UpLoop: Training Looped Transformers via Upcycling at No Extra Pretraining Compute

arXiv:2610.41720 · cs.LG, cs.CL · Submitted 2026-10-30 · Read on arXiv

cs.LG, cs.CL

Submitted: 2026-10-30

Updated: 2026-10-30

Terminology

Sources

Related papers