Identifiable World Models from Pretrained Diffusion Representations
arXiv:2610.07028v1 Announce Type: new Abstract: Diffusion-based world models can generate and predict trajectories in high-dimensional dynamical systems, but predictive accuracy does not imply that their latent coordinates recover the underlying state variables or causal interactions. We ask whethe…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-07 04:00 · arXiv cs.LG
Identifiable World Models from Pretrained Diffusion Representations