Adding dynamics and force reasoning to generative 3-D models is essential for applications like architecture and robotics. The team explores two pathways: attaching physical properties directly to splats and distilling classical physics engine simulations into neural weights. Accurate physics remains a hard problem, especially when models must generalise to unseen forces.
View full episode →“Attaching mass and spring properties to splats enables physics simulation”
“Hybrid pipelines can distill classical physics engine data into neural weights”
“Robotics suffers from data starvation; high‑fidelity synthetic worlds fill the gap”