Delve into advanced concepts of state space modeling and inference in this comprehensive talk by Scott Linderman, Assistant Professor in the Statistics Department at Stanford University. Explore recent research developments, including structured variational autoencoders that combine deep neural networks with probabilistic state space models. Learn about new algorithms for inference in nonlinear state space models using sequential Monte Carlo with learned "twists." Discover cutting-edge work on simple state space layers achieving state-of-the-art performance in long-range sequence modeling for machine learning and neuroscience applications. This 90-minute presentation, delivered on March 29, 2023, builds upon the foundations established in Part I and offers valuable insights into modern state space model techniques.