| title | Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning |
|---|---|
| authors | Jiawei Wang, Ke Rui, Yushen Zuo, Yichun Feng, Minglei Li |
| date | 2026-08-19 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2608.18746 |
| affiliation | Simple World Lab |
| upvotes | 8 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| primer | World models |
| abstract | JEPA-style latent world models can use Euclidean distance to a goal latent as the cost for model-predictive control (MPC). Strong decoding of task variables, however, does not guarantee that this particular cost ranks candidate action sequences by real task progress. We call the latter property decision-metric alignment. We introduce Plan-Real Spearman, which measures latent--real rank agreement on random plans, and CEM-stage Spearman, which measures the same agreement as cross-entropy-method (CEM) search concentrates its proposal. We analyze sufficient conditions under which latent distance preserves real-cost rankings, identifying encoder distortion, terminal rollout error, and candidate margins as the controlling quantities. Guided by the observed empirical alignment gap, DA-LeWM augments LeWM with inverse-dynamics and demonstration-conditioned goal-action heads. Across all our experiments, DA-LeWM accelerates convergence and achieves higher online success than LeWM, while probe scores remain similar. These results show that action-conditioned objectives improve the geometry used by Euclidean-cost, CEM-based latent MPC. |
cite
@misc{wang2026decision,
title={Decision-Metric Alignment in Latent World Models: Diagnostics and Action-Conditioned Objectives for MPC Planning},
author={Jiawei Wang and Ke Rui and Yushen Zuo and Yichun Feng and Minglei Li},
year={2026},
eprint={2608.18746},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2608.18746}
}