CADRE combines LoRA with self-scaling similarity-aware EWC and an anchor-to-prior penalty to achieve lower forgetting and positive backward transfer when adapting a medical VLM across dissimilar imaging modalities while training only 0.23% of parameters.
arXiv:2405.13482 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CADRE: Stable, Parameter Efficient Adaptation of Medical Vision Language Models with Bounded Forgetting and Prior Drift
CADRE combines LoRA with self-scaling similarity-aware EWC and an anchor-to-prior penalty to achieve lower forgetting and positive backward transfer when adapting a medical VLM across dissimilar imaging modalities while training only 0.23% of parameters.