The cellular functions are executed by biological macromolecular complexes in nonequilibrium dynamic processes, which exhibit a vast diversity of conformational states. Solving conforma-tional continuum of important biomolecular complexes at atomic level is essential to understand their functional mechanisms and to guide structure-based drug discovery. In this talk, I will discuss on our recent development of a deep manifold learning framework, named AlphaCryo4D, which enables atomic-level cryogenic electron microscopy (cryo-EM) reconstructions that approximately visualize conformational space of biomolecular complexes of interest. AlphaCryo4D integrates 3D deep residual learning with manifold embedding of pseudo-energy landscapes, which simultaneously improves 3D classification accuracy and reconstruction resolution via an energy-based particle-voting algo-rithm. By applications of this approach to analyze several simulated and experimental datasets, we demonstrate its generality in breaking resolution barrier of visualizing dynamic components of functional complexes, in choreographing continuous inter-subunit motions and in exploring their hidden conformational space inaccessible to conventional methods. Integration of our machine-learning approach with time-resolved cryo-EM further allows visualization of conforma-tional continuum in nonequilibrium regime at atomic level, thus paving the way for therapeutic discovery against highly dynamic biomolecular targets.