Edward Johns

Becoming the expert - interactive multi-class machine teaching

2015

Compared to machines, humans are extremely good at classifying images into categories, especially when they possess prior knowledge of the categories at hand. If this prior information is not available, supervision in the form of …

DALL-E-Bot: Introducing Web-Scale Diffusion Models to Robotics

2022 · arXiv (Cornell University)

We introduce the first work to explore web-scale diffusion models for robotics. DALL-E-Bot enables a robot to rearrange objects in a scene, by first inferring a text description of those objects, then generating an image …

SceneScore: Learning a Cost Function for Object Arrangement

2023 · arXiv (Cornell University)

Arranging objects correctly is a key capability for robots which unlocks a wide range of useful tasks. A prerequisite for creating successful arrangements is the ability to evaluate the desirability of a given arrangement. Our …