9 papers
Multimodal Evaluation of Russian-language Architectures
Artem Chervyakov, Ulyana Isaeva, Anton Emelyanov +15
Multimodal large language models (MLLMs) are currently at the center of research attention, showing rapid progress in scale and capabilities, yet their intelligence, limitations, a…
Logos as a Well-Tempered Pre-train for Sign Language Recognition
Ilya Ovodov, Petr Surovtsev, Karina Kvanchiani +2
This paper examines two aspects of the isolated sign language recognition (ISLR) task. First, although a certain number of datasets is available, the data for individual sign langu…
Un-Doubling Diffusion: LLM-guided Disambiguation of Homonym Duplication
Evgeny Kaskov, Elizaveta Petrova, Petr Surovtsev +4
Homonyms are words with identical spelling but distinct meanings, which pose challenges for many generative models. When a homonym appears in a prompt, diffusion models may generat…
HandReader: Advanced Techniques for Efficient Fingerspelling Recognition
Pavel Korotaev, Petr Surovtsev, Alexander Kapitanov +2
Fingerspelling is a significant component of Sign Language (SL), allowing the interpretation of proper names, characterized by fast hand movements during signing. Although previous…
Training Strategies for Isolated Sign Language Recognition
Karina Kvanchiani, Roman Kraynov, Elizaveta Petrova +3
Accurate recognition and interpretation of sign language are crucial for enhancing communication accessibility for deaf and hard of hearing individuals. However, current approaches…
RusCode: Russian Cultural Code Benchmark for Text-to-Image Generation
Viacheslav Vasilev, Julia Agafonova, Nikolai Gerasimenko +4
Text-to-image generation models have gained popularity among users around the world. However, many of these models exhibit a strong bias toward English-speaking cultures, ignoring…