A Transformer that generates its own low-rank weight updates from a running context summary can specialize to a prefix without keeping the prompt in the input.
Gaussian process prior variational autoencoders
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Contextually Guided Transformers via Low-Rank Adaptation
A Transformer that generates its own low-rank weight updates from a running context summary can specialize to a prefix without keeping the prompt in the input.