The field of 3D world modeling is witnessing significant advancements, driven by the development of innovative generative models and large language models. Researchers are exploring new approaches to create realistic and interactive 3D environments, with a focus on improving computational efficiency, controllability, and fidelity. One notable direction is the integration of multimodal inputs, such as textual descriptions and visual instructions, to generate dynamic and immersive worlds. Another area of interest is the development of frameworks that streamline the production pipeline of 3D environments, enabling faster and more efficient creation of high-quality virtual worlds. Noteworthy papers include: OccTENS, which proposes a generative occupancy world model that enables controllable and high-fidelity long-term occupancy generation. LatticeWorld, which presents a multimodal large language model-empowered framework for interactive complex world generation, achieving superior accuracy and efficiency in scene layout generation and visual fidelity.