Author

Shi-Han Wang

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Apr 2026

Safety Training Modulates Harmful Misalignment Under On-Policy RL, But Direction Depends on Environment Design

On-policy RL preserves a safety buffer inherent in the model's own generation distribution, one that is bypassed during off-policy settings, one that is bypassed during off-policy settings.

Leon Eshuijs, Shi-Han Wang, Antske Fokkens · arXiv.org · 0 citations