Marwa Bazzi
Papers
1
Total Citations
2
H-Index
1
About
Marwa Bazzi is a rising researcher at the intersection of robotics and machine learning, with a focus on in-context meta-learning and dynamics modeling for physical systems. Her most-cited work, "RoboMorph: In-Context Meta-Learning for Robot Dynamics Modeling" (2024), introduces a novel Transformer-based framework that enables robots to adapt their dynamics models on the fly from minimal data—a breakthrough for real-time control in unstructured environments. This paper, already garnering 2 citations in its first year, reflects her broader interest in leveraging advances from Natural Language Processing—specifically Transformer architectures—to solve complex physical problems, including partial differential equations and robotic vision. Bazzi’s contributions are particularly notable for bridging the gap between large-scale deep learning and practical robotics, offering a path toward more flexible, data-efficient autonomous systems. Her work has been recognized for its potential to reshape how robots learn and interact with the world, marking her as a promising voice in the growing field of foundation models for embodied AI.
Research Focus
Key Achievements
Top Papers
- 1RoboMorph: In-Context Meta-Learning for Robot Dynamics Modeling2 citations · 2024