Language models can use a two-stage sleep process of upward distillation for memory consolidation and RL-based dreaming for unsupervised self-improvement to enable continual learning.
Stepwise synaptic plasticity events drive the early phase of memory consolidation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Language models can use a two-stage sleep process of upward distillation for memory consolidation and RL-based dreaming for unsupervised self-improvement to enable continual learning.