AI Paper Atlas

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

Trajectory Evaluation via Rollout-Free World Model for End-to-end Autonomous Driving

Junzhe Wang, Jinqing Zhang, Qingjie LIU

NeurIPS 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a rollout-free world-model trajectory evaluator for end-to-end autonomous driving that scores candidate trajectories without explicitly predicting candidate-conditioned future states.

Problem

Model-based candidate trajectory evaluators in end-to-end driving make scoring future-aware by explicitly predicting candidate-conditioned future states (rollout), which incurs high inference cost and accumulates prediction errors.

Approach

Replaces explicit candidate-conditioned rollout with a rollout-free world model that makes trajectory scoring future-aware implicitly, avoiding the cost and error accumulation of predicting future states for each candidate.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add world model branch without future supervision (ablation)RFWorld · NAVSIM-v1PDMS: 88.9 -> 88.4Hurt
add explicit future supervision (no world model transformer) (ablation)RFWorld · NAVSIM-v1PDMS: 88.9 -> 89.4Improved
add world model on top of future supervision (full RFWorld) (ablation)RFWorld · NAVSIM-v1PDMS: 89.4 -> 90.5Improved
supervise more future timestamps (0 to 8) (ablation)RFWorld · NAVSIM-v1PDMS: 88.4 -> 90.5Improved
increase number of test-time candidate anchors from 256 to 1024 (ablation)RFWorld · NAVSIM-v1PDMS: 89.6 -> 90.5Improved
increase test-time candidate anchors from 256 to 1024 (ablation)WoTE · NAVSIM-v1PDMS: 88.3 -> 88.7Improved
replace per-candidate rollout with shared-memory sparse readoutRFWorld vs WoTE · NAVSIM-v1inference latency (ms): 49.2 -> 37.5Improved
replace per-candidate rollout with shared-memory readoutRFWorld vs WoTE · NAVSIM-v1training GPU memory (GB): 33.9 -> 8.7Improved
use rollout-free world model scoring instead of WoTERFWorld vs WoTE · NAVSIM-v1PDMS: 88.3 -> 90.5Improved
evaluate in closed loop on Bench2DriveRFWorld vs TCP · Bench2DriveDriving Score: 59.90 -> 62.38Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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