Svyatoslav Pchelintsev

Moscow Institute of Physics and Technology

Papers

Total Citations

H-Index

About

Svyatoslav Pchelintsev is a researcher advancing the intersection of large language models (LLMs) and robotics, with a primary focus on autonomous task planning and visual feedback integration. His most notable contribution is the development of **LERa (Look, Explain, Replan)** , a Visual Language Model-based replanning framework that enables robots to adapt to real-world changes and failures by incorporating visual feedback into instruction following. This work, published in 2025, addresses a critical limitation of LLM-based robotics—their over-reliance on static textual inputs—by allowing systems to "look" at their environment, "explain" discrepancies, and "replan" actions accordingly. While still early in its citation trajectory (2 citations), LERa represents a significant step toward more resilient, context-aware autonomous agents. Pchelintsev’s research sits at the nexus of computer vision, natural language processing, and robotics, aiming to bridge the gap between high-level language instructions and low-level physical execution. His work is particularly relevant for students and researchers interested in embodied AI, human-robot interaction, and the practical deployment of LLMs in dynamic, unpredictable settings.