The field of flow estimation and reconstruction is witnessing significant advancements with the development of innovative frameworks and methods. Researchers are focusing on improving the accuracy and efficiency of flow estimation, particularly in challenging environments and scenarios. One of the key directions is the integration of multimodal data and self-supervised learning techniques to enhance the robustness and generalization of flow estimation models. Another important area of research is the development of efficient and scalable methods for reconstructing high-frequency flow fields from sparse and noisy data. Noteworthy papers in this area include: LatentFlow, which proposes a novel cross-modal temporal upscaling framework for reconstructing high-frequency turbulent wake flow fields. DeltaFlow, which introduces a lightweight 3D framework for scene flow estimation that captures motion cues via a Δ scheme. Scene-Agnostic Traversability Labeling and Estimation via a Multimodal Self-supervised Framework, which proposes a multimodal self-supervised framework for traversability labeling and estimation. DoGFlow, which presents a novel self-supervised framework for LiDAR scene flow estimation via cross-modal Doppler guidance.