# Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning

arXiv: https://arxiv.org/abs/2606.05645 · HTML: https://mlsanity.com/paper/2606.05645/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 58 of its 103 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 30 of 58)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [WorldVLA: Towards Autoregressive Action World Model](https://mlsanity.com/paper/2506.21539/) (2025)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026)
- [VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning](https://mlsanity.com/paper/2402.13243/) (2024)
- [AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.13757/) (2025)
- [Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation](https://mlsanity.com/paper/2406.06978/) (2024)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving](https://mlsanity.com/paper/2506.08052/) (2025)
- [Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning](https://mlsanity.com/paper/2503.15558/) (2025)
- [GenAD: Generalized Predictive Model for Autonomous Driving](https://mlsanity.com/paper/2403.09630/) (2024)
- [Pseudo-Simulation for Autonomous Driving](https://mlsanity.com/paper/2506.04218/) (2025)
- [DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos](https://mlsanity.com/paper/2602.06949/) (2026)
- [DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving](https://mlsanity.com/paper/2510.12796/) (2025)
- [OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2409.03272/) (2024)
- [Path Planning for Masked Diffusion Model Sampling](https://mlsanity.com/paper/2502.03540/) (2025)
- [DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control](https://mlsanity.com/paper/2603.10448/) (2026)
- [3D and 4D World Modeling: A Survey](https://mlsanity.com/paper/2509.07996/) (2025)
- [DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT](https://mlsanity.com/paper/2412.19505/) (2024)
- [Think While You Generate: Discrete Diffusion with Planned Denoising](https://mlsanity.com/paper/2410.06264/) (2024)
- [Informed Correctors for Discrete Diffusion Models](https://mlsanity.com/paper/2407.21243/) (2024)
- [DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving](https://mlsanity.com/paper/2512.07745/) (2025)
- [iPad: Iterative Proposal-centric End-to-End Autonomous Driving](https://mlsanity.com/paper/2505.15111/) (2025)
- [RISE: Self-Improving Robot Policy with Compositional World Model](https://mlsanity.com/paper/2602.11075/) (2026)
- [SimScale: Learning to Drive via Real-World Simulation at Scale](https://mlsanity.com/paper/2511.23369/) (2025)

## Built on by (most cited first, 4 of 4)

- [WA-JEPA: Rethinking the Video JEPA Paradigm for World-Action Modeling in Autonomous Driving](https://mlsanity.com/paper/2608.20974/) (2026)
- [MM-Future: Multi-Mode Joint World-Action Modeling for Autonomous Driving](https://mlsanity.com/paper/2609.20377/) (2026)
- [World4Scorer: Outcome-Grounded World Modeling for Autonomous Driving](https://mlsanity.com/paper/2609.36438/) (2026)
- [MORE: Learning Motion-Oriented Registers for Driving World Models and Planning](https://mlsanity.com/paper/2610.14871/) (2026)

## Abstract (arXiv)

Autonomous driving requires reasoning about how ego actions shape future world evolution, rather than merely mapping observations to actions. However, most end-to-end methods rely on direct state-to-action imitation, while existing world models often remain weakly aligned with downstream policy generation. We introduce Discrete-WAM, a unified discrete vision-action world-policy framework that represents visual observations, future states, high-level decisions, and ego actions within a shared token space. Built on this discrete alignment, Discrete-WAM jointly trains world modeling, world-policy modeling, and policy modeling through multi-task and multi-stage pretraining, allowing action-conditioned future prediction to directly support policy generation. For downstream planning, Discrete-WAM further decomposes policy generation into hierarchical decision prediction and parallel action-token editing, where the decision token provides a high-level planning skeleton and confidence-based scheduling refines dense future actions efficiently. Experiments on large-scale autonomous-driving benchmarks show that Discrete-WAM achieves strong planning performance while supporting controllable future generation, counterfactual evaluation, surprise-based world-model analysis, and efficient parallel policy decoding. These results suggest that discrete representation alignment, unified world-policy training, and hierarchical token editing provide a promising design paradigm for physical AI.