CausalWAM: Learning the Causes of Actions in World Action Models
CausalWAM addresses a mismatch in world action models: predicting the whole scene is not the same as learning which latent causes drive actions. The authors prove that, with a sparsity constraint, action-relevant latent variables are identified up to permutation and the deployed compact state is an invertible function of the true action-relevant block. They propose CWAM by adding a sparse routing path to the action head of Cosmos 3. Experiments validate theory and improve closed-loop success efficiency.
