When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learningby Claas Voelcker, Tyler Kastner, Igor…
A New Perspective on Shampoo’s Preconditionerby Depen Morwani, Itai Shapira, Nikhil Vyas, Eran Malach, Sham…
Interpreting Attention Layer Outputs with Sparse Autoencodersby Connor Kissane, Robert Krzyzanowski, Joseph Isaac Bloom, Arthur…
XAMI – A Benchmark Dataset for Artefact Detection in XMM-Newton Optical Imagesby Elisabeta-Iulia Dima, Pablo…
Stacked Confusion Reject Plots (SCORE)by Stephan Hasler, Lydia FischerFirst submitted to arxiv on: 25 Jun…
Generalizability of experimental studiesby Federico Matteucci, Vadim Arzamasov, Jose Cribeiro-Ramallo, Marco Heyden, Konstantin Ntounas, Klemens…
Mind the Graph When Balancing Data for Fairness or Robustnessby Jessica Schrouff, Alexis Bellot, Amal…
Towards Compositional Interpretability for XAIby Sean Tull, Robin Lorenz, Stephen Clark, Ilyas Khan, Bob CoeckeFirst…
Peirce in the Machine: How Mixture of Experts Models Perform Hypothesis Constructionby Bruce RushingFirst submitted…
Virtual Mines – Component-level recycling of printed circuit boards using deep learningby Muhammad Mohsin, Stefano…