arXiv AI By F\'elix Marcoccia

Designing a Good Virtual Node: Addressable and Cardinality-Preserving Global Memory for Message Passing Architectures

Read the original on arXiv AI →

arXiv:2608. 02709v1 Announce Type: cross Abstract: Virtual nodes give message-passing neural networks a simple global communication route, but the standard node--VN--node pipeline compresses the graph into one homogeneous state and broadcasts it identically to every node.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jun 10

Dynamic Linear Attention

arXiv:2606. 10650v1 Announce Type: cross Abstract: The scalability of Large Language Models (LLMs) to long contexts is fundamentally constrained by the quadratic complexity of standard attention, motivating the adoption of linear attention mechanisms with sub-quadratic cost.

By Xin Wang, Hui Shen, Boyuan Zheng, Xueshen Liu, Minkyoung Cho, Zhongwei Wan, Zesen Zhao, Zhuoqing Mao, Shen Yan, Mi Zhang