Skip to content

Author

Youhei Akimoto

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.

#small language model Preprint Aug 2026

Safety Hacking in Constrained Best-of-$N$ Inference-time Scaling

It is shown that policies within a bounded $\chi^2$ divergence from the proxy-feasible reference distribution admit an $N$-independent safety-hacking bound, and instantiate this general coverage-control principle with constrained pessimistic sampling.

Akifumi Wachi, Takumi Tanabe, Youhei Akimoto · 0 citations