DIG-Mol: A Contrastive Dual-Interaction Graph Neural Network for Molecular Property Prediction.

Molecular property prediction is a key component of AI-driven drug discovery and molecular characterization learning. Despite recent advances, existing methods still face challenges such as limited ability to generalize, and inadequate representation of learning from unlabeled data, especially for tasks specific to molecular structures. To address these limitations, we introduce DIG-Mol, a novel self-supervised graph neural network framework for molecular property prediction.

Nonlinear optical response of inverse-designed integrated photonic devices.

Gradient-based optimization combined with the adjoint method has been demonstrated to be an efficient way to design a nano-structure with a vast number of degrees of freedom. However, most inverse-designed photonic devices are applied as linear photonic devices. Here, we demonstrate the nonlinear optical response in inverse-designed integrated splitters fabricated on a SiN platform.

MoS hybrid integrated micro-ring resonator phase shifter based on a silicon nitride platform.

We demonstrate a low-power, compact micro-ring phase shifter based on hybrid integration with atomically thin two-dimensional layered materials, and experimentally establish a low-loss silicon nitride platform. Using a wet transfer method, a large-area few-layer MoS film is hybrid integrated with a micro-ring phase shifter, leading to a tuning efficiency of 5.8 pm V at a center wavelength of 1545.