Pengyu Chen

This paper surveys model forensics in AI-native wireless networks, detailing key security problems and demonstrating practical workflows for verifying model authenticity and detecting malicious functions.

The paper proposes a graph-constrained approach to scale multi-hop training data by decoupling path discovery from path verbalization, significantly expanding the usable corpus size for LLMs.

The paper proposes Skill-RM, a unified framework that treats reward modeling as an agentic task to consistently integrate diverse evaluation criteria, achieving superior performance over traditional methods.