The field of computer vision and graphics is rapidly advancing, with a growing focus on applications in scientific research. Recent developments have seen the integration of computer graphics and science, with techniques such as geometric reasoning and physical modeling being used to address challenges in data-scarce settings. Additionally, there has been a surge in research on multimodal reasoning, with applications in areas such as video action recognition and 3D scene synthesis. Notable papers in this area include a study on emergent symbolic mechanisms in vision language models, which sheds light on the mechanisms that support symbol-like processing in these models. Another noteworthy paper presents a novel framework for sign language video generation, which achieves state-of-the-art performance across various metrics. Overall, the field is moving towards more advanced and specialized applications, with a focus on developing techniques that can effectively integrate and process multiple sources of data.