Augmenting self-attention with persistent memory vectors allows removal of feed-forward layers from Transformers without degrading performance on character and word level language modeling benchmarks.
Pointer sentinel mixture models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
Training Super Weights in isolation collapses LLM performance to random guessing, while full-layer low-rank updates succeed, showing parameter importance does not imply trainability.
citing papers explorer
-
Augmenting Self-attention with Persistent Memory
Augmenting self-attention with persistent memory vectors allows removal of feed-forward layers from Transformers without degrading performance on character and word level language modeling benchmarks.
-
Super Weights in LLMs and the Failure of Selective Training
Training Super Weights in isolation collapses LLM performance to random guessing, while full-layer low-rank updates succeed, showing parameter importance does not imply trainability.