AI RESEARCH

Linear-Time Global Visual Modeling without Explicit Attention

arXiv CS.CV

ArXi:2605.01711v1 Announce Type: new Existing research largely attributes the global sequence modeling capability of Transformers to the explicit computation of attention weights, a process that inherently incurs quadratic computational complexity. In this work, we offer a novel perspective: we nstrate that attention can be mathematically reframed as a Multi-Layer Perceptron (MLP) equipped with dynamically predicted parameters.