DynIMTS replaces static graphs with instance-attention that updates edge weights on the fly, delivering SOTA imputation and P12 classification accuracy for streaming irregular multivariate time series.

Tomatoes are an important vegetable crop worldwide, but their picking operations have long relied on manual labor, facing problems such as high labor intensity, high costs, and easy fruit damage. In protected tomato cultivation, fruits often grow in clusters with dense branches and leaves. Traditional mechanical picking equipment is prone to environmental interference, resulting in low picking success rates or high damage rates. How to achieve efficient and non-destructive picking of tomatoes in complex planting environments?

In the vast cotton fields of Xinjiang, plastic film covering technology has been a weapon for increasing yield—it conserves water, raises temperatures, and improves water utilization efficiency, significantly boosting cotton production in arid regions.

A research paper by scientists from Liaoning Cancer Hospital & Institute, The First Affiliated Hospital of Ningbo University, and other institutions proposed a hollow mesoporous carbon (HMC) nanoparticle prepared via the sacrificial template method, featuring a porphyrin-like structure that enables efficient singlet oxygen generation and synergistic sono-immunotherapy for pancreatic cancer.

The new research paper, published on May 9 in the journal Cyborg and Bionic Systems, presented the preparation, characterization, and therapeutic application of MOF-derived HMC nanoparticles, and demonstrated their potential to enhance sono-immunotherapy efficacy by inducing tumor cell apoptosis and activating the immune

 Anti-forgetting representation learning method reduces the weight aggregation interference on model memory and augments the representation performance.