research
∙
05/31/2023
ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning
Two-Tower Vision-Language (VL) models have shown promising improvements ...
share
research
∙
06/17/2022
Bridge-Tower: Building Bridges Between Encoders in Vision-Language Representation Learning
Vision-Language (VL) models with the Two-Tower architecture have dominat...
research
∙
10/09/2020
Relation Extraction as Two-way Span-Prediction
The current supervised relation classification (RC) task uses a single e...
research
∙
10/07/2020