Vladimir Malinovskii

I am an incoming PhD student at Carnegie Mellon University (Fall 2026), where I will be advised by Tim Dettmers.

I am currently a Machine Learning Engineer at Together AI, based in the Netherlands. Previously, I worked on large language model quantization at Yandex Research. I hold a Master's degree in Computer Science from the Higher School of Economics (HSE), through a joint program with the Yandex School of Data Analysis, and a Bachelor of Science in Applied Mathematics and Physics from the Moscow Institute of Physics and Technology (MIPT).

Email  /  Scholar  /  Github  /  Linkedin  /  X

profile photo

Projects

AQLM.rs: Llama-3.1-8B in your Browser

Chat with local compressed Llama-3.1-8B fully in your browser, with no server and no GPU.

Demo  |  About  |  Source

Publications

PV‑Tuning: Beyond Straight‑Through Estimation for Extreme LLM Compression

Vladimir Malinovskii*, Denis Mazur*, Ivan Ilin*, Denis Kuznedelev, Konstantin Burlachenko, Kai Yi, Dan Alistarh, and Peter Richtarik

NeurIPS, 2024, Oral  |  Arxiv  |  Code

Pushing the Limits of Large Language Model Quantization via the Linearity Theorem

Vladimir Malinovskii, Andrei Panferov, Ivan Ilin, Han Guo, Peter Richtarik, Dan Alistarh

NAACL, 2025  |  Arxiv

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models

Alina Shutova, Vladimir Malinovskii, Vage Egiazarian, Denis Kuznedelev, Denis Mazur, Nikita Surkov, Ivan Ermakov, Dan Alistarh

ICML, 2025  |  Arxiv