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

Yao Ma

2 indexed papers

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

Publications per year

2
26

Top categories

AI×2Signal Processing×1Crypto×1ML×1

Frequent co-authors

Lizhou Liu1×
Xiaohui Chen1×
Zihan Tang1×
Mengyao Ma1×
Wenyi Zhang1×
Jiacheng Liang1×

Research Timeline

2026
ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial prompts, leading to enhanced safety robustness.

Scene-Conditioned PINN-GNN for Multipath RF Maps: Cross-Scene Generation and In-Scene Completion

This paper proposes a unified RF map construction framework using physics-informed neural networks and graph neural networks, achieving high-fidelity RF map construction under sparse observations.

Highlighted terms show continued research focus across papers

Papers

eess.SPcs.AIEmpiricalRecentJul 2, 2026

Scene-Conditioned PINN-GNN for Multipath RF Maps: Cross-Scene Generation and In-Scene Completion

Lizhou Liu, Xiaohui Chen, Zihan Tang, Mengyao Ma +1 more

This paper proposes a unified RF map construction framework using physics-informed neural networks and graph neural networks, achieving high-fidelity RF map construction under sparse observations.

View →
cs.AIcs.CRcs.LGRecent
Apr 20, 2026

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System

Jiacheng Liang, Yao Ma, Tharindu Kumarage, Satyapriya Krishna +4 more

ARES is a novel framework that systematically discovers and mitigates dual vulnerabilities in RLHF systems by simultaneously testing the core LLM and its Reward Model (RM) using structured adversarial…

View →