# Embodied and robot world models Area: [World models](https://mlsanity.com/wm/index.md). HTML: https://mlsanity.com/wm/embodied-and-robot-world-models/ ## Key facts - Embodied and robot world models: 575 papers on arXiv since 2014 (data through 14 Oct 2026). - 187 of its 575 mapped papers (33%) cite “Diffusion Policy: Visuomotor Policy Learning via Action Diffusion” (2023, arXiv 2303.04137). - 163 of its 575 mapped papers (28%) cite “World Action Models are Zero-shot Policies” (2026, arXiv 2602.15922). - 160 new papers 17 Sep–14 Oct. ## Most cited here - [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023), cited by 187 papers here - [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026), cited by 163 papers here - [Causal World Modeling for Robot Control](https://mlsanity.com/paper/2601.21998/) (2026), cited by 137 papers here - [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026), cited by 135 papers here - [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025), cited by 119 papers here - [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025), cited by 117 papers here - [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025), cited by 105 papers here - [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025), cited by 94 papers here - [Ctrl-World: A Controllable Generative World Model for Robot Manipulation](https://mlsanity.com/paper/2510.10125/) (2025), cited by 82 papers here - [RoboDreamer: Learning Compositional World Models for Robot Imagination](https://mlsanity.com/paper/2404.12377/) (2024), cited by 79 papers here ## New (17 Sep–14 Oct) - [VITAL: From Visual Motion to Precise Action](https://mlsanity.com/paper/2610.20604/) (2026-10-14) - [OneLA: Learning Many Worlds from Latent Actions](https://mlsanity.com/paper/2610.20160/) (2026-10-14) - [Atomic-WAM: Execution-Grounded Atomic-Motion Reasoning for World Action Models](https://mlsanity.com/paper/2610.20157/) (2026-10-14) - [Complementary Future Token Pruning for World Action Models](https://mlsanity.com/paper/2610.19957/) (2026-10-14) - [LoopWAM: Closed-Loop Generalist Policy Improvement from Deployment Rollouts](https://mlsanity.com/paper/2610.18873/) (2026-10-13) - [ForceWAM: Decoupling Future and Response Learning from Demo and Play Data for Contact-Rich Manipulation](https://mlsanity.com/paper/2610.18852/) (2026-10-13) - [WorldOracle: Benchmarking Action-Conditioned World Models against Real-World Executions](https://mlsanity.com/paper/2610.18826/) (2026-10-13) - [GreenWAM: A World Foundation Model for Robotics](https://mlsanity.com/paper/2610.18774/) (2026-10-13) - [RoboFQE: Rollout-Free Evaluation of Visual Robot Policies from Offline Trajectories](https://mlsanity.com/paper/2610.18699/) (2026-10-13) - [UniW(A)M: A Unified Mixture-of-Experts Framework for World and World-Action Models](https://mlsanity.com/paper/2610.18697/) (2026-10-13) - [WAVE-0: Bridging VLA Policies and WAMs with Lightweight Latent Future Prediction](https://mlsanity.com/paper/2610.18568/) (2026-10-13) - [Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence](https://mlsanity.com/paper/2610.18447/) (2026-10-13) - [Data-Free Continual Learning for World Action Model with Rectified Generative Replay](https://mlsanity.com/paper/2610.18038/) (2026-10-13) - [WoVR+: World Model as Reliable Simulator for Versatile VLA Policy Optimization with RL](https://mlsanity.com/paper/2610.17922/) (2026-10-13) - [Acting Through Registers](https://mlsanity.com/paper/2610.17638/) (2026-10-13) - [From Pixels to Executable Physics: Behavior-Grounded World Models for Embodied Action Consequence Prediction](https://mlsanity.com/paper/2610.17630/) (2026-10-13) - [Box-WAM: Box Trajectories as Compact State Representations for World Action Models](https://mlsanity.com/paper/2610.17526/) (2026-10-13) - [MARS: Systematic Multi-Level Acceleration for World Action Models](https://mlsanity.com/paper/2610.17141/) (2026-10-12) - [D-World: An Explicit World-Language-Action Model with Recursive Self-Improvement under Dual Control](https://mlsanity.com/paper/2610.17114/) (2026-10-12) - [What Limits Cross-Task Generalization in World Action Models?](https://mlsanity.com/paper/2610.16641/) (2026-10-12) - [RAP-WAM: Learning World-Action Models through Predictive Rehearsal and Action Perturbations](https://mlsanity.com/paper/2610.16443/) (2026-10-12) - [PINT: A Unified Model with Shared Predictive Intent for Robot Manipulation](https://mlsanity.com/paper/2610.16355/) (2026-10-12) - [1Step-WAM: Your World Action Model but Faster using 1-Step Action Generation](https://mlsanity.com/paper/2610.15625/) (2026-10-11) - [StreamingWAM: Streaming World Action Modeling via Chunk-Wise Staircase Flow Matching](https://mlsanity.com/paper/2610.15585/) (2026-10-11) - [RM-WAM: Reliable Memory-Augmented World Action Models for Long-Horizon Robot Manipulation](https://mlsanity.com/paper/2610.15305/) (2026-10-11) - [ProWorld: Multi-View World Model with Proprioceptive Feedback for Closed-Loop Policy Evaluation](https://mlsanity.com/paper/2610.15294/) (2026-10-11) - [BridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries](https://mlsanity.com/paper/2610.14746/) (2026-10-10) - [CAG-WAM: Causal Action-Gain World Action Models for Robot Manipulation](https://mlsanity.com/paper/2610.14720/) (2026-10-10) - [Remembering What Matters for Long-Horizon Robotic World Models](https://mlsanity.com/paper/2610.14583/) (2026-10-10) - [Learning Transferable World-Action Models from Task-Paired Human Videos](https://mlsanity.com/paper/2610.14351/) (2026-10-09)