Posts in tag

Facebook AI


Talking to each other is a natural way for people to interact, and as voice technology has evolved, to interact with our devices — and the metaverse in the future, where virtual experiences blend with our physical worlds. Yet speech technology is only available for a fraction of the thousands of languages spoken around the …

Building a universal translation system to help everyone access information and better connect with one another is the ultimate goal of the machine translation (MT) field. But the MT field needs to solve fundamental limitations in order to make that future a reality. Most MT systems today use groups of bilingual models, which typically require …

Touch is important to the way people experience the world. We typically think of touch as a way to convey warmth and care, but it’s also a key sensing modality for perceiving the world around us. Touching provides us with information that’s not discernible through any other sense, for example, about the temperature of a …

AI that understands the world from a first-person point of view could unlock a new era of immersive experiences, as devices like augmented reality (AR) glasses and virtual reality (VR) headsets become as useful in everyday life as smartphones. Imagine your AR device displaying exactly how to hold the sticks during a drum lesson, guiding …

Pretraining using large labeled data sets has become a core tool for developing high-performance computer vision (CV) models. But while this method works well with many types of media, it hasn’t been widely used for 3D recognition tasks, such as identifying and localizing a couch in a 3D scan of a living room. This is …

It’s been one year since Facebook AI launched Dynabench, a first-of-its-kind platform that radically rethinks benchmarking in AI. Starting today, we’re unlocking Dynabench’s full capabilities for the AI community — AI researchers can now create their own custom tasks to better evaluate the performance of natural language processing (NLP) models in more flexible, dynamic, and realistic …

Generative adversarial networks (GANs) are a well-established AI method to create images, whether photorealistic pictures or abstract collages. However, to date these models have had an important limitation: They can typically only generate images of objects or scenes that are closely related to the training data set. A traditional GAN trained on images of cars …

The speed at which AI has evolved over the last decade means it’s easy to overlook the significance of individual developments along the way. Things have changed so fast that what seemed like a milestone just a couple of years ago is already outdated. But to understand the progress, it’s important to note those milestones. …

Every day, we’re inundated with a constant stream of information — most of which we’ll forget. Sure, you can probably remember what you had for breakfast this morning, but what about last year? We often take for granted the ability to forget mundane, day-to-day details to make room for valuable moments that matter in our …

Training AI systems with curated and labeled data sets has produced specialized AI models that excel at tasks like object recognition. But relying solely on this approach also has real limitations, including one we consider particularly important to address: Such systems can struggle to recognize objects that are common in daily life for billions of …