works on
image forgery detection 1localization 1reasoning traces 1reinforcement learning 1vision-language models 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

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

Ashim Dhor, Rasel Mondal, Pin-Yu Chen

Convolutional networks, recurrent networks, and transformers each encode different inductive biases -- locality, sequential memory, and content-dependent pairwise interaction -- an…