Skip to content
View VityaVitalich's full-sized avatar

Block or report VityaVitalich

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
VityaVitalich/README.md

Viktor Moskvoretskii.

AI Researcher focusing on Self-Improvement, LLM Trustworthiness and RL Methods. Full CV

πŸŽ“ Education

  • Ph.D. in Applied Mathematics and Informatics β€” EPFL, Lausanne (09.2025 - Present)
  • M.S. in Applied Mathematics and Informatics β€” HSE University, Moscow (09.2023 - 06.2025)
  • Diploma in Applied Mathematics and Informatics β€” MSU, Moscow (09.2021 - 06.2023)
  • B.S. in Neuroscience β€” HSE University, Moscow (09.2018 - 06.2022)

πŸ’Ό Positions

  • Research Engineer β€” Skoltech (07.2023 - Present)
  • Intern Researcher β€” DeepPavlov.ai (08.2022 - 06.2023)
  • Intern Researcher β€” HSE UX Lab (09.2019 - 03.2020)

πŸ“š Publications

For a complete list of publications, please visit:

πŸ“š Collaboration

If interested in collaboration, you may find my Research Proposals

Reach me via [email protected]

Pinned Loading

  1. TaxoLLaMA TaxoLLaMA Public

    [ACL 2024] TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Sematic Tasks

    Python 16 2

  2. STASC STASC Public

    [ICLR 2025 SSI-FM] Self-Taught Self-Correction for Small Language Models

    Jupyter Notebook 11 2

  3. MeritOpt MeritOpt Public

    [EMNLP 2024] Low-Resource Machine Translation through the Lens of Personalized Federated Learning

    Python 3

  4. s-nlp/AdaRAGUE s-nlp/AdaRAGUE Public

    [ACL 2025] Adaptive Retrieval without Self-Knowledge? Bringing Uncertainty Back Home

    Python 6

  5. GIFT_SW GIFT_SW Public

    Forked from On-Point-RND/GIFT_SW

    Code for Paper "GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLM"s

    Python

  6. SCoRe SCoRe Public

    TRL Reproduction of paper "Training Language Models to Self-Correct via Reinforcement Learning"

    Python 2 1