The field of multimodal reasoning and perception is witnessing significant developments, with a focus on enhancing the ability of models to understand and process multiple forms of data, such as images, audio, and text. Researchers are exploring new architectures and techniques to improve the performance of multimodal models, including the use of chain-of-thought reasoning, latent space reasoning, and interleaved vision-language reasoning. These advancements have the potential to improve the accuracy and robustness of multimodal models, enabling them to better capture the complexities of real-world data. Noteworthy papers in this area include: Ovis2.5, which integrates a native-resolution vision transformer and strengthens reasoning capabilities, and Thyme, which enables MLLMs to transcend existing 'think with images' approaches by autonomously generating and executing diverse image processing and computational operations via executable code. Additionally, Simple o3 and Multimodal Chain of Continuous Thought are also making significant contributions to the field.