Dima Pozdeev

Hi :)

I am excited about applications and fundamentals of machine learning.

I am finishing my Masters degree in math and data science at TUM.
I did my undergrad in applied math and computer science at HSE University.

Feel free to reach out on X or via email if you want to chat.

I am looking for technical roles in ML / AI starting from October 2026.

           

profile photo

Research

As part of my master's thesis, I am currently researching new methods for tokenisation / representation learning / memory mechanisms for video data (I think all of these problems are closely related to each other).

DenseMarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks
Dmitrii Pozdeev, Alexey Artemov, Ananta R. Bhattarai, Artem Sevastopolsky
ICLR, 2026
project page / arXiv / video / code

Learning per-pixel 3D embeddings from in-the-wild head videos improves dense correspondences across subjects and poses, and boosts monocular head tracking.

To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning
Ildus Sadrtdinov*, Dmitrii Pozdeev*, Dmitry Vetrov, Ekaterina Lobacheva
NeurIPS, 2023
arXiv / X thread / code

How to improve ensembles in the transfer learning setup by exploring the target task loss landscape.

GG-Langevin teaser Generative Shape Reconstruction with Geometry-Guided Langevin Dynamics
Linus Härenstam-Nielsen, Dmitrii Pozdeev, Thomas Dagès, Nikita Araslanov, Daniel Cremers
arXiv, 2026
code / arXiv

Traversing diffusion model trajectories while enforcing measurement consistency at each step enables complete and realistic 3D shape reconstruction from partial observations.