LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation
Trains a shared transformer stack on long and short computation paths, conditioning each pass on its location and step size. A consistency loss aligns shorter paths with the longest path so one model can run under different depth budgets.
First public: · Added to this list: November 3, 2026
Cite this paper
Published version
LoopFormer: Elastic-Depth Looped Transformers for Latent Reasoning via Shortcut Modulation
Ahmadreza Jeddi, Marco Ciccone, Babak Taati
International Conference on Learning Representations, 2026.
Explore this approach
Recurrent reasoning — Repeat parts of the model or keep intermediate information in memory while working through a problem. Some methods also learn how many passes to run.