The Surprising Effectiveness of Shared Memory in Looped Transformers
Looped Transformers apply the same layers several times per token, adding compute to improve quality without more parameters. Each recursion, however, writes its own key-value cache, so memory still grows with compute. Inference-time techniques can shrink this cache at a cost in quality. We pretrain looped language mod...
Giovanni Monea, Keshav Ramji, Yousef El-Kurdi et al.
· 0 citations