arXiv AI

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.

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
arXiv AI
Oct 19

Beyond Action Prediction: Learning Search-Free Planning in Latent Space

The paper introduces Hindsight Inverse JEPA Planning (HIJP), a search‑free framework that replaces costly online action sequence optimization with a goal‑conditioned inverse model. HIJP trains by relabeling future observations as goals, providing action supervision across multiple horizons and shaping visual representations. The method also aligns predicted actions with a latent predictor model to enforce action‑transition consistency, achieving high success rates and significant speedups on visual control tasks.

By Guanchen Du, Jinhao Du, Yanpeng Sun, Shan Zhang, Na Zhao, Zechao Li
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 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 Machine Learning
Sep 30

FlexiWorld: Learning and Planning via Flexible Action Chunks Across Multiple Time Scales

FlexiWorld is a JEPA-based latent world model that learns variable‑length action chunks across multiple time scales for goal‑directed planning. It jointly trains a causal action encoder and an autoregressive actor, using mixed‑span goal supervision and Student Forcing to reduce exposure bias. In experiments on four benchmarks, FlexiWorld with the Actor‑Residual Cross‑Entropy Method (ARCEM) achieves higher mean success rates than the strongest baseline and supports flexible planning chunk lengths without retraining.

By Shidu Ren, Qilin Gu, Zhenghao Ni, Junhan Sun, Jiaqi Wang, Damien Scieur, Yunze Liu
arXiv Machine Learning
Sep 25

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.

By Xvyuan Liu, Jianjie Fang, Chen Gao, Yong Li