The field of robotics and computer vision is moving towards more accurate and efficient pose estimation and control methods. Researchers are exploring new approaches to improve the accuracy and robustness of pose estimation, including the use of event-based cameras and machine learning algorithms. Additionally, there is a growing interest in developing more advanced control strategies for robotic systems, such as flexible manipulators and brachiation robots. These advancements have the potential to improve the performance and autonomy of robotic systems in various applications, including surgery, cultural heritage digitization, and industrial automation. Noteworthy papers include: VERNIER, an open-source software for pose estimation, which achieves high accuracy and robustness using phase-based local thresholding. Efficient Surgical Robotic Instrument Pose Reconstruction, which proposes a novel framework for pose estimation in real-world conditions using unified feature detection. Learning Efficient Meshflow and Optical Flow from Event Cameras, which presents a lightweight model for event-based meshflow estimation and achieves state-of-the-art performance.