Training a model to separate the objects in a picture typically requires labeled images for best results. Recent work upped the ante for training without labels.
Typical text-to-image generators can generate pictures of a cat, but not your cat. That’s because it’s hard to describe in a text prompt precisely all the things that distinguish your pet from other members of the same species.
Typical text-to-image generators can generate pictures of a cat, but not your cat. That’s because it’s hard to describe in a text prompt precisely all the things that distinguish your pet from other members of the same species.
Researchers pushed the boundaries of language models to address persistent problems of trustworthiness, bias, and updatability.
Researchers pushed the boundaries of language models to address persistent problems of trustworthiness, bias, and updatability.
Work on vision transformers exploded in 2022. Researchers published well over 17,000 ViT papers during the year. A major theme: combining self-attention and convolution.
Work on vision transformers exploded in 2022. Researchers published well over 17,000 ViT papers during the year. A major theme: combining self-attention and convolution.
Large language models are trained only to predict the next word based on previous ones. Yet, given a modest fine-tuning set, they acquire enough information to learn how to perform tasks such as answering questions.
Large language models are trained only to predict the next word based on previous ones. Yet, given a modest fine-tuning set, they acquire enough information to learn how to perform tasks such as answering questions.
If a robot can predict what it’s likely to see next, it may have a better basis for choosing an appropriate action — but it has to predict quickly. Transformers, for all their utility in computer vision, aren’t well suited to this because of their steep computational and memory requirements...
If a robot can predict what it’s likely to see next, it may have a better basis for choosing an appropriate action — but it has to predict quickly. Transformers, for all their utility in computer vision, aren’t well suited to this because of their steep computational and memory requirements...
Neural networks can describe in words what’s happening in pictures and videos — but can they make sensible guesses about things that happened before or will happen afterward? Researchers probed this ability.
Neural networks can describe in words what’s happening in pictures and videos — but can they make sensible guesses about things that happened before or will happen afterward? Researchers probed this ability.
The route to improving transformer-based language models like GPT-3 and Gopher, which are trained on immense quantities of text scraped from the web, has been to increase their size. But research shows that, given a processing budget, bigger doesn’t necessarily mean better.
The route to improving transformer-based language models like GPT-3 and Gopher, which are trained on immense quantities of text scraped from the web, has been to increase their size. But research shows that, given a processing budget, bigger doesn’t necessarily mean better.
Stay updated with weekly AI News and Insights delivered to your inbox