Hi there 👋

I'm specializing in Natural Language Processing (NLP) and actively seeking exciting collaboration opportunities!

🎓 Education

• PhD in Artificial Intelligence, ITMO University (2024–Present)
• Master of Machine Learning and Data Analysis, HSE (2022–2024)
• Bachelor of Software Engineering, HSE (2018–2022)

💻 Professional Experience

• Laboratory Assistant, VK Lab (2023–2025) - NLP, research, sentence encoders.
• NLP Consultant, NDA (Outsourced Project, 2025) - developed and trained a classifier model for industry application.

🚀 Featured Projects

2023

• Simultaneous Determination of Ethnicity and Toxicity in Texts [Code]

2024

• Russian Joke Generation Model [Model] | [Code]

• USER: Universal Sentence Encoder for Russian

  • Master's Diploma Project (graded 8/10) [Diploma Text] | [Presentation]

  • ISSCAI Conference Poster [Poster] | [Certificate]

  • Achievements:

    • SOTA results on the Encodechka benchmark
    • Developed datasets: ru-HNP, ru-WANLI
    • Published models: USER-base, USER-bge-m3

• Pruned/shrinked bge-m3 model [Model] | [Code]

2025

• RuModernBert [Models][Post on Habr]
• USER2 [Models][Post on Habr]

🎤 Conferences:

• IDOConf: "Text-Level Distillation: How to Build Small but Powerful Sentence Encoders" [Thesis] | [Presentation]
• КМУ: "Большие языковые модели для работы с векторной графикой" [Thesis] | [Presentation]
• AINL: "Leveraging Large Language Models for Scalable Vector Graphics Processing: A Review" [Paper]
• Datafest: "RuModernBert и USER2: Эволюция русскоязычных энкодеров" [Presentation][Recording]

🛠 Skills

• Python, PyTorch, Transformers
• Basic SQL, Git
• English: B2 (Upper-Intermediate)

🌱 Community Involvement

• Teaching Assistant for the course "Software Engineering"

📫 Let's Connect!

• HuggingFace: TatonkaHF
• Email: btmalashenko@itmo.ru | quelquemath@gmail.com
• Telegram: @btmalov