Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Models

arXiv:2607.23602 · cs.RO, cs.AI, cs.LG · Submitted 2026-07-26 · Read on arXiv

cs.RO, cs.AI, cs.LG

Submitted: 2026-07-26

Updated: 2026-08-31

Comments: 23 pages, 7 figures. Includes supplementary material

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• World Model — 32× in this paper · explained in 7 episodes
• Latent World Models — 7× in this paper · explained in 2 episodes
• Verification — 7× in this paper · explained in 2 episodes
• Core — 6× in this paper · explained in 2 episodes
• Mixture of Controllers — 6× in this paper
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Adjacent Set Action Reconstruction — 5× in this paper
• Trace — 5× in this paper · explained in 2 episodes
• Provenance — 4× in this paper · explained in 3 episodes
• Trajectory Reachability Metrics — 4× in this paper
• Aggregation — 3× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Closed-Loop Control — 2× in this paper · explained in 2 episodes
• Latent Dynamics — 2× in this paper · explained in 2 episodes
• Verifier — 2× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Deep Reinforcement Learning — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Objective Mismatch — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sample Efficiency — 1× in this paper · explained in 4 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations
• SAGE: Subgoal-Conditioned Action Generation for Latent World Model Planning
• Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• Beyond the Next Step: Variable-Length Latent World Models for Long-Horizon Planning
• Search on the Replay Buffer: Bridging Planning and Reinforcement Learning
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
• Mastering Diverse Domains through World Models
• Transformers are Sample-Efficient World Models
• Offline Goal-conditioned Reinforcement Learning with Quasimetric Representations
• OGBench: Benchmarking Offline Goal-Conditioned RL
• Closing the Train-Test Gap in World Models for Gradient-Based Planning
• World Model Control by Trajectory Reachability Metrics
• UniZero: Generalized and Efficient Planning with Scalable Latent World Models
• Predictive but Not Plannable: RC-aux for Latent World Models
• Goal-Conditioned Reinforcement Learning with Disentanglement-based Reachability Planning
• stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
• PRISM: PRior-guided Imagination Sampling in world Models
• DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies