This dataset encompasses human preferences in text-to-video generation tasks along two primary dimensions: helpfulness and harmlessness.

Sequential decision-making problems typically require significant human supervision and data.

In this supplementary material, we first give additional details about the method in Sec. 1. Queries used for zero-shot semantic segmentation. We do this for all the annotated classes in the dataset (second column). One can see that, for example, class name'manmade' lacks descriptive specificity. In the text description of this class, we can find "... buildings, walls, guard rails, fences, poles, street signs, traffic lights ..." and more. Table 1: Queries used for zero-shot semantic segmentation.

Building upon this "motion vocabulary", we perform language modeling on both motion and text in a unified manner, treating human motion as a