Research
Designing technology that is more intuitive, accessible, and useful across the full range of human experiences.
In today’s world, people have to attend to a number of tasks near simultaneously, and with the widespread use of mobile devices, tasks can be tackled almost anywhere at any time. It is not surprising,…
The bistring library provides non-destructive versions of common string processing operations like normalization, case folding, and find/replace. Each bistring remembers the original string, and how its substrings map to substrings of the modified version.
The project is an official implementation of our CVPR2019 paper “Deep High-Resolution Representation Learning for Human Pose Estimation”
The ELL models repository contains a number of pretrained models suited for different device footprints. Currently, there are pretrained models for image classification and audio keyword spotting.
Scripts for dialog generation evaluation, tokenization, data preprocessing, and GUI interface.
A synthetic dataset of visual programs for the program synthesis task, now a common benchmark in the academic community. This webpage hosts the dataset for synthetically generated Karel programs that are used for training and…
