4 papers
Sona Technical Report
Sona Team, Alexandr Udeneev, Aleksei Krasilnikov +33
We introduce Sona, a single-model generative recommender for Yandex Music. In an online A/B test, Sona replaced the entire production cascade, comprising more than 15 candidate gen…
Excision Score: Evaluating Edits with Surgical Precision
Nikolai Gruzinov, Ksenia Sycheva, Earl T. Barr +1
Many tasks revolve around editing a document, whether code or text. We formulate the revision similarity problem to unify a wide range of machine learning evaluation problems whose…
DOoM: Difficult Olympiads of Math
Ilya Kuleshov, Ilin Pavel, Nikolay Kompanets +2
This paper introduces DOoM, a new open-source benchmark designed to assess the capabilities of language models in solving mathematics and physics problems in Russian. The benchmark…
The Best of N Worlds: Aligning Reinforcement Learning with Best-of-N Sampling via max@k Optimisation
Farid Bagirov, Mikhail Arkhipov, Ksenia Sycheva +2
The application of Reinforcement Learning with Verifiable Rewards (RLVR) to mathematical and coding domains has demonstrated significant improvements in the reasoning and problem-s…