6 papers
BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation
Jiaqi Wang, Zhuo Zhang, Haining Guan +15
Modern driving action models are increasingly improved in a self-improvement loop, where a learned world simulator imagines future observations and the resulting data is fed back t…
WA-JEPA: Rethinking the Video JEPA Paradigm for World-Action Modeling in Autonomous Driving
Xinlin Wang, Yujiao Xiang, Yuheng Zhou +11
Video Joint Embedding Predictive Architecture (V-JEPA) learns powerful spatiotemporal representations from video through self-supervised latent feature prediction. However, V-JEPA…
ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
Xiyang Wang, Xinlin Wang, Tingguang Zhou +7
Current end-to-end autonomous driving systems are fundamentally limited by a mismatch between temporal causal reasoning and global trajectory consistency. Autoregressive (AR) model…
CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
Minqing Huang, Yujiao Xiang, Zihan Liang +7
Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving. However, existing reasoning mechanisms still struggle to provide plannin…
Bridging Scene Generation and Planning: Driving with World Model via Unifying Vision and Motion Representation
Xingtai Gui, Meijie Zhang, Tianyi Yan +5
End-to-end autonomous driving aims to generate safe and plausible planning policies from raw sensor input. Driving world models have shown great potential in learning rich represen…
TrajDiff: End-to-end Autonomous Driving without Perception Annotation
Xingtai Gui, Jianbo Zhao, Wencheng Han +5
End-to-end autonomous driving systems directly generate driving policies from raw sensor inputs. While these systems can extract effective environmental features for planning, rely…