Wander is a low-rank sequence adapter that fuses token-level features across an arbitrary number of modalities with far fewer parameters than full fine-tuning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Wander Through the Multimodal Landscape: Efficient Transfer Learning via Low-rank Sequence Multimodal Adapter
Wander is a low-rank sequence adapter that fuses token-level features across an arbitrary number of modalities with far fewer parameters than full fine-tuning.