3 papers
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…
cs.CV2024
GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization
Gennady Sidorov, Malik Mohrat, Denis Gridusov +2
Although various visual localization approaches exist, such as scene coordinate regression and camera pose regression, these methods often struggle with optimization complexity or…