← Back to the collection
Adaptive depth ·
Mixture-of-Recursions
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
Routes tokens through different numbers of shared recursions and studies recursion-aware caching strategies.
Inside the method
Token → Router → Rᵢ loops
Simplified conceptual schematic. Consult the paper for the complete architecture.
- Recurrence family
- Adaptive depth
- Depth control
- Token-level routing
- KV / state strategy
- Recursion-wise / shared KV
Reading note
Appendix E measures forward time without KV cache maintenance. Do not read its throughput gains as universal end-to-end serving speedups.
Sources checked 2026-09-15. This catalog does not imply independent reproduction.
Cite this work
@misc{mor2025,
title = {Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation},
author = {Sangmin Bae and Yujin Kim and Reza Bayat and Sungnyun Kim and Jiyoun Ha and Tal Schuster and Adam Fisch and Hrayr Harutyunyan and Ziwei Ji and Aaron Courville and Se-Young Yun},
year = {2025},
eprint = {2507.10524},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2507.10524}
}