Nader Zantout

Carnegie Mellon University

Papers

2

Total Citations

4

H-Index

2

About

Nader Zantout is a rising researcher at the intersection of robotics, computer vision, and natural language processing, with a primary focus on enabling robots to understand and interact with 3D environments through language. His work centers on **referential grounding**—the challenge of mapping natural language descriptions to specific objects and locations in three-dimensional space. Zantout’s major contributions include the development of **SORT3D**, a spatial object-centric reasoning toolbox that leverages large language models for zero-shot 3D grounding, allowing robots to interpret complex spatial relations and attributes without task-specific training. He also introduced **IRef-VLA**, a benchmark designed to evaluate interactive referential grounding under imperfect, human-like language conditions—a critical step toward robust human-robot collaboration. Though early in his career, his 2025 publications have already garnered citations, signaling growing interest in his practical, benchmark-driven approach. Zantout’s work directly addresses the gap between high-level language understanding and low-level spatial reasoning, making him a key voice in the push toward general-purpose, language-guided robotics. His research is particularly relevant for students and engineers working on embodied AI, human-robot interaction, and multimodal perception systems.

Research Focus

Key Achievements

2
H-Index
2
Papers
4
Total Citations
2
Avg Citations/Paper
🏆 Most Cited Paper
SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models
2 citations · 2025
📈 Most Prolific Year: 2025 (2 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: Carnegie Mellon University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago