Recirculation Technique Recycles Activations in Transformers

Researcher Michael C. Mozer posted a paper describing recirculation, an enhancement for off-the-shelf foundation models. The approach passes activations from higher layers into lower layers during subsequent inference steps. It requires no retraining. The paper states the change markedly reduces perplexity and boosts accuracy on generation and reasoning tasks while adding near-zero latency. Several researchers shared the work on X and highlighted its simplicity.