Preserving training dynamics across batch sizes is an important tool for...
Self-supervised representation learning (SSL) methods provide an effecti...
While state-of-the-art contrastive Self-Supervised Learning (SSL) models...
In this work we examine how fine-tuning impacts the fairness of contrast...
Despite the success of a number of recent techniques for visual
self-sup...
In this work, we introduce a new method for imitation learning from vide...
Modern neural network training relies on piece-wise (sub-)differentiable...
We describe experiments towards building a conversational digital assist...
Image classification with deep neural networks is typically restricted t...
Knowledge Matters: Importance of Prior Information for Optimization [7],...
With recent progress in graphics, it has become more tractable to train
...