ReRead: Wrong Predictions, Useful Representations - Correcting Frozen Robot Policies by Re-reading Their Own Representations
From the abstract
When a pretrained robot policy fails on challenging tasks, common remedies include retraining the backbone, adding an external visual encoder, or introducing a memory module. We argue that wrong predictions do not imply wrong representations: a policy can retain the required information yet fail to read it out as the correct action.
From the abstract. Our summary is in progress.