Structured Latent Dynamics for Long-Horizon Embodied World Models
The authors propose HWM, a structured latent dynamics framework that encodes backbone latents into generalized coordinates and momenta, evolves them with dissipative Hamiltonian dynamics, and maps back via a learnable inverse interface. Multi-step transition supervision aligns structured rollouts with latent trajectories from real observations. Experiments show improved higher-order motion prediction, reduced long-horizon energy drift, and better downstream task success when integrated into existing world-model backbones.
