AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving

Lingjun Zhang, Changjie Wu, Linzhe Shi, Jiangyang Li, Jiaxin Liu, Lei Yang, Hang Zhang, Mu Xu, Hong Wang

ICML 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 0 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 DINOv3 latent-feature world modeling instead of VAE reconstruction (ablation)DeepSight · Dev 10 routes, one frameDriving Score: 27.75 -> 74.79Improved
increase VAE world model from one to five frames (ablation)VAE world model · Dev 10 routesDriving Score: 27.75 -> 14.66Hurt
increase DINOv3 world model from one to five frames (ablation)DeepSight · Dev 10 routesDriving Score: 74.79 -> 86.57Improved
use BEV view instead of front view (ablation)DeepSight · Dev 10 routesDriving Score: 77.77 -> 86.57Improved
add world modeling (no adaptive CoT) (ablation)DeepSight · Bench2Drive 220 routesDriving Score: 58.16 -> 84.52Improved
add world modeling (no adaptive CoT) (ablation)DeepSight · Bench2Drive 220 routesSuccess Rate: 28.18 -> 65.91Improved
add adaptive CoT to model without world model (ablation)DeepSight · Bench2Drive 220 routesSuccess Rate: 28.18 -> 42.27Improved
add adaptive CoT to model without world model (ablation)DeepSight · Bench2Drive 220 routesDriving Score: 58.16 -> 69.87Improved
add adaptive CoT on top of world model (ablation)DeepSight · Bench2Drive 220 routesDriving Score: 84.52 -> 86.23Improved
add adaptive CoT on top of world model (ablation)DeepSight · Bench2Drive 220 routesSuccess Rate: 65.91 -> 71.36Improved
raise lambda_world from 1.0 to 2.0 (ablation)DeepSight · Dev 10 routesDriving Score: 86.57 -> 79.82Hurt
lower lambda_world from 1.0 to 0.5 (ablation)DeepSight · Dev 10 routesDriving Score: 86.57 -> 78.93Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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