Content not yet available

This lecture has no active video or poster.

AAAI 2026

January 24, 2026

Singapore, Singapore

Would you like to see your presentation here, made available to a global audience of researchers?
Add your own presentation or have us affordably record your next conference.

Differentiable simulators represent an environment’s dynamics as a differentiable function. Within robotics and autonomous driving, this property is used in Analytic Policy Gradients (APG), which relies on backpropagating through the dynamics to train accurate policies for diverse tasks. Here we show that differentiable simulation also has an important role in world modeling, where it can impart predictive, prescriptive, and counterfactual capabilities to an agent. Specifically, we design three novel task setups in which the differentiable dynamics are combined within an end-to-end computation graph not with a policy, but a state predictor. This allows us to learn relative odometry, optimal planners, and optimal inverse states. We collectively call these predictors Analytic World Models (AWMs) and demonstrate how differentiable simulation enables their efficient, end-to-end learning. In autonomous driving scenarios, they have broad applicability and can augment an agent’s decision-making beyond reactive control.

Downloads

Paper

Next from AAAI 2026

Vulnerability-Aware Robust Multimodal Adversarial Training
poster

Vulnerability-Aware Robust Multimodal Adversarial Training

AAAI 2026

+3
Tianlong Chen and 5 other authors

24 January 2026

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Presentations
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2025 Underline - All rights reserved