CybAI news

(symbiot/Shutterstock) The European Union’s Artificial Intelligence Act went into effect on August 1, becoming one of the first laws to implement broad regulation of AI applications. While all elements of the law are not yet being enforced, the new law is generating plenty of questions. The AI Act, which was initially proposed to the European Commission in 2021, was formally approved by European Parliament in March of this year. Like the General Data Protection Regulation (GDPR) law that came before it, the AI Act harmonizes existing AI laws among members of the European Union, while introducing new legal frameworks governing…

arXiv:2408.02705v1 Announce Type: new Abstract: Network embedding has numerous practical applications and has received extensive attention in graph learning, which aims at mapping vertices into a low-dimensional and continuous dense vector space by preserving the underlying structural properties of the graph. Many network embedding methods have been proposed, among which factorization of the Personalized PageRank (PPR for short) matrix has been empirically and theoretically well supported recently. However, several fundamental issues cannot be addressed. (1) Existing methods invoke a seminal Local Push subroutine to approximate textit{a single} row or column of the PPR matrix. Thus, they have to execute $n$…

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol

arXiv:2408.03092v1 Announce Type: new Abstract: Merging Large Language Models (LLMs) aims to amalgamate multiple homologous LLMs into one with all the capabilities. Ideally, any LLMs sharing the same backbone should be mergeable, irrespective of whether they are Fine-Tuned (FT) with minor parameter changes or Pre-Trained (PT) with substantial parameter shifts. However, existing methods often manually assign the model importance, rendering them feasible only for LLMs with similar parameter alterations, such as multiple FT LLMs. The diverse parameter changed ranges between FT and PT LLMs pose challenges for current solutions in empirically determining the optimal combination. In this paper, we make…