In this post, we will try to connect Energy-Based Model with classical optimal control frameworks like Model-Predictive Control from the perspective of Lagrangian optimization.

In short, using diffusion process instead of directly applying MSE loss on trajectories enables a wider variety of trajectory solutions learnt from imitation data, instead of the trajectory provided by dataset(s), which is beneficial for small-set imitation learning. In this blog post, we will discuss how and why diffusion process can achieve such and trajectory-agnostic result.

The paper proposed a way of modeling interactive objects in a large-scale 3D space by making affordance predictions and inferring the articulation properties from the visual observations before and after the self-driven interaction.

This paper proposes a two-stage localization mechanism in city-scale NeRF.