Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Epona: Autoregressive Diffusion World Model for Autonomous Driving

About

Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-based world models struggle with flexible-length, long-horizon predictions and integrating trajectory planning. This is because conventional video diffusion models rely on global joint distribution modeling of fixed-length frame sequences rather than sequentially constructing localized distributions at each timestep. In this work, we propose Epona, an autoregressive diffusion world model that enables localized spatiotemporal distribution modeling through two key innovations: 1) Decoupled spatiotemporal factorization that separates temporal dynamics modeling from fine-grained future world generation, and 2) Modular trajectory and video prediction that seamlessly integrate motion planning with visual modeling in an end-to-end framework. Our architecture enables high-resolution, long-duration generation while introducing a novel chain-of-forward training strategy to address error accumulation in autoregressive loops. Experimental results demonstrate state-of-the-art performance with 7.4\% FVD improvement and minutes longer prediction duration compared to prior works. The learned world model further serves as a real-time motion planner, outperforming strong end-to-end planners on NAVSIM benchmarks. Code will be publicly available at \href{https://github.com/Kevin-thu/Epona/}{https://github.com/Kevin-thu/Epona/}.

Kaiwen Zhang, Zhenyu Tang, Xiaotao Hu, Xingang Pan, Xiaoyang Guo, Yuan Liu, Jingwei Huang, Li Yuan, Qian Zhang, Xiao-Xiao Long, Xun Cao, Wei Yin• 2025

Related benchmarks

TaskDatasetResultRank
Autonomous DrivingNAVSIM v1 (test)
NC97.9
113
PlanningnuScenes (val)
Collision Rate (Avg)36
80
Open-loop planningnuScenes v1.0 (val)
L2 (1s)0.61
71
Autonomous Driving PlanningNAVSIM (navtest)
NC97.9
68
Autonomous Driving PlanningNAVSIM v1 (test)
NC97.9
59
Autonomous DrivingNAVSIM (test)
PDMS86.2
48
Video GenerationnuScenes (val)
FVD82.8
48
PlanningNAVSIM (test)
PDMS86.2
44
Closed-loop Autonomous Driving PlanningNAVSIM v1 (test)
NC97.9
36
End-to-end PlanningnuScenes
L2 Error (3s)1.98
34
Showing 10 of 22 rows

Other info

Follow for update