4 citations · 6 across the 4 of their papers we have counts for
5 papers
RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models
Dmitrii Kharlapenko, Sergei Bratchikov, Konstantin Korolev +1
On modern production text-to-image systems, successful policy violations are rare, and previously effective human-written seeds are often patched out. Current automated red-teamers…
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…
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…
Emojich -- zero-shot emoji generation using Russian language: a technical report
Alex Shonenkov, Daria Bakshandaeva, Denis Dimitrov +1
This technical report presents a text-to-image neural network "Emojich" that generates emojis using captions in Russian language as a condition. We aim to keep the generalization a…