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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add key-frame temporal perception (KTP) (ablation) | TEX-Drive · Bench2Drive | Driving Score / Success Rate: +2.6 DS, +3.4 SR | Improved |
| add experience-driven MoE (E-MoE) (ablation) | TEX-Drive · Bench2Drive | Driving Score / Success Rate: 3.1/3.8 | Improved |
| combine KTP with E-MoE instead of unfiltered history plus standard MoE (ablation) | TEX-Drive · Bench2Drive | Driving Score / Success Rate: +5.2 DS, +4.9 SR | Improved |
| replace TP+MoE with KTP+E-MoE routing (ablation) | TEX-Drive · Bench2Drive | Routing entropy: 0.78 -> 0.49 | Improved |
| replace TP+MoE with KTP+E-MoE routing (ablation) | TEX-Drive · Bench2Drive | Temporal persistence: 1.9 -> 4.8 | Improved |
| replace TP+MoE with KTP+E-MoE routing (ablation) | TEX-Drive · Bench2Drive | Utilization entropy: 0.83 -> 0.61 | Mixed |
| increase number of activated experts K3 (ablation) | TEX-Drive · Bench2Drive | Driving Score | Hurt |
| increase number of key frames K2 (ablation) | TEX-Drive · Bench2Drive | Driving Score | Hurt |
| use key-frame temporal perception and E-MoE vs GEMINUS | TEX-Drive · Bench2Drive | Driving Score / Success Rate: +2.83, +2.89 | Improved |
| use key-frame temporal perception and E-MoE vs DriveAdapter | TEX-Drive · Bench2Drive multi-ability | Mean ability score: +3.01 | Improved |
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.
- DriveAdapter — DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving (ICCV 2023) · better on 3 of 3 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
- Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.88)
- SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving (CVPR 2026 · similarity 0.88)
- $AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-Tuning (ICLR 2026 · similarity 0.88)
- DriveTransformer: Unified Transformer for Scalable End-to-End Autonomous Driving (ICLR 2025 · similarity 0.87)
- DriveSpatial: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving (NeurIPS 2026 · similarity 0.87)
- Embodied Cognition Augmented End2End Autonomous Driving (NeurIPS 2025 · similarity 0.87)
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.
