Damian Mrowca
Papers
1
Total Citations
91
H-Index
1
About
Damian Mrowca is a leading researcher at the intersection of artificial intelligence, cognitive science, and computational neuroscience, best known for his pioneering work in building neural networks that learn intuitive physics. His most influential contribution, the 2018 paper "Flexible Neural Representation for Physics Prediction" (91 citations), introduced a hierarchical, particle-based object representation that allows AI systems to model complex physical dynamics—from rigid bodies to deformable materials—with remarkable flexibility. This work bridges the gap between human-like physical reasoning and machine learning, demonstrating how neural networks can capture multi-level structural interactions in dynamic environments. Mrowca’s research has profound implications for robotics, where machines must predict object behavior in real time, and for understanding how the brain represents the physical world. By enabling AI to reason about physics with the nuance of human intuition, his contributions have shaped a new generation of models that learn to simulate and predict interactions, earning him recognition as a key innovator in embodied intelligence and cognitive modeling.
Research Focus
Key Achievements
Top Papers
- 1Flexible Neural Representation for Physics Prediction91 citations · 2018