Linear attention delivers significant computational savings in multimodal transformers and follows the same scaling laws as softmax attention on ViT models trained on LAION-400M with ImageNet-21K zero-shot validation.
Efficient attention: Attention with lin- ear complexities
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On The Application of Linear Attention in Multimodal Transformers
Linear attention delivers significant computational savings in multimodal transformers and follows the same scaling laws as softmax attention on ViT models trained on LAION-400M with ImageNet-21K zero-shot validation.