# The DAWN of World-Action Interactive Models arXiv: https://arxiv.org/abs/2605.11550 ยท HTML: https://mlsanity.com/paper/2605.11550/ ## Key facts - Cited by 8 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 31 of its 65 references that are in the map. - First posted on arXiv 12 May 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 31) - [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025) - [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023) - [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) - [VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning](https://mlsanity.com/paper/2402.13243/) (2024) - [Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation](https://mlsanity.com/paper/2406.06978/) (2024) - [Enhancing End-to-End Autonomous Driving with Latent World Model](https://mlsanity.com/paper/2406.08481/) (2024) - [ADriver-I: A General World Model for Autonomous Driving](https://mlsanity.com/paper/2311.13549/) (2023) - [Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation](https://mlsanity.com/paper/2503.12820/) (2025) - [A Comprehensive Survey on World Models for Embodied AI](https://mlsanity.com/paper/2510.16732/) (2025) - [A Survey of World Models for Autonomous Driving](https://mlsanity.com/paper/2501.11260/) (2025) - [iPad: Iterative Proposal-centric End-to-End Autonomous Driving](https://mlsanity.com/paper/2505.15111/) (2025) - [Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory](https://mlsanity.com/paper/2602.02393/) (2026) - [DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving](https://mlsanity.com/paper/2509.17940/) (2025) - [SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving](https://mlsanity.com/paper/2601.05640/) (2026) - [VaViM and VaVAM: Autonomous Driving through Video Generative Modeling](https://mlsanity.com/paper/2502.15672/) (2025) - [From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction](https://mlsanity.com/paper/2510.19654/) (2025) - [Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving](https://mlsanity.com/paper/2603.24581/) (2026) - [Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving](https://mlsanity.com/paper/2601.22032/) (2026) - [ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving](https://mlsanity.com/paper/2508.11428/) (2025) - [UniFuture: A 4D Driving World Model for Future Generation and Perception](https://mlsanity.com/paper/2503.13587/) (2025) - [Future-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution](https://mlsanity.com/paper/2510.11092/) (2025) - [UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving](https://mlsanity.com/paper/2604.02190/) (2026) - [WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving](https://mlsanity.com/paper/2512.06112/) (2025) - [WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG](https://mlsanity.com/paper/2603.23497/) (2026) - [Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving](https://mlsanity.com/paper/2603.27287/) (2026) - [Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving](https://mlsanity.com/paper/2511.19221/) (2025) - [CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention](https://mlsanity.com/paper/2603.18561/) (2026) - [VLA-R: Vision-Language Action Retrieval toward Open-World End-to-End Autonomous Driving](https://mlsanity.com/paper/2511.12405/) (2025) ## Built on by (most cited first, 8 of 8) - [World Action Models: A Survey](https://mlsanity.com/paper/2606.20781/) (2026) - [RISE: Adaptive Imagination for World Action Models](https://mlsanity.com/paper/2608.20430/) (2026) - [Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous Driving](https://mlsanity.com/paper/2609.04070/) (2026) - [MM-Future: Multi-Mode Joint World-Action Modeling for Autonomous Driving](https://mlsanity.com/paper/2609.20377/) (2026) - [DroneWAM: Efficient World Action Model for Drone Visual Navigation](https://mlsanity.com/paper/2609.33148/) (2026) - [ReDrive: Shaping Representations with World Modeling for End-to-End Driving](https://mlsanity.com/paper/2609.33854/) (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) A plausible scene evolution depends on the maneuver being considered, while a good maneuver depends on how the scene may evolve. Existing World Action Models (WAMs) largely miss this reciprocity, treating world prediction and action generation as either isolated parallel branches or rigid predict-then-plan pipelines. We formalize this perspective as World-Action Interactive Models (WAIMs), and instantiate it in autonomous driving with DAWN (Denoising Actions and World iNteractive model), a simple yet strong latent generative baseline. DAWN operates in a compact semantic latent space and couples a World Predictor with a World-Conditioned Action Denoiser: the predicted world hypothesis conditions action denoising, while the denoised action hypothesis is fed back to update the world prediction, so that both are recursively refined during inference. Rather than eliminating test-time world evolution altogether or rolling out the full future in pixel space, DAWN performs a short explicit latent rollout that is sufficient to support long-horizon trajectory generation in complex interactive scenes. Experiments show that DAWN achieves strong planning performance and favorable safety-related results across multiple autonomous driving benchmarks. More broadly, our results suggest that interactive world-action generation is a principled path toward truly actionable world models.