Dima Pozdeev

Hi :)

Currently, I am pursuing MS degree in Math and Data Science at Technical University of Munich (TUM).

I received BS in Computer Science at HSE University, where I worked on transfer learning and ensembles with Ekaterina Lobacheva and Dmitry Vetrov.

If you'd like to chat, feel free to reach out on X or via email.

P.S. I am attending ICLR 2026 in Rio de Janeiro, feel free to connect there ☕

I will be available for Machine Learning roles starting October 2026.

           

profile photo

Research

Currently, I am researching video pretraining methods and the representations they learn as part of my master's thesis at TUM.

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.

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.