AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

Yupeng Zheng, Pengxuan Yang, Zebin Xing, Qichao Zhang, Yuhang Zheng, Yinfeng Gao, Pengfei Li, Teng Zhang, Zhongpu Xia, Peng Jia, XianPeng Lang, Dongbin Zhao

ICCV 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 60 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 driving intentions to latent world model (ablation)LAW-like WM · nuScenes open-loopavg L2 / collision: 0.61 -> 0.55 L2; 0.30 -> 0.25 collisionImproved
add depth spatial prior (ablation)WM + intentions · nuScenes open-loopavg L2 / collision: 0.55 -> 0.51 L2; 0.25 -> 0.29 collisionMixed
add semantic prior (ablation)WM + intentions + depth · nuScenes open-loopavg L2 / collision: 0.29 -> 0.16 collisionImproved
add depth and semantic priors without intentions (ablation)WM only · nuScenes open-loopavg L2 / collision: 0.61 -> 0.49 L2; 0.30 -> 0.26 collisionImproved
add intentions on top of priors and WM (ablation)depth+semantic WM · nuScenes open-loopavg L2 / collision: 0.49 -> 0.50 L2; 0.26 -> 0.16 collisionMixed
add world model to intentions with priors (ablation)depth+semantic+intentions · nuScenes open-loopavg L2 / collision: 0.61 -> 0.50 L2; 0.36 -> 0.16 collisionImproved
scale backbone ResNet-34 to ResNet-50 (ablation)World4Drive · nuScenes open-loopavg L2 / collision: 0.52 -> 0.50 L2; 0.25 -> 0.16 collisionImproved
scale backbone ResNet-50 to ResNet-101 (ablation)World4Drive · nuScenes open-loopavg L2 / collision: 0.50 -> 0.47 L2; 0.16 -> 0.14 collisionImproved
increase hidden dimension 128 to 256 (ablation)World4Drive · nuScenes open-loopavg L2 / collision: 0.55 -> 0.50 L2; 0.27 -> 0.16 collisionImproved
increase hidden dimension 256 to 384 (ablation)World4Drive · nuScenes open-loopavg L2 / collision: 0.50 -> 0.49 L2; 0.16 -> 0.10 collisionImproved
World4Drive vs LAW at nightWorld4Drive · nuScenes Nightavg L2 / collision: 0.67 -> 0.76 L2; 0.22 -> 0.08 collisionMixed
World4Drive vs LAW in rainWorld4Drive · nuScenes Rainyavg L2 / collision: 0.54 -> 0.49 L2; 0.16 -> 0.05 collisionImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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