4 papers
When Do Conservation Laws Survive Learned Representations? Certified Horizons for Latent World Models
Hongbo Wang
We ask a representation-learning question about physical world models: when does a conservation law remain certifiable after a model learns a latent representation? A certified hor…
Certified World Models: Predictability Across Configuration, Horizon, and Resolution
Hongbo Wang
Scale buys interpolation; structure buys certifiable transfer. A world model's average error does not say whether a particular rollout can be trusted, or for how long. For equivari…
Certified World Models as Sensing Clocks: Drift-Aware Deadlines for Active Perception
Hongbo Wang
Certified world models estimate how long their predictions remain valid. We turn this validity horizon into an operational sensing clock: a rule for when an agent should stop coast…
Conformal Orbit-Valid Trust Horizons for Equivariant World Models
Hongbo Wang
Learned world models are useful only over horizons on which their rollout error remains controlled. We study trust-horizon certification for latent world models with known group sy…