No AI summary available for this article.
Why It Matters
World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
World models learn to predict how their environment will evolve, making them an important foundation for general-purpose robotic control. Yet world action models depend on camera inputs whose manipulation can corrupt the visual representations used across tasks and action policies. Existing attacks on these models optimize against the victim's actions or predicted futures and therefore require access to target-model outputs. In this paper, we propose an attack, TAPDreamer, against world action models that instead uses a public encoder alone to construct a fixed local perturbation that transfer...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2610.06814v1 · Indexed about 1 hour ago