Yao Ma
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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.
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.
Papers
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.