William Dwight Whitney
Papers
1
Total Citations
7
H-Index
1
About
William Dwight Whitney is a pioneering researcher at the intersection of machine learning and physical simulation, with a primary focus on learning rigid-body dynamics and interactive physical systems. His most notable contribution is the development of "face interaction graph networks," a novel approach that enables graph neural networks (GNNs) to accurately simulate rigid collisions among arbitrary shapes—a problem long considered notoriously difficult due to complex geometry and strong non-linearities. This work, published in 2022, has already garnered 7 citations, signaling its growing influence in the computational physics and AI communities. Whitney's research addresses a critical gap in learned simulation, where GNN-based models have excelled at fluids, cloth, and articulated bodies but struggled with rigid interactions. By introducing a method that captures face-level contact dynamics, he has opened new possibilities for robotics, computer graphics, and engineering design. His work stands out for its elegant integration of geometric reasoning with deep learning, offering a scalable path toward realistic, data-driven physical simulation. Whitney's contributions are shaping the future of interactive AI systems that must understand and predict the physical world.
Research Focus
Key Achievements
Top Papers
- 1Learning rigid dynamics with face interaction graph networks7 citations · 2022