1 citations · 1 across the 2 of their papers we have counts for
3 papers
Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian
Aleksandr Nikolich, Konstantin Korolev, Sergei Bratchikov +2
There has been a surge in the development of various Large Language Models (LLMs). However, text generation for languages other than English often faces significant challenges, inc…
Weight-Space Geometry of Offline Reasoning Training
Aleksandr Nikolich, Igor Kiselev, Vladimir Platonov +1
Offline reinforcement-learning losses (RFT, RIFT, DFT, Offline GRPO, DPO) are widely used to distill reasoning from large teachers into smaller students, and are typically compared…
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…