research
∙
11/30/2022
Quadapter: Adapter for GPT-2 Quantization
Transformer language models such as GPT-2 are difficult to quantize beca...
share
research
∙
05/30/2019
Learning to Balance: Bayesian Meta-Learning for Imbalanced and Out-of-distribution Tasks
While tasks could come with varying number of instances in realistic set...
research
∙
04/11/2019
MxML: Mixture of Meta-Learners for Few-Shot Classification
A meta-model is trained on a distribution of similar tasks such that it ...
research
∙
05/25/2018