arXiv Machine Learning
Jun 18
Hierarchical Planning with Latent World Models
arXiv:2604. 03208v2 Announce Type: replace Abstract: World models are a promising path to zero-shot embodied control through planning.
Mind the Gap: Promises and Pitfalls of Hierarchical Planning in LeWorldModel
arXiv:2607. 12547v1 Announce Type: cross Abstract: We investigate whether temporal hierarchy can improve LeWorldModel on long-horizon goal-conditioned control.
Related stories
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.
arXiv AI
Jul 21
SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning
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.
arXiv AI
4d ago
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 Machine Learning
Jun 8
Latent Geometry Beyond Search: Amortizing Planning in World Models
arXiv:2605. 08732v2 Announce Type: replace-cross Abstract: Modern vision-based world models can represent observations as compact yet expressive latent manifolds, but fast goal-oriented planning in these spaces remains challenging.
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.
Hugging Face Trending Papers
Sep 3
Latent Energy Action Planning with World Models
Latent Energy Action Planning (LEAP) improves model predictive control by treating the entire action horizon as a differentiable variable and optimizing it using a frozen LeWorldModel (LeWM). LEAP couples terminal latent goal matching with a terminal-window state energy, ensuring both the predicted terminal latent and the decoder-predicted terminal descriptor align with the goal. In four control domains, LEAP raises mean success from 77.5% (LeWM+CEM) to 94.8%, a 17.3‑percentage‑point improvement while keeping the frozen LeWM representation.
arXiv AI
Sep 15
LePlanner: An Iterative Amortized Controller For World Models
arXiv:2609.13845v1 Announce Type: cross Abstract: World models trained with joint-embedding predictive architectures learn compact, structured latent representations from physical interaction, yet pl...
arXiv Machine Learning
Sep 4
Latent Energy Action Planning with World Models
Latent Energy Action Planning (LEAP) is a new method that treats the entire action horizon as a differentiable variable and optimizes it using a frozen LeWorldModel (LeWM). LEAP couples terminal latent goal matching with a terminal‑window state energy, ensuring that the predicted terminal latent and decoder‑predicted terminal descriptor align with the goal. Using a frozen goal‑conditioned proposal, a quasi‑Newton solver, and post‑optimization projection, LEAP improves mean success from 77.5% to 94.8% across four control domains while keeping the LeWM representation frozen.
arXiv AI
4d ago
HorizonFlow: Variable-Length Planning for Offline Goal-Conditioned RL
HorizonFlow is a hierarchical planner for offline goal-conditioned reinforcement learning that treats the planning horizon as an output rather than a fixed input. It uses a subgoal route planner and an action-prefix controller, both employing insertion-based generation and flow matching, to jointly generate continuous plan content and its length. The method leverages the partially generated plan to guide token insertion and to steer generation toward shorter plans, achieving superior performance on Maze2D, Multi2D, and OGBench benchmarks.
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.
Hugging Face Trending Papers
Jul 23
Offline RL with Hierarchical Action Chunking
Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose policies from static datasets. However, scaling these methods to long-horizon tasks remains a challenge due to the curse of horizon, where value estimation errors can compound through long chains of bootstrapped Bellman backups.