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

• URL: http://arxiv.org/abs/2606.05645v2
• Date: Tue, 09 Jun 2026 07:25:40 GMT
• Title: Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning
• Abstract summary: We introduce Discrete-WAM, a unified vision-action world-policy framework that represents visual observations, future states, high-level decisions, and ego actions within a shared token space.<n>Built on this discrete alignment, Discrete-WAM jointly trains world modeling, world-policy modeling, and policy modeling through multi-task and multi-stage pretraining.<n>Experiments 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.
• Score: 28.162567330430928
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence [54.62791372989525]
  Action models, vision-language--action policies, and world models have advanced this goal.<n>World Action Models (WAMs) are particularly promising because they connect candidate interventions with predicted consequences.<n>We review the evolution toward WAMs and organize these limitations into three coupled gaps: model roles and representations, objectives and standardization, and system composition.
  arXiv  Detail & Related papers  (2026-07-13T15:22:56Z)
• NavWM: A Unified Navigation World Model for Foresight-Driven Planning [15.801647085785826]
  NavWM is a unified navigation world model that seamlessly integrates latent world reasoning, multimodal action prediction, and controllable visual generation.<n>To overcome the limitations of deterministic policies, we introduce an anchor-based multimodal trajectory forecasting framework.<n>Experiments across diverse datasets demonstrate that NavWM significantly advances the state-the-art.
  arXiv  Detail & Related papers  (2026-06-23T03:30:20Z)
• WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigation [42.8714305455232]
  We argue that the ability to "imagine" future states is critical for robust decision-making under such partial observability.<n>We propose WorldFly, a novel world-model-based VLA framework that employs a dual-branch coupled flow matching mechanism to jointly generate future video predictions and navigation actions.
  arXiv  Detail & Related papers  (2026-06-04T13:23:05Z)
• Post-Deterministic Distributed Systems: A New Foundation for Trustworthy Autonomous Infrastructure [2.124730017640531]
  Post-deterministic Distributed Systems is a research and engineering model for coordinating heterogeneous environments.<n>We show that classical distributed computing models form a zero-ambiguity special case of this participant model.<n>We outline five architectural pillars of post-deterministic infrastructure: Protocol-Driven Development, Verifiable Agentic Infrastructure, Autonomous State Control Planes, Semantic Quorum Assurance, and Epistemic State Replication.
  arXiv  Detail & Related papers  (2026-06-01T05:37:59Z)
• HEAT: Heterogeneous End-to-End Autonomous Driving via Trajectory-Guided World Models [50.18051979020699]
  End-to-end autonomous driving has emerged as a compelling alternative to traditional modular pipelines.<n>We propose a trajectory-driven learning paradigm that organizes training around planning trajectories.<n>We show that a single unified model can be trained on heterogeneous datasets while maintaining strong performance within each domain.
  arXiv  Detail & Related papers  (2026-05-19T10:12:01Z)
• World Action Models: The Next Frontier in Embodied AI [123.5787299299832]
  Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning.<n>They learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under intervention.<n>A growing body of work addresses this limitation by integrating world models, predictive models of environment dynamics, into the action generation pipeline.
  arXiv  Detail & Related papers  (2026-05-12T13:10:52Z)
• CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving [4.4380564455353975]
  CoWorld-VLA is a multi-expert world reasoning framework for autonomous driving.<n>World representations serve as explicit conditions to guide action planning.<n>Experiments show that CoWorld-VLA achieves competitive results in both future scene generation and planning.
  arXiv  Detail & Related papers  (2026-05-11T12:01:13Z)
• Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving [52.04950569530877]
  We present Uni-World VLA, a unified vision-language-action model that tightly interleaves future frame prediction and trajectory planning.<n>Our approach achieves competitive closed-loop planning performance while producing high-fidelity future frame predictions.
  arXiv  Detail & Related papers  (2026-03-28T14:39:51Z)
• The Trinity of Consistency as a Defining Principle for General World Models [106.16462830681452]
  General World Models are capable of learning, simulating, and reasoning about objective physical laws.<n>We propose a principled theoretical framework that defines the essential properties requisite for a General World Model.<n>Our work establishes a principled pathway toward general world models, clarifying both the limitations of current systems and the architectural requirements for future progress.
  arXiv  Detail & Related papers  (2026-02-26T16:15:55Z)
• Imagine-then-Plan: Agent Learning from Adaptive Lookahead with World Models [13.90532093512575]
  We propose Imagine-then-Plan (textttITP), a unified framework for agent learning via lookahead imagination.<n>We introduce a novel adaptive lookahead mechanism by trading off the ultimate goal and task progress.<n>Our experiments show that textttITP significantly outperforms competitive baselines.
  arXiv  Detail & Related papers  (2026-01-13T19:49:58Z)
• From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction [57.56072009935036]
  We introduce a new driving paradigm named Policy World Model (PWM)<n>PWM integrates world modeling and trajectory planning within a unified architecture.<n>Our method matches or exceeds state-of-the-art approaches that rely on multi-view and multi-modal inputs.
  arXiv  Detail & Related papers  (2025-10-22T14:57:51Z)
• ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving [64.12414815634847]
  Vision-Language Models (VLMs) and Driving World Models (DWMs) have independently emerged as powerful recipes addressing different aspects of this challenge.<n>We propose ImagiDrive, a novel end-to-end autonomous driving framework that integrates a VLM-based driving agent with a DWM-based scene imaginer.
  arXiv  Detail & Related papers  (2025-08-15T12:06:55Z)
• Isolating and Leveraging Controllable and Noncontrollable Visual Dynamics in World Models [65.97707691164558]
  We present Iso-Dream, which improves the Dream-to-Control framework in two aspects. First, by optimizing inverse dynamics, we encourage world model to learn controllable and noncontrollable sources. Second, we optimize the behavior of the agent on the decoupled latent imaginations of the world model.
  arXiv  Detail & Related papers  (2022-05-27T08:07:39Z)
• Instance-Aware Predictive Navigation in Multi-Agent Environments [93.15055834395304]
  We propose an Instance-Aware Predictive Control (IPC) approach, which forecasts interactions between agents as well as future scene structures. We adopt a novel multi-instance event prediction module to estimate the possible interaction among agents in the ego-centric view. We design a sequential action sampling strategy to better leverage predicted states on both scene-level and instance-level.
  arXiv  Detail & Related papers  (2021-01-14T22:21:25Z)

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.