CoVON merges past posteriors for slow adaptation within the VCL framework and applies IVON for fast updates, claiming consistent gains over prior VCL methods and weight-regularization baselines in domain-incremental, pre-training, and LLM fine-tuning tasks.
arXiv:2205.15902 , title =
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
-
Fast and Slow Variational Continual Learning
CoVON merges past posteriors for slow adaptation within the VCL framework and applies IVON for fast updates, claiming consistent gains over prior VCL methods and weight-regularization baselines in domain-incremental, pre-training, and LLM fine-tuning tasks.