The field of 3D scene understanding and generation is rapidly evolving, with a focus on developing more sophisticated and accurate methods for generating and manipulating 3D environments. Recent research has emphasized the importance of incorporating semantic information and high-level scene understanding into these methods, enabling more effective and efficient generation of complex scenes. Notable advancements include the development of frameworks that integrate large language models and visual reasoning to improve scene generation and manipulation capabilities. Additionally, there has been significant progress in creating large-scale datasets and benchmarks to support the development and evaluation of these methods. Overall, the field is moving towards more advanced and realistic 3D scene generation and understanding capabilities. Noteworthy papers include: Real-Time Indoor Object SLAM with LLM-Enhanced Priors, which achieves robust data association and improves mapping accuracy by 36.8% over the latest baseline. SAGE: Scene Graph-Aware Guidance and Execution for Long-Horizon Manipulation Tasks, which proposes a novel framework for scene graph-aware guidance and execution in long-horizon manipulation tasks and achieves state-of-the-art performance on distinct tasks.