AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

CausalDrive: Real-time Causal World Models for Autonomous Driving

Tianyi Yan, Huan Zheng, Dubing Chen, Meizhi Qu, Yingying Shen, Lijun Zhou, Mingfei Tu, Bing Wang, Guang Chen, Hangjun Ye, Haiyang Sun, Cheng-zhong Xu and 1 more

ECCV 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Data-driven traffic simulation · 7 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 Context-Forced DMD distillation to the AR teacher (CausalDrive+ to CausalDrive)CausalDrive · nuPlanFPS: 0.5 -> 12.4Improved
distill the AR teacher into a few-step student with Context-Forced DMDCausalDrive · nuPlanFVD: 113.6 -> 121.6Mixed
add sociology text prompt (Polite) to action conditioningCausalDrive vs Vista · SocioDrive-BenchYCR: 12.5% -> 82.0%Improved
add sociology prompt conditioning, lowering ghost collisionsCausalDrive vs Vista · SocioDrive-BenchFCR: 87.5% -> 18.0%Improved
replace log-replay with CausalDrive reactive simulationCausalDrive vs Log-Replay(GT) · SocioDrive-BenchFCR: 100.0% -> 18.0%Improved
use CausalDrive instead of DrivingSphere as closed-loop simulatorUniAD planner · Closed-loop PDM-ClosedPDMS: 0.7281 -> 0.7792Improved
use CausalDrive instead of DriveArena as closed-loop simulatorUniAD planner · Closed-loop PDM-ClosedPDMS: 0.6901 -> 0.7792Improved
RL post-train DiffusionDrive inside CausalDriveDiffusionDrive · NavsimPDMS: 88.1 -> 90.7Improved
RL post-train in CausalDrive versus DiffusionDrive-v2DiffusionDrive · NavsimPDMS: 90.3 -> 90.7Improved
use CausalDrive over Orbis for action followingCausalDrive · nuPlanADE precision: 0.39 -> 0.45Improved

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