T^2MLR: Transformer with Temporal Middle-Layer Recurrence
Transformer reasoning is limited by autoregressive decoding, which repeat edly compresses rich hidden computation through token space and makes it difficult for intermediate reasoning states to persist across time. We in troduce Transformers with Temporal Middle-Layer Recurrence (T2MLR), a transformers-based latent reasoning architecture that fuses a cached middle layer representation from the previous token directly into an earlier layer of the current token position, enabling abstract intermediate computation to persist across decoding steps with little inference overhead. Across natural-lan
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 47%Transformer →
- PossiblePossibly related (embedding) · 45%I shrank a transformer until every number fitted on the screen and made the weights editable [R] →
- LinkedLinked via arxiv author · 85%Ziyang Cai →
“T^2MLR: Transformer with Temporal Middle-Layer Recurrence”
- LinkedLinked via arxiv author · 85%Xingyu Zhu →
“T^2MLR: Transformer with Temporal Middle-Layer Recurrence”
- LinkedLinked via arxiv author · 85%Yihe Dong →
“T^2MLR: Transformer with Temporal Middle-Layer Recurrence”
- LinkedLinked via arxiv author · 85%Yinghui He →
“T^2MLR: Transformer with Temporal Middle-Layer Recurrence”
- LinkedLinked via arxiv author · 85%Sanjeev Arora →
“T^2MLR: Transformer with Temporal Middle-Layer Recurrence”