When trying to gain better visibility into a machine learning model in o...
Large language models (LLMs) may not equitably represent diverse global
...
The European Union's Artificial Intelligence (AI) Act is set to be a lan...
Medical data poses a daunting challenge for AI algorithms: it exists in ...
Contrastive learning methods have been applied to a range of domains and...
Language models have recently achieved strong performance across a wide ...
What role do augmentations play in contrastive learning? Recent work sug...
Models can fail in unpredictable ways during deployment due to task
ambi...
Little is known about what makes cross-lingual transfer hard, since fact...
Contrastive learning has made considerable progress in computer vision,
...
Self-supervised learning algorithms, including BERT and SimCLR, have ena...
Methods for designing organic materials with desired properties have hig...
On October 14th, 2020, researchers from OpenAI, the Stanford Institute f...
Language exhibits structure at different scales, ranging from subwords t...
Many recent methods for unsupervised representation learning involve tra...
While probing is a common technique for identifying knowledge in the
rep...
While maximizing expected return is the goal in most reinforcement learn...