SAE-FD anchors LLM representations in the sparse feature space of a pre-trained sparse autoencoder to enable more targeted regularization that reduces catastrophic forgetting while allowing new-task learning.
Zhizhong Li and Derek Hoiem
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Checkpoint monitoring during sequential LoRA adaptation of SLMs reveals instability patterns via reference set diagnostics that standard task metrics can miss.
citing papers explorer
-
SAE-FD: Sparse Autoencoder Feature Distillation for Continual Learning of Large Language Models
SAE-FD anchors LLM representations in the sparse feature space of a pre-trained sparse autoencoder to enable more targeted regularization that reduces catastrophic forgetting while allowing new-task learning.
-
Continual Learning for Sequential Personalization of Small Language Models: A Stability Monitoring Analysis
Checkpoint monitoring during sequential LoRA adaptation of SLMs reveals instability patterns via reference set diagnostics that standard task metrics can miss.