Rapid advancements in artificial intelligence (AI) have sparked growing
...
Generative Pre-trained Transformer (GPT) models have exhibited exciting
...
In recent years, deep neural networks have demonstrated increasingly str...
Forecasting future world events is a challenging but valuable task. Fore...
Model stealing attacks present a dilemma for public machine learning API...
Artificial intelligence (AI) has the potential to greatly improve societ...
In real-world applications of machine learning, reliable and safe system...
When making everyday decisions, people are guided by their conscience, a...
While programming is one of the most broadly applicable skills in modern...
We propose a new test to measure a text model's multitask accuracy. The ...
Detecting out-of-distribution examples is important for safety-critical
...
Self-supervision provides effective representations for downstream tasks...
Tuning a pre-trained network is commonly thought to improve data efficie...
It is important to detect and handle anomalous inputs when deploying mac...
The growing importance of massive datasets with the advent of deep learn...