AIBullisharXiv – CS AI · Jun 197/10
🧠
ITNet: A Learnable Integral Transform That Subsumes Convolution, Attention, and Recurrence
Researchers introduce ITNet, a unified neural network architecture built on learnable integral transforms that mathematically subsumes convolutional networks, transformers, and recurrent networks as special cases. The model demonstrates that these three historically distinct architectural families can emerge from a single underlying mathematical framework, with experiments showing competitive performance across vision, language, and multimodal tasks.