No AI summary available for this article.
Why It Matters
When a video model generates physically incorrect motion, did it fail to learn the correct motion, or did it learn it but fail to use it?
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
When a video model generates physically incorrect motion, did it fail to learn the correct motion, or did it learn it but fail to use it? We show the latter: the correct motion remains available inside the model and can still be made to control the generated video. We train on videos where red masses oscillate slowly and blue masses oscillate quickly, then test a red mass with fast observed motion. Even when the model generates slow motion in this conflicting case, a low-dimensional edit predicted from simple physical variables restores the correct fast motion. We call this ability causal writ...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.15980v1 · Indexed about 1 hour ago