Deep Learning
Understanding Visual Feature Reliance through the Lens of Complexity Thomas Fel Google DeepMind Brown University Louis Béthune
Recent studies suggest that deep learning models' inductive bias towards favoring
DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data
Current perceptual similarity metrics operate at the level of pixels and patches.
Bowen Li
All the code and data are open-sourced at our website.
Smooth Hess: ReLU Network Feature Interactions via Stein's Lemma
SmoothHess is applied post-hoc, requires no modifications to the ReLU network architecture, and the extent of smoothing can be controlled explicitly.
Deep Learning with Kernels through RKHM and the Perron-Frobenius Operator
We derive a new Rademacher generalization bound in this setting and provide a theoretical interpretation of benign overfitting by means of Perron-Frobenius operators.
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Current methods for identifying adversarial prompts aimed at "attacking" LLMs and eliciting undesirable outputs are limited by several factors.
Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean
The vast amount of data required to model wildfires at a larger scale presents difficulties in the collection and curation of the data.
