AI Paper Atlas

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

Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives

Junli Wang, HuaZhihua HuaZhihua, Xueyi Liu, Zebin Xing, Wei Zhang, Kun Ma, Guang Chen, Hangjun Ye, Long Chen, Pengxuan Yang

ECCV 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 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 BeyondDrive hard-negative repulsive loss to LTF* (ablation)LTF* · NAVSIM v1 navtestPDMS: 88.7 -> 89.7Improved
add BeyondDrive to DiffusionDriveDiffusionDrive · NAVSIM v1 navtestPDMS: 88.1 -> 89.2Improved
add BeyondDrive to MeanFuserMeanFuser · NAVSIM v1 navtestPDMS: 89.0 -> 90.3Improved
add BeyondDrive to WoTEWoTE · NAVSIM v1 navtestPDMS: 88.3 -> 89.2Improved
add BeyondDrive to DiffusionDrive on reactive benchmarkDiffusionDrive · NAVSIM v2 navtestEPDMS: 88.3 -> 88.9Improved
zero-shot transfer: LTFv7 vs LTF on HUGSIMLTFv7 · HUGSIM overallHD-Score: 24.8 -> 34.8Improved
hyperparameter tuning of LTF (cosine schedule with warmup, lower auxiliary weights) (ablation)LTF · NAVSIM v1 navtestPDMS: 83.8 -> 87.4Improved
add first-order-difference trajectory normalization (ablation)LTF with tuned hyperparameters · NAVSIM v1 navtestPDMS: 87.4 -> 88.7Improved
reduce CFG scale from 1.0 to 0.5 when sampling negatives (ablation)negative generator · valid negatives proportionProp_sample: 8.0% -> 78.8%Improved
enlarge sampling noise to 2.0 sigma (ablation)negative generator · NAVSIM v1 navtestPDMS: 89.1 -> 89.7; valid negatives 78.8% -> 96.4%Improved
increase RD loss weight from 0 to 5 (imitation weight 10) (ablation)LTFv7 · NAVSIM v1 navtestPDMS: 88.7 -> 89.7Improved
set RD loss weight equal to imitation weight (ablation)LTFv7 · NAVSIM v1 navtestPDMS: 89.7 -> 0.1Hurt

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