BadWAM: Right Mind but Wrong Action

Qi Li · hf · 2026-07-17

BadWAM: World-Action Models Can "Think Right, Act Wrong"

This paper investigates the adversarial vulnerability of World-Action Models (WAMs). WAMs couple action generation with future world prediction, making them often perceived as more robust, interpretable, and safe; however, the authors point out that this "imagination-execution consistency" is actually quite fragile.

Proposed Attacks

BadWAM uniformly describes and evaluates a class of World-Action Drift Attacks against WAMs:

Results

Conclusion: A WAM "thinking correctly" does not equate to "acting safely".

Original post →

More from Embodied

Embodied channel →