Yijia Guo
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes a channel prediction-based Physical Layer Authentication (PLA) framework using a Transformer module to maintain robust authentication accuracy against consecutive spoofing attacks in wireless networks.
The paper proposes CAST, an answer-free self-distillation method that enhances Group Relative Policy Optimization (GRPO) for verifiable rewards, allowing token-level advantage signals even when all sampled trajectories are uniformly correct or incorrect.
Papers
CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPO
Yang Li, Gongle Xue, Yijia Guo, Yuheng Yuan +2 more
The paper proposes CAST, an answer-free self-distillation method that enhances Group Relative Policy Optimization (GRPO) for verifiable rewards, allowing token-level advantage signals even when all sa…