Predictive but Not Plannable: RC-aux for Latent World Models

• URL: http://arxiv.org/abs/2605.07278v1
• Date: Fri, 08 May 2026 05:43:33 GMT
• Title: Predictive but Not Plannable: RC-aux for Latent World Models
• Abstract summary: Reachability-Correction auxiliary (RC-aux)<n>We present Reachability-Correction auxiliary (RC-aux), a lightweight correction for this mismatch in reconstruction-free latent world models.<n>RC-aux keeps the world-model backbone unchanged and adds planning-aligned supervision along two axes.
• Score: 44.63243875072762
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A latent world model may achieve accurate short-horizon prediction while still inducing a latent space that is poorly aligned with planning. A key issue is spatiotemporal mismatch: these models are often trained with local predictive supervision, but deployed for long-horizon goal-directed search in latent spaces where Euclidean distance may not reflect what is reachable within a finite action budget. We present the Reachability-Correction auxiliary objective (RC-aux), a lightweight correction for this mismatch in reconstruction-free latent world models. RC-aux keeps the world-model backbone unchanged and adds planning-aligned supervision along two axes. Along the time axis, multi-horizon open-loop prediction trains the model beyond one-step consistency. Along the space axis, budget-conditioned reachability supervision, together with temporal hard negatives, encourages the latent space to distinguish states that are eventually reachable from those reachable within the current planning horizon. At test time, the learned reachability signal can also be used by a reachability-aware planner to favor trajectories that are both goal-directed and attainable under the available budget. We instantiate RC-aux on LeWorldModel and evaluate it under both continuation-training and matched-from-scratch settings. Across goal-conditioned pixel-control tasks and a LIBERO-Goal extension, RC-aux improves LeWM-style planning with modest additional cost. These results suggest that planning with latent world models depends not only on predictive accuracy, but also on whether the learned representation encodes the temporal and geometric structure required by downstream search. The code is available at https://github.com/Guang000/RC-aux.

Related papers

• LePlanner: An Iterative Amortized Controller For World Models [0.0]
  We propose LePlanner, an amortized iterative controller that learns to construct and refine latent action sequences through a frozen world-model predictor.<n>LePlanner is trained with an arrival-and-hold objective that encourages the controller to reach the goal at the earliest feasible horizon and remain there.<n>It achieves success rates of 98% on PushT, 100% on Reacher, 100% on TwoRooms, and 92% on the OGBench Cube task.
  arXiv  Detail & Related papers  (2026-09-12T10:01:21Z)
• Temporal-Distance JEPA: Plan-Aware Representation Learning for Latent World Model Predictive Control [8.39933163242427]
  JEPAs learn world models by predicting in representation space rather than reconstructing pixels.<n>Prior JEPA planners often inherit ranking from embedding geometry, typically latent Euclidean distance.<n>We propose Temporal-Distance-JEPA, which retains the LeWM encoder-predictor backbone and mines a directed temporal cost from reward-free trajectories.
  arXiv  Detail & Related papers  (2026-07-28T06:38:16Z)
• SkyJEPA: Learning Long-Horizon World Models for Zero-Shot Sim-to-Real Control of Quadrotors [48.60897189520386]
  We introduce the JEPA-style model for real-time quadrotor control.<n>We combine a latent dynamics model with a novel physics-inspired prober that maps frozen latents to interpretable state.<n>To reduce the dependence on expensive and unsafe real-world data collection, we develop a structured pipeline for automated dataset generation.
  arXiv  Detail & Related papers  (2026-06-22T15:00:59Z)
• Sensorimotor World Models: Perception for Action via Inverse Dynamics [59.121736411156384]
  We introduce a sensorimotor world model trained end-to-end with inverse dynamics regularization.<n>It prevents representation collapse and induces action-aligned representations.<n>It learns compact, interpretable latent spaces and enables competitive planning performance across simple 2D and 3D control tasks.
  arXiv  Detail & Related papers  (2026-06-18T11:25:16Z)
• GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving [56.50032398571235]
  GraphWorld is an E2E-AD framework that explicitly enhances long-horizon planning through latent world modeling.<n>We present a World-State-Conditioned Planning that learns ego-centric latent world representations by modeling interactions between an ego vehicle and surrounding agents.<n>This latent world state captures key interaction dynamics and safety-relevant semantics, and serves as a conditioning signal to guide long-horizon, safety-aware trajectory planning.
  arXiv  Detail & Related papers  (2026-06-15T06:26:46Z)
• Latent Goal Prediction from Language for Model-Based Planning [19.768973349254285]
  Latent Goal Prediction from Language (LAGO) is a framework that predicts both sequences of intermediate goal states from language instructions and action-conditioned rollouts.<n>By achieving robust and precise long-horizon planning purely from language, LAGO bridges the precision of visual goals with the flexibility of text-guided control.
  arXiv  Detail & Related papers  (2026-05-26T20:04:33Z)
• Latent Geometry Beyond Search: Amortizing Planning in World Models [17.571800971505787]
  We show that a learned representation can simplify control, rather than merely enabling prediction.<n>We replace iterative planning with a lightweight Goal-Conditioned Inverse Dynamics Model (GC-IDM)<n>Our controller matches or exceeds CEM in seven of eight environment-protocol settings while reducing per-decision cost by 100-130x.
  arXiv  Detail & Related papers  (2026-05-09T06:36:23Z)
• Hierarchical Planning with Latent World Models [49.82095442483551]
  hierarchical planning achieves higher success while requiring up to 4x less planning-time compute.<n>We demonstrate that this hierarchical approach enables zero-shot control on real-world non-greedy robotic tasks.
  arXiv  Detail & Related papers  (2026-04-03T17:32:36Z)
• Laplacian Representations for Decision-Time Planning [20.25004555858261]
  We show that the Laplacian representation provides an effective latent space for planning by capturing state-space distances at multiple time scales.<n>This representation preserves meaningful distances and naturally decomposes long-horizon problems into subgoals, also mitigating the compounding errors that arise over long prediction horizons.<n>We introduce ALPS, a hierarchical planning algorithm, and demonstrate that it outperforms commonly used baselines on a selection of offline goal-conditioned RL tasks from OGBench.
  arXiv  Detail & Related papers  (2026-02-04T20:34:50Z)
• Act2Goal: From World Model To General Goal-conditioned Policy [14.222177107215648]
  Act2Goal is a goal-conditioned manipulation policy that integrates a goal-conditioned visual world model with multi-scale temporal control.<n>We show that Act2Goal improves success rates from 30% to 90% on challenging out-of-distribution tasks within minutes of autonomous interaction.
  arXiv  Detail & Related papers  (2025-12-29T15:28:42Z)
• GrndCtrl: Grounding World Models via Self-Supervised Reward Alignment [16.343768407636322]
  We introduce Reinforcement Learning with World Grounding (RLWG), a self-supervised post-training framework that aligns pretrained world models with a physically verifiable structure through geometric and perceptual rewards.<n>We instantiate this framework with GrndCtrl, a reward-aligned adaptation method based on Group Relative Policy Optimization (GRPO), yielding world models that maintain stable trajectories, consistent geometry, and reliable rollouts for embodied navigation.
  arXiv  Detail & Related papers  (2025-12-01T18:03:29Z)
• World Model-Based Learning for Long-Term Age of Information Minimization in Vehicular Networks [53.98633183204453]
  In this paper, a novel world model-based learning framework is proposed to minimize packet-completeness-aware age of information (CAoI) in a vehicular network.<n>A world model framework is proposed to jointly learn a dynamic model of the mmWave V2X environment and use it to imagine trajectories for learning how to perform link scheduling.<n>In particular, the long-term policy is learned in differentiable imagined trajectories instead of environment interactions.
  arXiv  Detail & Related papers  (2025-05-03T06:23:18Z)
• Large-scale Autonomous Flight with Real-time Semantic SLAM under Dense Forest Canopy [48.51396198176273]
  We propose an integrated system that can perform large-scale autonomous flights and real-time semantic mapping in challenging under-canopy environments. We detect and model tree trunks and ground planes from LiDAR data, which are associated across scans and used to constrain robot poses as well as tree trunk models. A drift-compensation mechanism is designed to minimize the odometry drift using semantic SLAM outputs in real time, while maintaining planner optimality and controller stability.
  arXiv  Detail & Related papers  (2021-09-14T07:24:53Z)
• Model-Based Reinforcement Learning via Latent-Space Collocation [110.04005442935828]
  We argue that it is easier to solve long-horizon tasks by planning sequences of states rather than just actions. We adapt the idea of collocation, which has shown good results on long-horizon tasks in optimal control literature, to the image-based setting by utilizing learned latent state space models.
  arXiv  Detail & Related papers  (2021-06-24T17:59:18Z)
• Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors [124.30562402952319]
  The ability to predict and plan into the future is fundamental for agents acting in the world. Current learning approaches for visual prediction and planning fail on long-horizon tasks. We propose a framework for visual prediction and planning that is able to overcome both of these limitations.
  arXiv  Detail & Related papers  (2020-06-23T17:58:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.