Svetlana Ladanova

Moscow Institute of Physics and Technology

Papers

Total Citations

H-Index

About

Svetlana Ladanova is an emerging researcher specializing in 3D scene understanding, open-vocabulary object grounding, and autonomous agent perception — a field at the intersection of computer vision, natural language processing, and robotics. Her most notable contribution, "Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph," addresses a critical limitation in state-of-the-art CLIP-based methods: their inability to resolve ambiguous object descriptions that require contextual, relational reasoning within a scene. By leveraging 3D scene graphs, Ladanova's approach enables autonomous agents to ground natural language queries that go beyond simple, unambiguous object references — a significant leap toward more robust and human-like scene comprehension. The work has accumulated 13 citations across its 2024 and 2025 versions, reflecting rapid uptake within a competitive research community and signaling its relevance to ongoing challenges in embodied AI and robotics navigation. For students and researchers working on autonomous systems, semantic scene representation, or vision-language models, Ladanova's research offers a compelling framework for tackling the nuanced complexity of real-world object localization from natural language descriptions.