Researchers have developed a new method to synthesize full-cycle biventricular motion from a single end-diastolic mesh. This task is challenging due to the spatial heterogeneity and phenotype dependency of cardiac deformation. The proposed framework integrates motion-informed functional parcellation with conditional latent flow, enabling region-specific and phenotype-adaptive synthesis. Experiments show consistent improvements in geometric accuracy and functional fidelity compared to existing methods. --- Why it matters: This work matters because it provides a more accurate and adaptive way to synthesize biventricular motion from limited data, which can be useful for medical imaging applications such as cardiac function analysis and disease diagnosis. Source: https://arxiv.org/abs/2608.19738