Iaroslav Ponomarenko
Papers
2
Total Citations
21
H-Index
2
About
Iaroslav Ponomarenko is a rising researcher at the forefront of embodied AI and robotic manipulation, with a focus on bridging the gap between large language models and physical world interaction. His work centers on developing vision-language-action models that enable robots to understand and execute complex manipulation tasks with greater precision and common-sense reasoning. In his highly-cited 2024 paper, *ManipVQA*, Ponomarenko pioneered the injection of robotic affordance and physically grounded knowledge into Multi-modal Large Language Models (MLLMs), addressing a critical limitation where these models lacked robotics-specific understanding—a contribution that has already garnered 18 citations. He further advanced the field with *CrayonRobo* (2025), introducing an object-centric, prompt-driven framework that resolves ambiguities in task specification across language, images, and video. By tackling the challenge of how robots can interpret nuanced human instructions without over-specification, Ponomarenko is shaping the next generation of more intuitive and capable robotic systems. His work is essential reading for students and researchers interested in the intersection of computer vision, natural language processing, and robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2