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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

A Data-Based Perspective on Transfer Learning


Jul 12, 2022
Saachi Jain, Hadi Salman, Alaa Khaddaj, Eric Wong, Sung Min Park, Aleksander Madry


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

When does Bias Transfer in Transfer Learning?


Jul 06, 2022
Hadi Salman, Saachi Jain, Andrew Ilyas, Logan Engstrom, Eric Wong, Aleksander Madry


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Distilling Model Failures as Directions in Latent Space


Jun 29, 2022
Saachi Jain, Hannah Lawrence, Ankur Moitra, Aleksander Madry


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Adversarially trained neural representations may already be as robust as corresponding biological neural representations


Jun 19, 2022
Chong Guo, Michael J. Lee, Guillaume Leclerc, Joel Dapello, Yug Rao, Aleksander Madry, James J. DiCarlo

* 10 pages, 6 figures, ICML2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Missingness Bias in Model Debugging


Apr 19, 2022
Saachi Jain, Hadi Salman, Eric Wong, Pengchuan Zhang, Vibhav Vineet, Sai Vemprala, Aleksander Madry

* Published at ICLR 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Datamodels: Predicting Predictions from Training Data


Feb 01, 2022
Andrew Ilyas, Sung Min Park, Logan Engstrom, Guillaume Leclerc, Aleksander Madry


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

On Distinctive Properties of Universal Perturbations


Dec 31, 2021
Sung Min Park, Kuo-An Wei, Kai Xiao, Jerry Li, Aleksander Madry


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Editing a classifier by rewriting its prediction rules


Dec 02, 2021
Shibani Santurkar, Dimitris Tsipras, Mahalaxmi Elango, David Bau, Antonio Torralba, Aleksander Madry


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Combining Diverse Feature Priors


Oct 15, 2021
Saachi Jain, Dimitris Tsipras, Aleksander Madry


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

3DB: A Framework for Debugging Computer Vision Models


Jun 07, 2021
Guillaume Leclerc, Hadi Salman, Andrew Ilyas, Sai Vemprala, Logan Engstrom, Vibhav Vineet, Kai Xiao, Pengchuan Zhang, Shibani Santurkar, Greg Yang, Ashish Kapoor, Aleksander Madry


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
>>