Physics-informed AI learns local rules behind flocking and collective motion behaviors

Researchers at Seoul National University and Kyung Hee University report a framework to control collective motions, such as ring, clumps, mill, flock, by training a physics-informed AI to learn the ...
decrypt

Monero '51% Attackers' Qubic Release AI Model—But It Can't Do Basic Math Yet

Qubic has given AIGarth, the AI model it has been training while it attacked privacy blockchain Monero, a social media account. AIGarth has faced public ridicule after it failed to solve basic math ...
IEEE

Causal Disentangled Graph Neural Network for Fault Diagnosis of Complex Industrial Process

Abstract: Graph neural networks (GNNs) are good at capturing the intricate topologies and dependencies among components and are outstanding in fault diagnosis tasks of complex industrial process. Bias ...
IEEE

A Survey on Deep Neural Network Pruning: Taxonomy, Comparison, Analysis, and Recommendations

Abstract: Modern deep neural networks, particularly recent large language models, come with massive model sizes that require significant computational and storage ...
The Hacker News

Ukrainian Network FDN3 Launches Massive Brute-Force Attacks on SSL VPN and RDP Devices

Cybersecurity researchers have flagged a Ukrainian IP network for engaging in massive brute-force and password spraying campaigns targeting SSL VPN and RDP devices between June and July 2025. The ...
C&EN

Molecular Simulations with a Pretrained Neural Network and Universal Pairwise Force Fields

Creative Commons (CC): This is a Creative Commons license. Attribution (BY): Credit must be given to the creator. Machine Learning Force Fields (MLFFs) promise to enable general molecular simulations ...