DriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for Autonomous Driving
cs.CV, cs.AI, cs.RO
Submitted: 2026-10-13
Updated: 2026-10-13
Comments: 17 pages, 4 figures
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Pseudo-Simulation for Autonomous Driving
- LTX-Video: Realtime Video Latent Diffusion
- DriveFuture: Future-Aware Latent World Models for Autonomous Driving
- GAIA-1: A Generative World Model for Autonomous Driving
- LoRA: Low-Rank Adaptation of Large Language Models
- CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
- EMMA: End-to-End Multimodal Model for Autonomous Driving
- SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving
- UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving
- Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models
- Flow Matching for Generative Modeling
- DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving
- UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation
- DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving
- DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
- Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving
- WA-JEPA: Rethinking the Video JEPA Paradigm for World-Action Modeling in Autonomous Driving
- ReWorld: Learning Better Representations for World Action Models
- EponaV2: Driving World Model with Comprehensive Future Reasoning
- BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models