AI Paper Atlas

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

LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving

Long Nguyen, Micha Fauth, Bernhard Jaeger, Daniel Dauner, Maximilian Igl, Andreas Geiger, Kashyap Chitta

CVPR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 13 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
train on state-aligned LEAD expert data instead of PDM-Lite (ablation)TFv5 · Longest6 v2Driving Score: 22.51 -> 34.05Improved
train on LEAD data (ablation)TFv5 · Bench2DriveDriving Score: 83.56 -> 84.94Improved
remove GRU, feed target point as token (ablation)TFv6 · Longest6 v2Driving Score: 34.05 -> 40.70Improved
remove GRU, feed target point as token (ablation)TFv6 · Bench2DriveDriving Score: 84.94 -> 87.26Improved
use three target points instead of one (ablation)TFv6 · Longest6 v2Driving Score: 40.70 -> 42.13Improved
use three target points instead of one (ablation)TFv6 · Bench2DriveDriving Score: 87.26 -> 89.29Improved
add LiDAR and radar to camera-only input (ablation)TFv6 ResNet-34 · Longest6 v2Driving Score: 43 -> 54Improved
swap ResNet-34 for RegNetY-032 backbone (ablation)TFv6 · Bench2DriveDriving Score: 94.7 -> 95.2No clear effect
pre-train with LEAD perception dataLTFv6 · NAVSIM v1/v2, WOD-E2EPDMS/EPDMS/RFS: 85.4 -> 86.4; 28.3 -> 31.4; 7.51 -> 7.76Improved
reduce intent asymmetry (remove GRU, multi-target)TFv6 · CARLA infractionsroute deviationHurt

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