The field of neural adaptation and brain-inspired computing is moving towards the development of more biologically plausible and robust models. Researchers are exploring new approaches to address the limitations of existing models, such as noise sensitivity and unbounded synaptic weight growth. One of the key directions is the integration of nonlinear plasticity models, which can provide enhanced noise robustness and critical thresholds for synaptic regulation. Another area of focus is the development of brain-inspired learning frameworks, such as Equilibrium Propagation, which can enable rapid convergence and improved performance in artificial intelligence applications. Additionally, there is a growing interest in designing artificial neural networks that incorporate principles from systems neuroscience, such as sparse and modular connectivity, to improve efficiency and accuracy. Noteworthy papers in this area include: Allee Synaptic Plasticity and Memory, which proposes a nonlinear plasticity model with biologically inspired weight stabilization mechanisms. Toward Practical Equilibrium Propagation, which develops a biologically plausible Feedback-regulated REsidual recurrent neural network that substantially enhances the applicability and practicality of Equilibrium Propagation. Neuro-inspired Ensemble-to-Ensemble Communication Primitives for Sparse and Efficient ANNs, which introduces a novel architecture that imposes sparse, modular connectivity across feedforward layers and achieves superior accuracy on standard vision benchmarks.