9 June 2024 in Physica Status Solidi (RRL) – Rapid Research Letters
The highly promising linear and nonlinear optical properties of innovative thin films of GeSe1–xTex chalcogenide materials in the amorphous as‐deposited state, and after crystallization, are revealed here. These innovative alloys bridge the gap between two families of materials: chalcogenide glasses (GeSe) and phase‐change materials (GeTe). Their unique optical properties make them attractive candidates for reconfigurable and nonlinear photonic applications in the infrared. In this context, it is shown how, by varying the Te content of GeSe1–xTex thin films, it is possible to tailor their linear and nonlinear optical properties to optimize them for a wide range of innovative applications.
4 June 2026 in Nature Photonics
17 June 2026 in Communications Engineering
The physical scaling of photonic matrix-vector multiplication hardware for deep neural network acceleration is fundamentally limited by accumulated optical losses, crosstalk noise, and the prohibitive footprint of conventional devices such as Mach-Zehnder interferometers. Here we present LightPro, a fully programmable linear photonic processor designed to optimize scalability, power efficiency, and area footprint. At its core, our architecture integrates a neural architecture search and pruning framework with tunable phase-change material directional couplers. By thermally modulating the phase-change material state, we dynamically adjust coupling coefficients to achieve precise splitting ratios, facilitating highly optimized topologies for matrix-vector multiplication operations. The underlying phase-change material-based devices are evaluated using numerical multiphysics simulations and compact models, which are validated against reported experimental data from prior work. System-level evaluations demonstrate that the neural architecture search-optimized LightPro architectures achieve up to an 85% footprint reduction and a greater than 50% decrease in power consumption. Network scaling evaluations using handwritten digit and Gaussian datasets yield an inference accuracy degradation of less than 5%. Experimental prototyping on a commercial photonic processor validates the computational accuracy of LightPro, establishing a scalable and efficient pathway for next-generation photonic artificial intelligence accelerators.