Maxim Monastyrny

Russian State Scientific Center for Robotics and Technical Cybernetics

Papers

Total Citations

H-Index

About

Maxim Monastyrny is a researcher advancing the frontier of 3D scene understanding and open-vocabulary object grounding. His work focuses on enabling autonomous agents to interpret complex, ambiguous natural language queries within three-dimensional environments. Monastyrny’s major contribution, "Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph" (2025, 11 citations), tackles a critical limitation in existing CLIP-based methods: while these approaches handle simple object descriptions, they fail when queries require reasoning about object relationships, attributes, or context. By integrating 3D scene graphs with open-vocabulary learning, Monastyrny’s framework allows agents to resolve ambiguous descriptions—such as "the red mug next to the laptop"—by leveraging spatial and semantic relationships. This work bridges the gap between raw perception and contextual understanding, a key step toward robust embodied AI. Though early in his career, his research has already garnered attention for its practical implications in robotics, autonomous navigation, and human-robot interaction. Monastyrny’s approach promises to make AI systems more intuitive and responsive to natural human commands, marking him as a rising voice in 3D vision and language grounding.