T2-z: Test-Time Optimization of Environment Latents for Robotic World Models
arXiv:2610.22364v1 Announce Type: cross Abstract: Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly observable nor explicitly specified, from physical properties such as friction and mass to human-defined environmental rules. We introduce T2-Z for test-time optimization of environment latents, which augments a robotic world model with a learnable environment latent to condition world predic…