MSLoRA-CR incrementally adds modality-specific LoRA branches to a frozen medical LVLM with contrastive regularization, reporting improved overall performance over separate per-modality models on nine biomedical datasets.
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning
MSLoRA-CR incrementally adds modality-specific LoRA branches to a frozen medical LVLM with contrastive regularization, reporting improved overall performance over separate per-modality models on nine biomedical datasets.