# Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigation

arXiv: https://arxiv.org/abs/2606.15869 · HTML: https://mlsanity.com/paper/2606.15869/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in World models for autonomous driving, one of 11 directions in World models.
- Builds on 94 of its 98 references that are in the map.
- First posted on arXiv 14 Jun 2026.

## Placed in

- World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-driving/)
- End-to-end autonomous driving / [Generative simulation for driving](https://mlsanity.com/driving/generative-simulation-for-driving/)

## Builds on (most cited first, 30 of 94)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [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)
- [NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking](https://mlsanity.com/paper/2406.15349/) (2024)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability](https://mlsanity.com/paper/2405.17398/) (2024)
- [DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2411.15139/) (2024)
- [Causal World Modeling for Robot Control](https://mlsanity.com/paper/2601.21998/) (2026)
- [Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving](https://mlsanity.com/paper/2311.17918/) (2023)
- [LMDrive: Closed-Loop End-to-End Driving with Large Language Models](https://mlsanity.com/paper/2312.07488/) (2023)
- [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026)
- [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)
- [Motus: A Unified Latent Action World Model](https://mlsanity.com/paper/2512.13030/) (2025)
- [NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration](https://mlsanity.com/paper/2310.07896/) (2023)
- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [NaVid: Video-based VLM Plans the Next Step for Vision-and-Language Navigation](https://mlsanity.com/paper/2402.15852/) (2024)
- [ViNT: A Foundation Model for Visual Navigation](https://mlsanity.com/paper/2306.14846/) (2023)
- [World Simulation with Video Foundation Models for Physical AI](https://mlsanity.com/paper/2511.00062/) (2025)
- [ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving](https://mlsanity.com/paper/2506.08052/) (2025)
- [GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2503.20523/) (2025)
- [ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation](https://mlsanity.com/paper/2503.19755/) (2025)
- [GNM: A General Navigation Model to Drive Any Robot](https://mlsanity.com/paper/2210.03370/) (2022)

## Built on by (most cited first, 11 of 11)

- [SimWAM: A Simple World Action Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2608.07468/) (2026)
- [N0-TWAM: Scaling Tactile-Native World-Action Model for Contact-Rich Manipulation](https://mlsanity.com/paper/2607.23783/) (2026)
- [SUV: Future Scene Understanding as Video Generation for End-to-End Driving](https://mlsanity.com/paper/2608.03084/) (2026)
- [UniNav: A Unified World-Action Diffusion Model for Visual Navigation](https://mlsanity.com/paper/2608.03244/) (2026)
- [4D-WAM: 4D Consistent World Modeling for Autonomous Driving](https://mlsanity.com/paper/2608.10107/) (2026)
- [MM-Future: Multi-Mode Joint World-Action Modeling for Autonomous Driving](https://mlsanity.com/paper/2609.20377/) (2026)
- [DriveReferee: Geometric Safety Verdicts Need Not Be Learned for Driving World-Action Models](https://mlsanity.com/paper/2609.22762/) (2026)
- [ReDrive: Shaping Representations with World Modeling for End-to-End Driving](https://mlsanity.com/paper/2609.33854/) (2026)
- [V2X-WAM: A Cooperative World Action Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2609.37098/) (2026)
- [Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse Imagination](https://mlsanity.com/paper/2609.38984/) (2026)
- [VITAL: From Visual Motion to Precise Action](https://mlsanity.com/paper/2610.20604/) (2026)

## Abstract (arXiv)

World action models~(WAMs) have shown great promise for autonomous driving and urban navigation. Built upon Vision-Language-Action models or video generation models, existing approaches suffer key limitations: (1) High inference latency due to future observation prediction at test time, and (2) tightly coupled video and action modeling leading to representational mismatch and degraded generalization. To address both issues, we propose Metis, an end-to-end WAM framework that decouples video generation and action prediction. Specifically, Metis employs a Mixture-of-Transformers architecture with dedicated experts for video generation and action prediction, preserving the intrinsic distributional properties of each task. To enhance efficiency, we introduce an asymmetric attention mask that enables joint training of both experts while allowing the action model to bypass explicit video generation during inference. This design ensures training-inference consistency and significantly reduces computational costs without compromising planning performance. Extensive experiments demonstrate state-of-the-art performance on the NAVSIM navhard and navtest benchmarks and the CityWalker navigation benchmark, validating both the generalizability and efficiency across diverse tasks. Real-robot deployments further confirm the practical feasibility of our approach.