Madhavan Iyengar
Papers
3
Total Citations
67
H-Index
2
About
Madhavan Iyengar is a rising star in embodied AI and 3D vision, whose work is redefining how robots perceive and interact with the physical world through language. His primary research focuses on 3D visual grounding—the ability for robots to locate objects and navigate spaces based on complex, open-vocabulary language instructions. Iyengar’s major contribution is the development of **LLM-Grounder**, a pioneering framework that leverages large language models (LLMs) as intelligent agents to parse natural language queries and ground them in 3D scenes without requiring extensive labeled data. This work, which has already garnered over 60 citations, directly addresses a critical bottleneck in household robotics: handling ambiguous or complex user commands. Building on this, he introduced **3D-GRAND**, a million-scale dataset designed to train 3D-LLMs with better grounding and reduced hallucination, a significant step toward reliable, real-world deployment. Iyengar’s research is not only technically innovative but also practically impactful, bridging the gap between high-level language understanding and low-level spatial reasoning. His work is essential reading for anyone interested in the future of intelligent, language-driven robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3