Andrei Polubarov

PhD student, Innopolis University

Joined

September 2024

Names

Andrei Polubarov (Preferred)

Andrey Polubarov

Emails

****@mail.ru (Confirmed)

****@skoltech.ru (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

PhD student

Innopolis University (innopolis.university)

2024 – 2028

Researcher

Artificial Intelligence Research Institute (airi.net)

2024 – 2025

Advisors, Relations & Conflicts

Coauthor

Viacheslav Sinii

2025 – Present

Coauthor

Igor Kiselev

2025 – Present

Coworker

Ilya Zisman

2024 – Present

Coworker

Alexander Nikulin

2024 – Present

Coworker

Denis Tarasov

2024 – Present

Coworker

Lyubaykin Nikita

2024 – Present

Coworker

Vladislav Kurenkov

2024 – Present

PhD Advisor

Ivan Oseledets

2024 – Present

Coworker

Alexander Derevyagin

2024 – Present

Coworker

Albina Klepach

2024 – Present

Expertise

Reinforcement Learning

Present

Reccomender Systems

Present

NLP

Present

Publications

Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner
Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin, Artyom Grishin, Igor Saprygin, Aleksandr Serkov, Mark Averchenko, Daniil Tikhonov, Maksim Zhdanov, Alexander Nikulin, Ilya Zisman, Albina Klepach, Alexey Zemtsov, Vladislav Kurenkov
- ICLR 2026 Poster
- Readers: Everyone
N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs
Ilya Zisman, Alexander Nikulin, Viacheslav Sinii, Denis Tarasov, Lyubaykin Nikita, Andrei Polubarov, Igor Kiselev, Vladislav Kurenkov
- Submitted to ICLR 2026
- Readers: Everyone
Vision-Language Models Unlock Task-Centric Latent Actions
Alexander Nikulin, Ilya Zisman, Albina Klepach, Denis Tarasov, Alexander Derevyagin, Andrei Polubarov, Lyubaykin Nikita, Vladislav Kurenkov
- Submitted to ICLR 2026
- Readers: Everyone
Yes, Q-learning Helps Offline In-Context RL
Denis Tarasov, Alexander Nikulin, Ilya Zisman, Albina Klepach, Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin, Igor Kiselev, Vladislav Kurenkov
- Submitted to ICLR 2026
- Readers: Everyone
Vision-Language Models Unlock Task-Centric Latent Actions
Alexander Nikulin, Ilya Zisman, Albina Klepach, Denis Tarasov, Alexander Derevyagin, Andrei Polubarov, Lyubaykin Nikita, Vladislav Kurenkov
- SEA @ NeurIPS 2025 Poster
- Readers: Everyone
Vision-Language Models Unlock Task-Centric Latent Actions
Alexander Nikulin, Ilya Zisman, Denis Tarasov, Albina Klepach, Alexander Derevyagin, Andrei Polubarov, Lyubaykin Nikita, Vladislav Kurenkov
- CoRL 2025 Robot Data Workshop
- Readers: Everyone
NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows
Denis Tarasov, Alexander Nikulin, Ilya Zisman, Albina Klepach, Lyubaykin Nikita, Andrei Polubarov, Alexander Derevyagin, Vladislav Kurenkov
- NeurIPS 2025 Workshop EWM
- Readers: Everyone
NinA: Normalizing Flows in Action. Training VLA Models with Normalizing Flows
Denis Tarasov, Alexander Nikulin, Ilya Zisman, Albina Klepach, Lyubaykin Nikita, Andrei Polubarov, Alexander Derevyagin, Vladislav Kurenkov
- SpaVLE Poster
- Readers: Everyone
N-Gram Induction Heads for In-Context RL: Improving Stability and Reducing Data Needs
Ilya Zisman, Alexander Nikulin, Viacheslav Sinii, Denis Tarasov, Lyubaykin Nikita, Andrei Polubarov, Igor Kiselev, Vladislav Kurenkov
- PUT at ICML 2025 Poster
- Readers: Everyone
Object-Centric Latent Action Learning
Albina Klepach, Alexander Nikulin, Ilya Zisman, Denis Tarasov, Alexander Derevyagin, Andrei Polubarov, Lyubaykin Nikita, Vladislav Kurenkov
- WRL@ICLR 2025 Poster
- Readers: Everyone

View all 23 publications

Andrei Polubarov

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

Co-Authors