Claims: ITNet: A Learnable Integral Transform That Subsumes Convolution, Attention, and Recurrence

These are attributed source records, not independent verification of each assertion.

Complete claim record (JSON) · Original source

1. title: ITNet: A Learnable Integral Transform That Subsumes Convolution, Attention, and Recurrence (alleges; supported) Source
2. url: https://arxiv.org/abs/2606.19538 (alleges; supported) Source
3. summary: arXiv:2606.19538v1 Announce Type: new Abstract: Convolutional networks, recurrent networks, and transformers each encode different inductive biases -- locality, sequential memory, and content-dependent pairwise interaction -- and have remained mathematically distinct since their inception. We show that this fragmentation reflects not a fundamental diversity in how signals should be processed, but rather incomplete views of a single underlying mathematical object: a learnable integral transform.… (alleges; supported) Source
4. published: Fri, 19 Jun 2026 00:00:00 -0400 (alleges; supported) Source