Skip to content

2 papers 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 Oct 2026

A Sign Law for Entropy Drift under Sampler Mismatch in RLVR

It is proved that a constant advantage shift then changes the entropy of a softmax policy, at first order and in expectation, with a sign fixed by the sampler, as well as a covariance between advantages and the sampler's sharpness gap.

Zhi-Yuan Wang, Jacob Steeves, Chang Liu · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.