arXiv:2608. 16287v1 Announce Type: new Abstract: Joint-embedding predictive world models plan by scoring predicted terminal embeddings against a goal embedding using a cost defined on the representation itself.
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:2606.20627v2 Announce Type: replace Abstract: Joint-Embedding Predictive Architectures (JEPAs) enable agents to plan in latent space by imagining the outcomes of candidate actions, yet task spe...
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.
arXiv:2610.27280v1 Announce Type: cross Abstract: Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based meth...
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.
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.
arXiv:2606. 09311v1 Announce Type: new Abstract: Joint Embedding Predictive Architectures (JEPAs) have shown promising world modeling capabilities, enabling planning in latent space by optimizing action trajectories using methods like the Cross-Entropy Method (CEM).
Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based methods allow for planning by scaling test-time compute...
arXiv:2607. 17973v1 Announce Type: new Abstract: Latent world models have emerged as a powerful planning paradigm by learning action-conditioned predictive dynamics and using them as internal simulators to imagine and evaluate candidate action sequences.
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.
The paper introduces SCALE (State-CAlibrated Latent Embeddings), a technique that aligns pairwise latent distances with task-relevant state-space distances in joint-embedding predictive world models. By adding SCALE to the LeWorldModel (LeWM) objective, the authors preserve LeWM’s architecture while ensuring that latent geometry reflects meaningful task outcomes. Experiments demonstrate that SCALE improves planning success across manipulation and navigation tasks with various solvers, and the authors analyze how the method reshapes representation geometry to support planning.