The field of text-to-video generation is moving towards more precise control over text elements and animated graphics. Researchers are exploring novel approaches to extend static graphic layouts with temporal dynamics, enabling fine-grained video control through hierarchical visual elements. This direction has significant implications for applications such as video advertisements and educational videos. Noteworthy papers in this area include: Generating Animated Layouts as Structured Text Representations, which introduces a novel approach to extend static graphic layouts with temporal dynamics, and T2VTextBench, which provides a human-evaluation benchmark for evaluating on-screen text fidelity and temporal consistency in text-to-video models.