arXiv cs.LG
· Papers
Looped Latent Attention: Cross-Loop KV Compression for Looped Transformers
arXiv:2607.15456v1 Announce Type: new Abstract: Looped, weight-tied Transformers reduce parameters by reusing a block, but decoding still stores a separate K/V cache for every recurrence step. We show that this loop-indexed cache is highly structured. For a fixed token, layer and head, K/V vectors trace a short low-ran