# Is Your Driving World Model an All-Around Player?

arXiv: https://arxiv.org/abs/2605.10858 · HTML: https://mlsanity.com/paper/2605.10858/

## Key facts

- Cited by 6 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 33 of its 36 references that are in the map.
- First posted on arXiv 11 May 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 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Depth Anything V2](https://mlsanity.com/paper/2406.09414/) (2024)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control](https://mlsanity.com/paper/2503.03751/) (2025)
- [MagicDrive: Street View Generation with Diverse 3D Geometry Control](https://mlsanity.com/paper/2310.02601/) (2023)
- [DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation](https://mlsanity.com/paper/2403.06845/) (2024)
- [GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2503.20523/) (2025)
- [DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving](https://mlsanity.com/paper/2408.00415/) (2024)
- [SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction](https://mlsanity.com/paper/2404.09502/) (2024)
- [3D and 4D World Modeling: A Survey](https://mlsanity.com/paper/2509.07996/) (2025)
- [DiST-4D: Disentangled Spatiotemporal Diffusion with Metric Depth for 4D Driving Scene Generation](https://mlsanity.com/paper/2503.15208/) (2025)
- [DreamForge: Motion-Aware Autoregressive Video Generation for Multi-View Driving Scenes](https://mlsanity.com/paper/2409.04003/) (2024)
- [ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association](https://mlsanity.com/paper/2405.08909/) (2024)
- [WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World](https://mlsanity.com/paper/2512.10958/) (2025)

## Built on by (most cited first, 6 of 6)

- [VOICE: A Vision-Omics Foundation Model Integrating Direct and Retrieval-Based Prediction of In-situ Single-Cell Gene Expression](https://mlsanity.com/paper/2608.08366/) (2026)
- [Beyond Representation Learning: A Systematic Study of Joint-Embedding Predictive Generation for 3D Brain MRI](https://mlsanity.com/paper/2608.28787/) (2026)
- [Quo Vadis, World Modeling?](https://mlsanity.com/paper/2608.02713/) (2026)
- [LIBERO-MAX: Do Robot Policies Adapt When the World Changes?](https://mlsanity.com/paper/2609.36518/) (2026)
- [DeepJEPA: Scaling World Models from Within](https://mlsanity.com/paper/2610.00368/) (2026)
- [VITAL: From Visual Motion to Precise Action](https://mlsanity.com/paper/2610.20604/) (2026)

## Abstract (arXiv)

Today's driving world models can generate remarkably realistic dash-cam videos, yet no single model excels universally. Some generate photorealistic textures but violate basic physics; others maintain geometric consistency but fail when subjected to closed-loop planning. This disconnect exposes a critical gap: the field evaluates how real generated worlds appear, but rarely whether they behave realistically. We introduce WorldLens, a unified benchmark that measures world-model fidelity across the full spectrum, from pixel quality and 4D geometry to closed-loop driving and human perceptual alignment, through five complementary aspects and 24 standardized dimensions. Our evaluation of six representative models reveals that no existing approach dominates across all axes: texture-rich models violate geometry, geometry-aware models lack behavioral fidelity, and even the strongest performers achieve only 2-3 out of 10 on human realism ratings. To bridge algorithmic metrics with human perception, we further contribute WorldLens-26K, a 26,808-entry human-annotated preference dataset pairing numerical scores with textual rationales, and WorldLens-Agent, a vision-language evaluator distilled from these judgments that enables scalable, explainable auto-assessment. Together, the benchmark, dataset, and agent form a unified ecosystem for assessing generated worlds not merely by visual appeal, but by physical and behavioral fidelity.