The field of computer vision is witnessing significant advancements with the introduction of Mamba-based architectures. These innovative models are being applied to various tasks such as atmospheric turbulence removal, burst image super-resolution, and event-based video reconstruction, leading to improved performance and efficiency. The use of Mamba-based architectures is enabling researchers to overcome traditional limitations and achieve state-of-the-art results. Notably, these models are being designed to preserve spatio-temporal locality, retain robust global modeling capabilities, and balance computational efficiency with information integration. Overall, the integration of Mamba-based architectures in computer vision is pushing the boundaries of what is possible in this field. Noteworthy papers include: MAMAT, which achieves up to a 3% improvement in visual quality and a 15% boost in object detection accuracy. Burst Image Super-Resolution with Mamba, which introduces a novel Mamba-based architecture for burst image super-resolution, achieving SOTA performance on public benchmarks. EventMamba, which enhances spatio-temporal locality with state space models for event-based video reconstruction, drastically improving computation speed and delivering superior visual quality. EBS-EKF, which proposes a novel algorithm for event-based star tracking, demonstrating an order-of-magnitude improvement in accuracy compared to existing methods.