arXiv Machine Learning

Aim Short to Reach Far: Your Frozen World Model Can Plan Better Than You Think

The paper demonstrates that planners using frozen visual world models can achieve better control by changing the target used for action scoring. Instead of scoring actions solely by distance to the final goal image, the authors propose Anchored Planning, which retrieves a recorded trajectory segment that matches the current and goal observations and then scores actions toward an intermediate observation shortly after the segment’s start. Experiments on Cube, PushT, Reacher, and TwoRoom show that this intermediate-target approach outperforms the released LeWM planner on all long‑range tasks, while simple final‑goal search fails to achieve the same gains.

arXiv AI
Aug 17

Traj-LeWM: Path-Aware World-Model Planning via Latent Trajectory Cost

arXiv:2608. 14125v1 Announce Type: new Abstract: LeWM is a lightweight visual world model that learns latent dynamics end-to-end from pixels and ranks candidate action sequences by the distance between their predicted endpoints and the goal.

By Xiaodi Huang, Ziyi Ding, Jingtian Wan, Yuchen Liu, Yuan Zhang, Xiao-Ping Zhang, Jiayu Chen, Zhang Zhang, Tao Huang
arXiv AI
Sep 30

Beyond a single latent space: a dual-latent world model for long-horizon planning

The paper introduces the Dual-Latent World Model (Dual-WM), which separates local execution and long-range planning into distinct latent spaces and dynamics models. A new learning method, Long-Horizon Representation Learning with Weighted Rollout (LoRe), supervises predictions at both levels using exponential horizon weights. Experiments on five goal-conditioned visual control tasks show that Dual-WM improves success rates over strong baselines, especially at longer horizons.

By Delin Zhao, Zhengrong Yue, Shaobin Zhuang, Junlin He, Xiaoyu Chen, Zikang Wang, Yuxin Liu, Limin Wang, Yali Wang
arXiv Machine Learning
Oct 9

How Long, Not How Close: A Learned Temporal Metric for Planning in Latent World Models

The paper introduces TEMPO, a temporal-distance planning objective that augments latent world models by learning a map of the frozen latent space where distances correspond to the number of environment steps between states. TEMPO blends this learned temporal distance into the planner’s cost, requiring no additional rewards or policies, and adds negligible computational overhead. Experiments on eleven simulated environments show that TEMPO consistently improves planner performance across all goal distances, notably raising LeWM’s success rate from 36% to 99% on the TwoRoom task.

By Lama Moukheiber, Haotian Xue, Yongxin Chen
arXiv Machine Learning
Sep 22

FIRM-WM: State-factorized factual-interventional recurrent modeling for reward-free visual planning

FIRM-WM is a compact pixel world model that separates a goal‑comparable configuration from a 128‑dimensional dynamic fiber, enabling reward‑free visual planning from offline videos. It addresses two key mismatches: aligning planning states with goal images and reconciling factual trajectories with interventional sampling. In experiments, FIRM‑WM achieves high success rates on TwoRoom, Reacher, and OGBench‑Cube while using fewer parameters and faster planning times than prior models.

By Yilun Wu, Yunjian Zhang, Aobo Li, Mujiangshan Wang, Haitao Wu, Aqiang Zhang
arXiv Machine Learning
Jun 26

Fast LeWorldModel

arXiv:2606. 26217v1 Announce Type: new Abstract: Joint-Embedding Predictive Architectures (JEPAs), including recent LeWorldModel (LeWM), have become a promising foundation for reconstruction-free visual world models.

By Yuntian Gao, Xiangyu Xu
arXiv Computer Vision
Nov 5

Time-to-Goal: Learned Temporal Metrics for Long-Horizon Planning with JEPA World Models

The paper introduces Time-to-Goal (T2G), a lightweight metric that learns temporal ordering for goal costs in Joint-Embedding Predictive Architectures (JEPAs). By training on latent triples from offline trajectories with a margin ranking loss, T2G replaces the Euclidean planning cost while keeping the JEPA encoder and predictor frozen. Experiments on AntMaze, FourRoom, and other navigation and manipulation benchmarks show that T2G improves planning success rates from 32.7% to 63.0% and matches or surpasses hierarchical H-JEPA baselines.

By Ruilong Yu, Fei Ye