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

Pengkun Wang

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2ML×1

Frequent co-authors

Xucong Wang2×
Ziyu Ma1×
Yong Wang1×
Yuxiang Ji1×
Shidong Yang1×
Guanhua Chen1×

Research Timeline

2026
FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and improve robustness.

APPO: Agentic Procedural Policy Optimization

This paper proposes a new method for agentic Reinforcement Learning called Agentic Procedural Policy Optimization (APPO) that improves tool-use capabilities by assigning credit to fine-grained decision points.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIEmpiricalRecentJun 10, 2026

APPO: Agentic Procedural Policy Optimization

Xucong Wang, Ziyu Ma, Yong Wang, Yuxiang Ji +4 more

This paper proposes a new method for agentic Reinforcement Learning called Agentic Procedural Policy Optimization (APPO) that improves tool-use capabilities by assigning credit to fine-grained decisio…

View →
cs.AIRecentMay 27, 2026

FedMPT: Federated Multi-label Prompt Tuning of Vision-Language Models

Xucong Wang, Pengkun Wang, Zhe Zhao, Liheng Yu +2 more

FedMPT introduces a novel federated learning framework for Multi-Label Recognition (MLR) using Vision-Language Models (VLMs) by leveraging generalizable conditions to mitigate label overfitting and im…

View →