Search Results for author:
Found 4 papers, 1 papers with code
Pretrained Hybrids with MAD Skills
Manticore $\textit{automates the design of hybrid architectures}$ while reusing pretrained models to create $\textit{pretrained}$ hybrids.
OTTER: Improving Zero-Shot Classification via Optimal Transport
Popular zero-shot models suffer due to artifacts inherited from pretraining.
Mitigating Source Bias for Fairer Weak Supervision
Weak supervision enables efficient development of training sets by reducing the need for ground truth labels.
Relational Boosted Regression Trees
Many tasks use data housed in relational databases to train boosted regression tree models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
