mlsanityData to 7 Oct 2026

DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving

arXiv 2510.12796 ↗First posted 14 Oct 2025cs.CV cs.AIcited by 127

On the map: World models → World models for autonomous driving

also in 2 more
Abstract (arXiv)

Scaling Vision-Language-Action (VLA) models on large-scale data offers a promising path to achieving a more generalized driving intelligence. However, VLA models are limited by a ``supervision deficit'': the vast model capacity is supervised by sparse, low-dimensional actions, leaving much of their representational power underutilized. To remedy this, we propose DriveVLA-W0, a training paradigm that employs world modeling to predict future images. This task generates a dense, self-supervised signal that compels the model to learn the underlying dynamics of the driving environment. We showcase the paradigm's versatility by instantiating it for two dominant VLA archetypes: an autoregressive world model for VLAs that use discrete visual tokens, and a diffusion world model for those operating on continuous visual features. Building on the rich representations learned from world modeling, we introduce a lightweight action expert to address the inference latency for real-time deployment. Extensive experiments on the NAVSIM v1/v2 benchmark and a 680x larger in-house dataset demonstrate that DriveVLA-W0 significantly outperforms BEV and VLA baselines. Crucially, it amplifies the data scaling law, showing that performance gains accelerate as the training dataset size increases.

Key facts. Cited by 127 papers in the map (data through 7 Oct 2026). Placed in World models for autonomous driving, one of 11 directions in World models. Builds on 54 of its 61 references that are in the map. First posted on arXiv 14 Oct 2025.

Builds on

54 of 61 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025End-to-End Driving with Online Trajectory Evaluation via BEV World Model2 Apr
  2. 2025VaViM and VaVAM: Autonomous Driving through Video Generative Modeling21 Feb
  3. 2024DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers24 Dec
  4. 2024Doe-1: Closed-Loop Autonomous Driving with Large World Model12 Dec
  5. 2024Enhancing End-to-End Autonomous Driving with Latent World Model12 Jun
  6. 2023Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion2 Nov
  7. 2023GAIA-1: A Generative World Model for Autonomous Driving29 Sep
  8. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers31 Mar
  9. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles22 Jun

Other references · 45

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2020Scaling Laws for Neural Language Modelscited by 6,411
  3. 2025Qwen2.5-VL Technical Reportcited by 5,418
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  5. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  6. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  7. 2025DINOv3cited by 1,297
  8. 2021Scaling Vision Transformerscited by 993
  9. 2024Emu3: Next-Token Prediction is All You Needcited by 761
  10. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  11. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  12. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
33 more
  1. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 613
  2. 2023DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Modelcited by 455
  3. 2021Multi-Modal Fusion Transformer for End-to-End Autonomous Drivingcited by 372
  4. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 351
  5. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarkingcited by 343
  6. 2024DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Drivingcited by 324
  7. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuningcited by 252
  8. 2024Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillationcited by 244
  9. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 190
  10. 2025ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generationcited by 177
  11. 2025OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Modelcited by 172
  12. 2025FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Drivingcited by 165
  13. 2025SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignmentcited by 149
  14. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulationcited by 144
  15. 2025Pseudo-Simulation for Autonomous Drivingcited by 141
  16. 2025Unified Vision-Language-Action Modelcited by 128
  17. 2022MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generationcited by 125
  18. 2024RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Modelcited by 91
  19. 2025DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planningcited by 91
  20. 2025DriveMoE: Mixture-of-Experts for Vision-Language-Action Model in End-to-End Autonomous Drivingcited by 85
  21. 2024CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Drivingcited by 74
  22. 2025ARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Drivingcited by 66
  23. 2025DiffVLA: Vision-Language Guided Diffusion Planning for Autonomous Drivingcited by 64
  24. 2024CarLLaVA: Vision language models for camera-only closed-loop drivingcited by 57
  25. 2024Reconstructive Visual Instruction Tuningcited by 54
  26. 2025Interleave-VLA: Enhancing Robot Manipulation with Interleaved Image-Text Instructionscited by 50
  27. 2025LangCoop: Collaborative Driving with Languagecited by 25
  28. 2023Large Trajectory Models are Scalable Motion Predictors and Plannerscited by 23
  29. 2025SafeAuto: Knowledge-Enhanced Safe Autonomous Driving with Multimodal Foundation Modelscited by 22
  30. 2025Scaling Laws of Motion Forecasting and Planning -- Technical Reportcited by 19
  31. 2025Data Scaling Laws for End-to-End Autonomous Drivingcited by 14
  32. 2025DynRsl-VLM: Enhancing Autonomous Driving Perception with Dynamic Resolution Vision-Language Modelscited by 12
  33. 2025TS-VLM: Text-Guided SoftSort Pooling for Vision-Language Models in Multi-View Driving Reasoningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 118.

127 papers.

Sort:

By area:

  1. 2025DriveLaW:Unifying Planning and Video Generation in a Latent Driving Worldcited by 43
  2. 2026World Model for Robot Learning: A Comprehensive Surveycited by 42
  3. 2026Driving on Registerscited by 38
  4. 2026DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generationcited by 36
  5. 2025SimScale: Learning to Drive via Real-World Simulation at Scalecited by 34
  6. 2025Vision-Language-Action Models for Autonomous Driving: Past, Present, and Futurecited by 32
  7. 2026DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Drivingcited by 31
  8. 2026MIND: Benchmarking Memory Consistency and Action Control in World Modelscited by 31
  9. 2026Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Drivingcited by 27
  10. 2026LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Drivingcited by 26
  11. 2026GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learningcited by 23
  12. 2026UniDrive-WM: Unified Understanding, Planning and Generation World Model for Autonomous Drivingcited by 20
38 more
  1. 2026DriveVA: Video Action Models are Zero-Shot Driverscited by 19
  2. 2026DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Drivingcited by 18
  3. 2026Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failurescited by 17
  4. 2026DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planningcited by 17
  5. 2026UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Drivingcited by 17
  6. 2025DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planningcited by 15
  7. 2026SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Modelcited by 15
  8. 2026DriveFuture: Future-Aware Latent World Models for Autonomous Drivingcited by 15
  9. 2026Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Modelscited by 14
  10. 2026Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representationcited by 13
  11. 2026DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Drivingcited by 13
  12. 2025Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresightcited by 12
  13. 2026Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directionscited by 12
  14. 2026DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scalecited by 12
  15. 2026EponaV2: Driving World Model with Comprehensive Future Reasoningcited by 12
  16. 2026DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Drivingcited by 12
  17. 2026DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Drivingcited by 11
  18. 2025WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Drivingcited by 10
  19. 2026ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Drivingcited by 10
  20. 2026CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Drivingcited by 10
  21. 2026World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesiscited by 10
  22. 2026Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigationcited by 10
  23. 2026FLARE: Learning Future-Aware Latent Representations from Vision-Language Models for Autonomous Drivingcited by 9
  24. 2026Unifying Language-Action Understanding and Generation for Autonomous Drivingcited by 9
  25. 2026Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Drivingcited by 9
  26. 2026CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planningcited by 9
  27. 2026Test-Time Trajectory Optimization for Autonomous Drivingcited by 7
  28. 2026Vega: Learning to Drive with Natural Language Instructionscited by 6
  29. 2026MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Drivingcited by 6
  30. 2026GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Drivingcited by 6
  31. 2026World Engine: Towards the Era of Post-Training for Autonomous Drivingcited by 6
  32. 2026DreamWAM: Beyond RGB Future Prediction for World Action Modelscited by 6
  33. 2026UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generationcited by 5
  34. 2026SimWAM: A Simple World Action Model for End-to-End Autonomous Drivingcited by 5
  35. 2025DAP: A Discrete-token Autoregressive Planner for Autonomous Drivingcited by 4
  36. 2025Forging Spatial Intelligence: A Roadmap of Multi-Modal Data Pre-Training for Autonomous Systemscited by 4
  37. 2026Auto-JEPA: A Latent World Model of Continuous Intent for End-to-End Autonomous Drivingcited by 4
  38. 2026EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillationcited by 3

50 most cited of 127 All 127 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning Vision-Language-Action World Models for Autonomous Driving
  2. 2025DriveAction: A Benchmark for Exploring Human-like Driving Decisions in VLA Models
  3. 2026FIVE-VLA: Fast and EffectIVE Autonomous Driving with Recurrent Action Memory
  4. 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models
  5. 2026RAF-VLA: Representation Alignment with the Future for End-to-End Autonomous Driving
  6. 2026Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Driving
  7. 2026WorldVLM: Combining World Model Forecasting and Vision-Language Reasoning
  8. 2025Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving