AI Paper Atlas

Research map / Video / Video generation

Epona: Autoregressive Diffusion World Model for Autonomous Driving

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

ICCV 2025 · Video › Video generation · approach: World-model video generation · 72 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add joint video prediction with shared latent to trajectory planning (ablation)Epona · NAVSIM testPDMS: 78.1 -> 86.2Improved
add temporal-aware DCAE decoder (ablation)Epona · NuPlan testFVD40: 100.11 -> 74.88Improved
add temporal-aware DCAE decoder (ablation)Epona · NuPlan testFVD10: 52.95 -> 50.77Improved
add chain-of-forward training (ablation)Epona · NuPlan testFID over long generationImproved
increase condition frames from 2 to 10 (ablation)Epona · NuPlan testFVD40: 103.70 -> 74.88Improved
increase condition frames from 5 to 10 (ablation)Epona · NuPlan testFVD25: 71.28 -> 61.46Improved
increase condition frames beyond 10 (ablation)Epona · NuPlan testcomputeHurt
autoregressive diffusion world model versus fixed-length video diffusionEpona vs Vista · NuScenes valFVD: 89.4 -> 82.8Improved
autoregressive diffusion world model versus fixed-length video diffusionEpona vs Vista · NuScenes valFID: 6.9 -> 7.5Hurt
planning from the world model without perception inputs versus end-to-end plannersEpona vs DRAMA · NAVSIM testPDMS: 85.5 -> 86.2Improved
continuous diffusion trajectories versus discrete tokensEpona vs DrivingGPT · NAVSIM testPDMS: 82.4 -> 86.2Improved
no extra supervision versus annotated supervision for planningEpona vs UniAD · NuScenes planningaverage L2 (m): 1.03 -> 1.25Hurt

Later papers that compared with this method

2 later accepted papers report Epona as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy