ATLAS: Aligned Transport of Latent Structure for Reliable World Model Planning
cs.RO, cs.AI
Submitted: 2026-09-28
Updated: 2026-09-30
Code: https://github.com/Annie969/atlas-world-model
License: http://creativecommons.org/licenses/by/4.0/
The gist: Latent world models rely on representation geometry for planning, yet regularizing the latent marginal alone does not determine the state-to-state relationships used for action selection.
Terminology
Abstract
Latent world models rely on representation geometry for planning, yet regularizing the latent marginal alone does not determine the state-to-state relationships used for action selection. We show that this can cause planning-relevant novelty structure to be weakened as representations are transformed into the final latent used by the planner. We introduce Aligned Transport of Latent Structure (ATLAS), a training objective that explicitly preserves relational geometry while calibrating the global latent distribution. ATLAS transfers normalized pairwise structure from an informative encoder representation to the planning latent and uses Wasserstein embedding matching (WEMReg) to calibrate its marginal through one-dimensional Wasserstein-2 transport. Our analysis shows that relational preservation and marginal calibration impose non-redundant constraints, and connects finite-candidate planning stability to relational distortion, latent-scale mismatch, and prediction error. Instantiated in LeWM, ATLAS improves mean goal-reaching success across PushT, TwoRoom, and OGBench-Cube on both lower- and higher-novelty evaluation subsets, with the largest gain on higher-novelty TwoRoom episodes. Representation and rollout diagnostics further show stronger novelty-related structure in the planning latent, improved marginal calibration, and lower multi-step prediction error. Together, these results highlight preservation of planning-relevant latent geometry as an important ingredient for reliable world-model planning. Code is available at https://anonymous.4open.science/r/atlas-world-model-72C4/.
Sources
- LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
- Revisiting Feature Prediction for Learning Visual Representations from Video
- Fast LeWorldModel
- stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
- LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
- DINOv2: Learning Robust Visual Features without Supervision
- Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models
- Wasserstein Auto-Encoders
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies