630 citations · 2.3k across the 52 of their papers we have counts for
15 papers · 1 filter
Discovering Non-monotonic Autoregressive Orderings with Variational Inference
Xuanlin Li, Brandon Trabucco, Dong Huk Park +4
The predominant approach for language modeling is to process sequences from left to right, but this eliminates a source of information: the order by which the sequence was generate…
On-target Adaptation
Dequan Wang, Shaoteng Liu, Sayna Ebrahimi +2
Domain adaptation seeks to mitigate the shift between training on the \emph{source} domain and testing on the \emph{target} domain. Most adaptation methods rely on the source data…
Tune it the Right Way: Unsupervised Validation of Domain Adaptation via Soft Neighborhood Density
Kuniaki Saito, Donghyun Kim, Piotr Teterwak +3
Unsupervised domain adaptation (UDA) methods can dramatically improve generalization on unlabeled target domains. However, optimal hyper-parameter selection is critical to achievin…
Predicting with Confidence on Unseen Distributions
Devin Guillory, Vaishaal Shankar, Sayna Ebrahimi +2
Recent work has shown that the performance of machine learning models can vary substantially when models are evaluated on data drawn from a distribution that is close to but differ…
Early Convolutions Help Transformers See Better
Tete Xiao, Mannat Singh, Eric Mintun +3
Vision transformer (ViT) models exhibit substandard optimizability. In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and tra…
Auto-Tuned Sim-to-Real Transfer
Yuqing Du, Olivia Watkins, Trevor Darrell +2
Policies trained in simulation often fail when transferred to the real world due to the `reality gap' where the simulator is unable to accurately capture the dynamics and visual pr…