An innovative set-level adversarial learning method to improve domain adaptation
Peer-Reviewed Publication
Updates every hour. Last Updated: 12-Jun-2026 10:15 ET (12-Jun-2026 14:15 GMT/UTC)
Domain adaptation remains a significant challenge in artificial intelligence, especially when models trained in one domain are required to perform well in another.
A groundbreaking artificial intelligence model has achieved unprecedented accuracy in tropical cyclone intensity prediction, marking a significant advancement in weather forecasting technology. The new system, known as Prithvi-TC, addresses one of the most challenging aspects of meteorological forecasting - predicting tropical cyclone (TC) intensity and rapid intensification events. This advancement comes at a crucial time, as climate change continues to influence the frequency and intensity of tropical cyclones worldwide.
Researchers from Beihang University have conducted a comprehensive bibliometric analysis to identify evolving trends and challenges in evaluating research talent at Chinese universities.
Entity resolution (ER) aims to identify and match records referring to the same entity from multiple data sources, which is a crucial task in data integration. Traditional methods rely on structured data and require extensive manual labeling for better performance, limiting their effectiveness for long-text, unstructured data scenarios, while directly apply LLM for ER occurs with hallucination results with factual error.
Mobile CrowdSensing (MCS) has become a powerful sensing paradigm for information collection recently. As sensing becomes more complicated, it is beneficial to deploy edge servers between users and the cloud center with a so-called mobile edge computing.
Researchers at Shanghai Jiao Tong University have made a groundbreaking discovery in the field of Temporal Knowledge Graphs (TKGs), challenging the conventional reliance on graph-based techniques and proposing a novel approach that prioritizes historical temporal information.
Aqueous zinc (Zn) metal batteries (AZMBs) have distinct advantages in terms of safety and cost-effectiveness. However, the industrial application of AZMBs is currently not ready due to challenges of Zn dendrite growth and the side reactions such as hydrogen evolution reaction (HER) on the Zn anodes. In this review, we discuss how inorganic interfaces impact the Zn2+ plating/stripping reaction and overall cell performance. The discussion is categorized based on the types of inorganic materials, including metal oxides, other metal compounds, and inorganic salts. The proposed protection mechanisms for Zn metal anodes are highlighted, with a focus on the dendrite and HER inhibition mechanisms facilitated by various inorganic materials. We also provide our perspective on the rational design of advanced interfaces to enable highly reversible Zn2+ plating/stripping reactions toward highly stable AZMBs, paving the way for their practical implementation in energy storage.
"Welcome to the world of RDHNet, a groundbreaking approach to multi-agent reinforcement learning (MARL) introduced by Dongzi Wang and colleagues from the College of Computer Science at the National University of Defense Technology.
Single-cell analyses have emerged as powerful tools for studying cellular heterogeneity and gene regulation. Single-cell chromatin accessibility sequencing (scCAS) is a key technology that enables the analysis of chromatin accessibility at the resolution of individual cells.