AI Paper Atlas

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

TEX-Drive: Temporal Perception Meets Experience-Guided Mixture-of-Experts for End-to-End Autonomous Driving

Yitong Li, Xuchong Zhang, Fanjie Kong, Weihuang Chen, Haonan Hou, Hongbin Sun

ECCV 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. 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 key-frame temporal perception (KTP) (ablation)TEX-Drive · Bench2DriveDriving Score / Success Rate: +2.6 DS, +3.4 SRImproved
add experience-driven MoE (E-MoE) (ablation)TEX-Drive · Bench2DriveDriving Score / Success Rate: 3.1/3.8Improved
combine KTP with E-MoE instead of unfiltered history plus standard MoE (ablation)TEX-Drive · Bench2DriveDriving Score / Success Rate: +5.2 DS, +4.9 SRImproved
replace TP+MoE with KTP+E-MoE routing (ablation)TEX-Drive · Bench2DriveRouting entropy: 0.78 -> 0.49Improved
replace TP+MoE with KTP+E-MoE routing (ablation)TEX-Drive · Bench2DriveTemporal persistence: 1.9 -> 4.8Improved
replace TP+MoE with KTP+E-MoE routing (ablation)TEX-Drive · Bench2DriveUtilization entropy: 0.83 -> 0.61Mixed
increase number of activated experts K3 (ablation)TEX-Drive · Bench2DriveDriving ScoreHurt
increase number of key frames K2 (ablation)TEX-Drive · Bench2DriveDriving ScoreHurt
use key-frame temporal perception and E-MoE vs GEMINUSTEX-Drive · Bench2DriveDriving Score / Success Rate: +2.83, +2.89Improved
use key-frame temporal perception and E-MoE vs DriveAdapterTEX-Drive · Bench2Drive multi-abilityMean ability score: +3.01Improved

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