Featured Demos
Explore how our planet is changing through AI-annotated satellite imagery | PRIOR, Research VisualizationSatlas is a platform for visualizing and downloading global geospatial data products generated by AI using satellite images. It is our hope that this data will be useful for earth and environmental scientists, as well as for organizations working in a variety of geospatial domains. The marine infrastructure data…
Try the demo
A new general-purpose model with unprecedented breadth that can perform a wide array of visual and linguistic tasks. | PRIOR, Research VisualizationUnified-IO is the first neural model to perform a large, diverse set of AI tasks from computer vision to natural language processing.
Try the demo
A QA model that outperforms other popular language models while being an order of magnitude smaller | Aristo, Research VisualizationMacaw is a high-performance question-answering (QA) model capable of outperforming other popular current language models, all while being an order of magnitude smaller. This demo allows you to explore Macaw's answers and compare them to those of the popular GPT-3 language model on a benchmark set of questions.
Try the demo
A research prototype designed to model people’s moral judgments on a variety of everyday situations | Mosaic, Research VisualizationDelphi
PrototypeDelphi is intended to demonstrate what state-of-the-art models can accomplish today on machine ethics as well as to highlight their limitations.
Try the prototype
Evaluating neural toxic degeneration in language models | Mosaic, Research VisualizationIn new joint work at AI2 and UW, we study how often popular NLP components produce problematic content, what might trigger this neural toxic degeneration from a given system, and whether or not it can be successfully avoided. We also study how much toxicity is present in the web text that these systems learned…
Try the demo
Several demos of a variety of popular computer vision models | PRIOR, Research VisualizationThe Computer Vision Explorer lets you try and compare a variety of popular computer vision models related to recognition, vision and language, human-centric vision, and scene geometry tasks. Use our example images or try with your own.
Try the demo
Search over our AI-curated corpus of 1,923 supplements, 2,727 drugs, and 55,946 interactions | Semantic Scholar, Research VisualizationSUPP.AI
PrototypeSUPP.AI automatically extracts evidence of supplement and drug interactions from the scientific literature. Search for all known potential interactions with a particular agent, or look up the evidence for a specific interaction.
Try the prototype
Inferring commonsense knowledge from text | Mosaic, Research VisualizationExplore ATOMIC, an atlas of everyday commonsense reasoning focused on inferential knowledge, organized through 877k textual if-then descriptions. Then see ATOMIC in action via COMeT and VisualCOMeT, a knowledge base construction engine that learns to access commonsense knowledge implicitly acquired when reading…
Try the demo
