This paper demonstrates a novel approach to recurrent neural networks using the natural spatiotemporal dynamics of light in multimode optical fibers. The system processes temporal data with high energy efficiency by leveraging passive light propagation and inherent optical nonlinearities, achieving competitive performance across diverse temporal and spatiotemporal learning tasks without trainable optical parameters.

This paper introduces SKYLIGHT, a scalable 3D photonic in-memory tensor core architecture that overcomes existing limitations in photonic computing through innovations in topology, wavelength routing, accumulation, and programming. It demonstrates superior throughput and energy efficiency for real-time AI inference compared to traditional electronic and prior photonic accelerators.

This paper proposes a novel three-dimensional framework—Source, Depth, and Scope—for categorizing the explanatory requirements of AI applications. This framework aims to standardize the definition of explainable AI, helping to match specific application needs with the capabilities of different machine learning techniques, thereby building trust in AI systems.

This paper introduces a transformer-based AI system utilizing the RT-DETR model to accurately detect fungal elements in potassium hydroxide (KOH) microscopy images for dermatophytosis, effectively distinguishing them from common artefacts. The system demonstrated high sensitivity and accuracy, suggesting its potential as a reliable automated screening tool in dermatomycology.

This paper argues that modularity is a fundamental computational principle underlying both natural and artificial intelligence. It reviews how modularity provides significant advantages in efficiency, generalization, and robustness across diverse fields like engineering, neuroscience, and AI, suggesting it as a core design principle for future intelligent systems.