Author

Duo-Han Zhang

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.

#artificial intelligence Preprint Sep 2026

Inference-Time Nash Alignment

This work forms the problem as obtaining a Nash equilibrium of a two-player zero-sum game between policies, and proposes two algorithms: Best-of-Nash (BoN) and Nash Mirror Descent (NMD), which are proved to achieve a duality gap that matches the problem lower bound.

Hadi Hosseini, Debmalya Mandal, Duo-Han Zhang · 0 citations