← Back to the collection
Full-stack recurrence ·
LT²
LT2: Linear-Time Looped Transformers
Combines looping with linear, sparse and hybrid token mixers to explore more efficient repeated computation.
Inside the method
[ Linear / sparse / hybrid mixer ] × R
Simplified conceptual schematic. Consult the paper for the complete architecture.
- Recurrence family
- Full-stack recurrence
- Depth control
- Iteration budget
- KV / state strategy
- Mixer-dependent state
Reading note
The Full+GDN variant still includes full attention; not all variants have strictly linear attention complexity.
Sources checked 2026-09-15. This catalog does not imply independent reproduction.
Cite this work
@misc{lt22026,
title = {LT2: Linear-Time Looped Transformers},
author = {Chunyuan Deng and Yizhe Zhang and Rui-Jie Zhu and Yuanyuan Xu and Jiarui Liu and T. S. Eugene Ng and Hanjie Chen},
year = {2026},
eprint = {2605.20670},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.20670}
}