SOURCE-LINKED INTELLIGENCE

LoopSpec: Pipelined Self-Speculative Decoding for Looped Transformers

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Looped Transformers achieve strong performance with compact parameter sizes by repeatedly applying a shared stack of Transformer blocks across recurrent depths. However, they incur higher decoding latency than standard Transformer models of comparable parameter size because shared weights are accessed at every recurrent depth. To improve decoding efficiency, self-speculative decoding is particularly well suited to Looped Transformers, as their intermediate recurrent states can directly provide draft predictions without an auxiliary draft model. We therefore propose LoopSpec, a training-free se

Read original source ↗ Open in workspace

recordType

paper

region

Global