The field of 3D editing and generation is rapidly evolving, with a focus on developing innovative methods for consistent and efficient editing of 3D scenes. Recent developments have centered around improving the accuracy and coherence of edits, particularly in the context of multi-view and dynamic 3D scenes. Researchers are exploring new approaches to enforce cross-view consistency, incorporating semantic similarity and geometric alignment to produce high-quality, detailed edits. Additionally, there is a growing interest in generative models for 4D scene representation, enabling efficient and scalable solutions for image-to-4D generation and novel-view video synthesis. Noteworthy papers in this area include CoreEditor, which introduces a correspondence-constrained attention mechanism for consistent text-to-3D editing, and 4DNeX, which presents a feed-forward framework for generating 4D scene representations from a single image. Other notable works include Sketch3DVE, which enables sketch-based 3D-aware scene video editing, and Tinker, which delivers robust, multi-view consistent edits from sparse inputs without per-scene optimization.