The field of astronomical signal processing and implicit neural representations is witnessing significant advancements, driven by the development of innovative architectures and techniques. Researchers are exploring new ways to improve the classification and representation of astronomical objects, leveraging tools such as LSTM neural networks and wavelet decomposition. Notably, there is a growing interest in implicit neural representations, with studies focusing on the development of frameworks that can effectively model complex signals and images. These advancements have the potential to revolutionize various applications in astronomy and beyond. Noteworthy papers in this regard include:

• Compact neural networks for astronomy with optimal transport bias correction, which introduces a theory-driven framework for integrating wavelet decomposition with state-space modeling and multi-level bias correction.
• NSTR: Neural Spectral Transport Representation for Space-Varying Frequency Fields, which proposes a novel INR framework that explicitly models spatially varying local frequency fields.
• Scaling Implicit Fields via Hypernetwork-Driven Multiscale Coordinate Transformations, which introduces a new class of INRs that learn signal-adaptive coordinate transformations using a hypernetwork.