SOURCE-LINKED INTELLIGENCE

GTR: Gated Token Recurrence for Efficient Dense Prediction

arXiv · AI, language, vision and robotics · article · Sep 22, 2026 · UTC

Self-attention-based vision backbones perform well on dense prediction, but the quadratic computational cost of global softmax attention limits their efficiency as image resolution increases. We introduce Gated Token Recurrence (GTR), a softmax-free recurrent vision backbone that combines gated linear attention, alternating spatial scan directions, and spatially enhanced SwiGLU blocks. GTR is distilled from a detection-specialized DINOv3 teacher using only final-layer patch-token alignment through a linear projection and squared $\ell_2$ loss, without masked-token prediction or intermediate-la

Read original source ↗ Open in workspace

recordType

paper

region

Global