research
∙
02/18/2023
MaxGNR: A Dynamic Weight Strategy via Maximizing Gradient-to-Noise Ratio for Multi-Task Learning
When modeling related tasks in computer vision, Multi-Task Learning (MTL...
share
research
∙
02/18/2023
Improving the Out-Of-Distribution Generalization Capability of Language Models: Counterfactually-Augmented Data is not Enough
Counterfactually-Augmented Data (CAD) has the potential to improve langu...
research
∙
05/18/2021
Dependent Multi-Task Learning with Causal Intervention for Image Captioning
Recent work for image captioning mainly followed an extract-then-generat...
research
∙
11/19/2018