“…The existence of multiple valid futures for a given observed sequence is a crucial attribute of several forecasting tasks, especially surrounding the dynamics of low-level human behavior. These tasks include the forecasting of trajectories of pedestrians [1][2][3][4][5], vehicles [6][7][8][9], and autonomous robots [10,11], or other more general nonverbal cues of humans [12][13][14][15][16] and artificial virtual agents [17] in group conversation settings. Consequently, rather than making point predictions, several machine learning methods in these settings have attempted to forecast a distribution over plausible futures [5,12].…”