The field of neuromorphic computing is moving towards more biological plausible models and energy efficient systems. Researchers are exploring new methods to integrate homeostatic mechanisms into spiking neural networks, allowing for more stable and adaptive systems.Additionally, there is a growing interest in developing event-based systems, which can provide faster and more efficient processing. These systems are being applied to a wide range of tasks, including image processing, control, and learning.Noteworthy papers include: Dynamic Weight Adaptation in Spiking Neural Networks Inspired by Biological Homeostasis, which proposes a novel mechanism for adapting network weights in real time. Temporal-adaptive Weight Quantization for Spiking Neural Networks, which achieves high energy efficiency while maintaining accuracy. Learning Scalable Temporal Representations in Spiking Neural Networks Without Labels, which enables large SNN architectures to be optimized without labeled data. Realizing Fully-Integrated, Low-Power, Event-Based Pupil Tracking with Neuromorphic Hardware, which demonstrates a wearable pupil-center-tracking system with complete on-device integration. Event-driven eligibility propagation in large sparse networks, which presents a biologically plausible extension of the eligibility propagation learning rule for recurrent spiking networks.