SV-WAM: An Efficient Surround-View World-Action Model for End-to-End Autonomous Driving
cs.CV, cs.RO
Submitted: 2026-09-03
Updated: 2026-11-02
Comments: 23 pages, 16 figures. Project page: https://jinyangwang427.github.io/SV-WAM/
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- GAIA-1: A Generative World Model for Autonomous Driving
- DriveVA: Video Action Models are Zero-Shot Drivers
- EponaV2: Driving World Model with Comprehensive Future Reasoning
- GigaWorld-Policy: An Efficient Action-Centered World--Action Model
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- Doe-1: Closed-Loop Autonomous Driving with Large World Model
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs