SRNNs are able to automatically identify discrete states with distinct nonlinear neural dynamics.

In this paper, we find, supported by both theoretical analysis and empirical evidence, that score-based methods with exact search can naturally address the issues of deterministic relations under rather mild assumptions. Nonetheless, exact score-based methods can be computationally expensive.

This paper introduces a novel prior called Diversified Block Sparse Prior to characterize the widespread block sparsity phenomenon in real-world data.

ASNPE brings an active learning scheme into the inference loop to estimate the utility of simulation parameter candidates to the underlying probabilistic model.

Intelligent agents must be generalists, capable of quickly adapting to various tasks.

Full experimental details are provided in Appendix C.