FOREVER aligns replay intervals in LLM continual learning with a model-centric time based on optimizer update magnitudes and an Ebbinghaus-inspired forgetting curve to reduce catastrophic forgetting.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
MoRAM frames continual learning as incremental addition of rank-1 adapters viewed as self-activating key-value associative memory units in a mixture-of-experts setup.
citing papers explorer
-
FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learning
FOREVER aligns replay intervals in LLM continual learning with a model-centric time based on optimizer update magnitudes and an Ebbinghaus-inspired forgetting curve to reduce catastrophic forgetting.
-
Little by Little: Continual Learning via Incremental Mixture of Rank-1 Associative Memory Experts
MoRAM frames continual learning as incremental addition of rank-1 adapters viewed as self-activating key-value associative memory units in a mixture-of-experts setup.