1 citations · 1 across the 3 of their papers we have counts for
3 papers
Stress Testing Deliberative Alignment for Anti-Scheming Training
Bronson Schoen, Evgenia Nitishinskaya, Mikita Balesni +16
Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions,…
The Hopf algebra of formal multiple polylogarithms
Steven Charlton, Andrei Matveiakin, Danylo Radchenko +1
We define a Hopf algebra of polylogarithms of an arbitrary field, which is a candidate for a conjectural Hopf algebra of framed mixed Tate motives. Our definition is elementary and…
Cluster Polylogarithms I: Quadrangular Polylogarithms
Andrei Matveiakin, Daniil Rudenko
We suggest a definition of cluster polylogarithms on an arbitrary cluster variety and classify them in type . We find functional equations for multiple polylogarithms which gene…