Yu2×
Yana Wei2×
Han Zhou2×
Liang Zhao2×

Research Timeline

2026
PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

Introduce PerceptionRubrics, a rubric-based evaluation framework for addressing real-world brittleness of models using 1,038 images and over 12,000 instance-specific rubrics.

MentalThink: Shaping Thoughts in Mental SVG World

The paper introduces MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal Language Models with an executable mechanism for mental visualization using SVG graphics.

Metal Sandbox: Isolated Execution and Command Scheduling for GPU Coding Agents on Apple Silicon

This paper presents Metal Sandbox, a system for efficient on-device inference on macOS that combines restricted file access, native command execution, and command-level scheduling.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.CLEmpiricalRecentNov 12, 2026

Metal Sandbox: Isolated Execution and Command Scheduling for GPU Coding Agents on Apple Silicon

Haozhe Wang, Lina Chen, Fanqi Wan, Qi Han +4 more

This paper presents Metal Sandbox, a system for efficient on-device inference on macOS that combines restricted file access, native command execution, and command-level scheduling.

View →
cs.AIEmpirical
Recent
Jul 3, 2026

MentalThink: Shaping Thoughts in Mental SVG World

Kangheng Lin, Jisheng Yin, Dingming Li, En Yu +10 more

The paper introduces MentalThink, a visual-symbolic reasoning paradigm that equips Multimodal Language Models with an executable mechanism for mental visualization using SVG graphics.

View →
cs.CVEmpiricalRecentJun 26, 2026

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

Yana Wei, Hongbo Peng, Yanlin Lai, Liang Zhao +13 more

Introduce PerceptionRubrics, a rubric-based evaluation framework for addressing real-world brittleness of models using 1,038 images and over 12,000 instance-specific rubrics.

View →