Targeted Model Editing
Practitioners can now make targeted edits to large models without the need for extensive retraining. By employing a meta learning approach, a small data set is used to train a model editor, allowing for specific updates, such as correcting outdated information. This method enhances efficiency and preserves the integrity of other model functions.In this clip
From this podcast

The Robot Brains Podcast
S3 E2 Stanford Prof Chelsea Finn: How to build AI that can keep up with an always changing world
Related Questions