M. Chandraker

LDR achieves unprecedented extrapolation of learned dynamics in video models, outperforming traditional methods by a staggering margin in both accuracy and efficiency.

Expert-driven procedural material generation reduces editing needs and aligns closely with professional design practices, outperforming traditional methods.

Task-aligned simulated futures can dramatically improve robot policy learning, yielding superior performance in complex manipulation tasks.

Control over physical properties like friction and restitution in generated videos is now possible, paving the way for more realistic and controllable video synthesis.

Real-time autonomous driving with language models is now possible, achieving 3x speedup and state-of-the-art performance by combining learned and rule-based planning.