Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Winnie Xu

Winnie Xu

Language Model Cascades

Jul 28, 2022
David Dohan, Winnie Xu, Aitor Lewkowycz, Jacob Austin, David Bieber, Raphael Gontijo Lopes, Yuhuai Wu, Henryk Michalewski, Rif A. Saurous, Jascha Sohl-dickstein, Kevin Murphy, Charles Sutton

Figure 1 for Language Model Cascades

Figure 2 for Language Model Cascades

Figure 3 for Language Model Cascades

Figure 4 for Language Model Cascades

* Presented as spotlight at the Beyond Bases workshop at ICML 2022 (https://beyond-bayes.github.io)

Access Paper or Ask Questions

Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

Jun 16, 2022
Sören Mindermann, Jan Brauner, Muhammed Razzak, Mrinank Sharma, Andreas Kirsch, Winnie Xu, Benedikt Höltgen, Aidan N. Gomez, Adrien Morisot, Sebastian Farquhar, Yarin Gal

Figure 1 for Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

Figure 2 for Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

Figure 3 for Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

Figure 4 for Prioritized Training on Points that are Learnable, Worth Learning, and Not Yet Learnt

* ICML 2022 (Follow up to arXiv:2107.02565)

Access Paper or Ask Questions

Noisy Feature Mixup

Oct 05, 2021
Soon Hoe Lim, N. Benjamin Erichson, Francisco Utrera, Winnie Xu, Michael W. Mahoney

Figure 1 for Noisy Feature Mixup

Figure 2 for Noisy Feature Mixup

Figure 3 for Noisy Feature Mixup

Figure 4 for Noisy Feature Mixup

* 28 pages

Access Paper or Ask Questions

Prioritized training on points that are learnable, worth learning, and not yet learned

Jul 06, 2021
Sören Mindermann, Muhammed Razzak, Winnie Xu, Andreas Kirsch, Mrinank Sharma, Adrien Morisot, Aidan N. Gomez, Sebastian Farquhar, Jan Brauner, Yarin Gal

Figure 1 for Prioritized training on points that are learnable, worth learning, and not yet learned

Figure 2 for Prioritized training on points that are learnable, worth learning, and not yet learned

Figure 3 for Prioritized training on points that are learnable, worth learning, and not yet learned

Figure 4 for Prioritized training on points that are learnable, worth learning, and not yet learned

* ICML 2021 Workshop on Subset Selection in Machine Learning

Access Paper or Ask Questions