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.
Recent work showed that models for multilingual machine translation can increase the number of languages they translate by scraping the web for pairs of equivalent sentences in different languages. A new study radically expanded the language repertoire through training on untranslated web text.
Recent work showed that models for multilingual machine translation can increase the number of languages they translate by scraping the web for pairs of equivalent sentences in different languages. A new study radically expanded the language repertoire through training on untranslated web text.
Only a week ago, researchers unveiled a system that generates a few seconds of video based on a text prompt. New work enables a text-to-video system to produce an entire visual narrative from several sentences of text.
Only a week ago, researchers unveiled a system that generates a few seconds of video based on a text prompt. New work enables a text-to-video system to produce an entire visual narrative from several sentences of text.
A new method enables robots to respond helpfully to verbal commands by pairing a natural language model with a repertoire of existing skills.
A new method enables robots to respond helpfully to verbal commands by pairing a natural language model with a repertoire of existing skills.
French tax authorities netted nearly €10 million using an automated system to identify unregistered pools
French tax authorities netted nearly €10 million using an automated system to identify unregistered pools
Google updated the Multitask Unified model its search algorithm to respond to the flood of misinformation on the web.
Google updated the Multitask Unified model its search algorithm to respond to the flood of misinformation on the web.
A CLIP model whose weights were the mean of an ensemble of fine-tuned models performed as well as the ensemble and better than its best-performing constituent.
A CLIP model whose weights were the mean of an ensemble of fine-tuned models performed as well as the ensemble and better than its best-performing constituent.
Convolutional neural networks separate proteins into functional families without considering their shapes.
Convolutional neural networks separate proteins into functional families without considering their shapes.
Stay updated with weekly AI News and Insights delivered to your inbox