no code implementations • 12 Apr 2024 • Changho Shin, Jitian Zhao, Sonia Cromp, Harit Vishwakarma, Frederic Sala
Popular zero-shot models suffer due to artifacts inherited from pretraining.
1 code implementation • NeurIPS 2023 • Changho Shin, Sonia Cromp, Dyah Adila, Frederic Sala
Weak supervision enables efficient development of training sets by reducing the need for ground truth labels.
no code implementations • 25 Jul 2021 • Sonia Cromp, Alireza Samadian, Kirk Pruhs
Many tasks use data housed in relational databases to train boosted regression tree models.