Graph neural networks have been used in various graph-related tasks, where they have achieved excellent performance. However, incomplete graph structures, commonly found in real-life scenarios, can severely degrade performance. In a new study, researchers develop a novel graph completion network that reconstructs missing features and structure simultaneously while also maintaining performance with extremely weak supervision, which is difficult to achieve with conventional models.

Tokyo, Japan – Researchers from Tokyo Metropolitan University have used an evolutionary algorithm to identify optimal shapes for ultra-thin, bio-inspired corrugated airfoils, the two-dimensional cut-throughs of wings. Lightweight membrane-like wings are a strong contender for use in unmanned aerial vehicles (UAVs) in thin atmospheres, like on Mars, and in UAV miniaturization. By using a “zero-thickness” model, they were able to focus on the effect of the airfoil corrugation pattern without the influence of a wing’s leading-edge thickness and shape. They discovered designs which were optimized for minimal drag or maximal lift.

A review, published on September 11 in Cyborg and Bionic Systems by researchers at Tianjin University, summarizes recent advances in intracortical microstimulation (ICMS), a technique that uses tiny electrodes implanted in the brain to activate specific groups of neurons. The researchers discuss how ICMS has evolved from a tool for mapping brain function into a potential technology for sensory feedback, information delivery, closed-loop neuromodulation and biointegrated neural interfaces.

Brain–computer interfaces are increasingly being explored as a way to restore lost functions or provide new channels for communication between the nervous system and electronic devices. While much BCI research focuses on reading neural signals, ICMS provides the complementary ability to write information back into the brain.

“ICMS has emerged as a prominent invasive modality capable of activating intracortical neuronal populations with high precision,” the researchers write. The technology can potentially replace or supplement natural sensory inputs, probe

dysfunctional neural circuits and influence behavior.

Five University of Texas at Dallas faculty members received 2026 Faculty Early Career Development Program (CAREER) awards from the National Science Foundation to support research aimed at making computer networks more resilient, developing next-generation electronics, strengthening software security and advancing mathematical understanding of complex systems.

The recipients of the five-year awards are Dr. Waseem Abbas, assistant professor of systems engineering; Dr. Sourav Dutta, assistant professor of electrical and computer engineering; Dr. Kirill Lazebnik, assistant professor of mathematical sciences; Dr. Kyle McCall, assistant professor of materials science and engineering; and Dr. Xinda Wang, assistant professor of computer science.