Iaroslav Chelombitko is a researcher specializing in Natural Language Processing, with a focus on tokenization, low-resource languages, and their application in computational linguistics and bioinformatics. He complements his academic work with over three years of industry experience as a Machine Learning Engineer and Product Owner, with prior experience at JetBrains.

Iaroslav earned his B.Sc. in Applied Computer Science with distinction from a joint program of Neapolis University Pafos and JetBrains Academy. His research, published in top-tier conferences like ICLR and ACL, includes developing novel tokenization frameworks and analyzing primate genomes using Byte-Pair Encoding. He actively collaborates with European universities, presents his findings at international venues, and contributes to the academic community as a peer reviewer and an active member of the ACL Special Interest Group on Uralic Languages (SIGUR).

Research Areas: LLMs, NLP, Tokenizers, Low-Resource Languages, Computational Linguistics, Bioinformatics