Hanyang Peng

GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning

AlignMark: Content-Aligned Audio Watermarking for Robustness Against Neural Transformations

Simple Convergence Proof of Adam From a Sign-like Descent Perspective

SoftSignSGD(S3): An Enhanced Optimize for Practical DNN Training and Loss Spikes Minimization Beyond Adam