collaborators

5 papers

cs.LG2026

A Model with No Head and Many Thoughts

Nikita Koriagin, Yaroslav Aksenov, George Bredis +3

Large language models decode by projecting hidden states through a large vocabulary head at every step. This operation is computationally costly and forces all reasoning to be expr…

cs.LG2026

Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control

Ruslan Rakhimov, George Bredis, Yuriy Maksyuta +1

Joint-Embedding Predictive Architectures (JEPAs) underpin a growing family of latent world models for control from raw pixels, but every existing JEPA world model commits at traini…

cs.LG2026

Rank-Then-Act: Reward-Free Control from Frame-Order Progress

Yuriy Maksyuta, George Bredis, Ruslan Rakhimov +1

We introduce Rank-Then-Act (RTA), a framework for learning control policies from expert video demonstrations without environment rewards. RTA trains a Vision-Language Model (VLM) o…

cs.LG2026

Next Embedding Prediction Makes World Models Stronger

George Bredis, Nikita Balagansky, Daniil Gavrilov +1

Capturing temporal dependencies is critical for model-based reinforcement learning (MBRL) in partially observable, high-dimensional domains. We introduce NE-Dreamer, a decoder-free…

cs.LG2025

Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success

George Bredis, Stanislav Dereka, Viacheslav Sinii +2

Interactive multimodal agents must convert raw visual observations into coherent sequences of language-conditioned actions -- a capability that current vision-language models (VLMs…