We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the solution of a latent stochastic differential equation (SDE).

This bound guides the design of an optimal exploration policy attaining minimal sample complexity. However, this lower bound involves solving a hard non-convex optimization problem.

The goal of this work is to advance research on video generation methods. A.2 Experimental Results on Long Video Generation T asks All experiments are conducted without conditional inputs. The detailed settings of model hyper parameters are presented in Table 4.