Alexey K. Kovalev

Часть публикаций из профиля, по году от новых к старым. Это не полный список последних работ автора; работы без года — в конце.

• VLA Grounder: Language-Conditioning Space Optimization for Black-Box VLA Models2026 · аннотациясвернуть

  Vision-Language-Action (VLA) models are commonly treated as end-to-end action policies conditioned on natural-language task descriptions. In practice, however, their behavior often depends sharply on how the instruction…

• Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models2026
• $μ$VLA: On Recurrent Memory for Partially Observable Manipulation in VLA Models2026
• Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization2026
• Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning2026
• Evaluation of Pretrained Large Language Models in Embodied Planning Tasks2023
• Fine-Tuning Multimodal Transformer Models for Generating Actions in Virtual and Real Environments2023 · аннотациясвернуть

  In this work, we propose and investigate an original approach to using a pre-trained multimodal transformer of a specialized architecture for controlling a robotic agent in an object manipulation task based on language…

• Vector Semiotic Model for Visual Question Answering2021