wjl2244/Awesome-End-to-End-Autonomous-Driving

Awesome paper list with code about End to End Autonomous Driving in NAVSIM Benchmark

100

16 commits

updated Jun 18, 2026

See the code

README

Awesome End-to-end Autonomous Driving Papers

📕Paper List: End-to-End Autonomous Driving on NavSim

🚗This repository maintains a curated list of academic papers that implement and evaluate end-to-end autonomous driving models on the NavSim simulation benchmark. The goal is to track progress and compare methods within this benchmark setting.

If you find this repository useful, please giving this list a star ⭐. Feel free to share it with others!

📌 Table of Contents

NavSimv2 navtest

MethodPDMSVenueDateCodeTitle
BeyondDrive90.5ECCV 202619/05/2026starGithubBeyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
CLOVER90.4arXiv15/05/2026starGithubCLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
LTFv790.1ECCV 202619/05/2026star GithubBeyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
WAM-Diff89.7arXiv11/12/2025starGithubWAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving
DVGT-289.7CVPR202601/02/2026starGithubDVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale
MeanFuser89.5CVPR202613/06/2025star GithubMeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
Vega89.4arXiv25/03/2026star GithubVega: Learning to Drive with Natural Language Instructions
DiffusionDrive88.1CVPR202515/11/2024star GithubDiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
Drive-JEPA87.7arXiv05/01/2026star GithubDrive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving
DriveWorld-VLA86.8ICML202606/02/2026starGithubDriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous Driving
Senna-286.6arXiv11/03/2026starGithubSenna-2: Aligning VLM and End-to-End Driving Policy for Consistent Decision Making and Planning
ZTRS86.2arXiv14/10/2025starGithubZTRS: Zero-Imitation End-to-end Autonomous Driving with Trajectory Scoring
DriveVLA-W086.1ICLR202612/10/2025star GithubDriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
SimScale85.9CVPR2026 oral20/09/2025starGithubLearning to Drive via Real-World Simulation at Scale
DiffusionDriveV285.5arXiv07/12/2025star GithubDiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
Curious-VLA85.3CVPR2026 Findings05/03/2025star GithubDevil is in Narrow Policy: Unleashing Exploration in Driving VLA Models
WAM-Flow84.7CVPR202606/12/2025starGithubWAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving
PRIX84.2RA-L202617/07/2025starGithubPRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving
DriveSuprim83.1AAAI202610/03/2025star GithubDriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning
Latent-WAM89.3arXiv24/03/2026-Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving
ExploreVLA88.8arXiv02/04/2026coming soonExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
HAD88.6arXiv03/04/2026-HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving
PaIR-Drive87.9CVPR2026 findings17/11/2025coming soonFine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving
DiffRefiner87.9AAAI202617/11/2025coming soonDiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving
ELF-VLA87.1arXiv01/03/2026-Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures
LaST-VLA87.1arXiv01/03/2026coming soonLaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
CdDrive86.4arXiv03/02/2026404A Unified Candidate Set with Scene-Adaptive Refinement via Diffusion for End-to-End Autonomous Driving
SpanVLA86.4arXiv19/04/2026coming soonSpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model
The Constant Eye45.8arXiv12/02/2026-The Constant Eye: Benchmarking and Bridging Appearance Robustness in Autonomous Driving
AnchDrive85.5arXiv--AnchDrive: Bootstrapping Diffusion Policies with Hybrid Trajectory Anchors for End-to-End Driving
Map-World85.0arXiv17/11/2025coming soonMap-World: Masked Action planning and Path-Integral World Model for Autonomous Driving
SUPER-AD84.3arXiv22/11/2025-SUPER-AD: Semantic Uncertainty-aware Planning for End-to-End Robust Autonomous Driving
MindDrive84.2arXiv04/12/2025-MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving

MethodPDMSVenueDateCodeTitle
DrivoR54.6CVPR202605/01/2026star GithubDriving on Registers
CLOVER48.3arXiv15/05/2026starGithubCLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
SimScale48.0CVPR2026 oral20/09/2025starGithubLearning to Drive via Real-World Simulation at Scale
ZTRS45.5arXiv14/10/2025starGithubZTRS: Zero-Imitation End-to-end Autonomous Driving with Trajectory Scoring
GTRS42.1arXiv06/06/2025starGithubGeneralized Trajectory Scoring for End-to-end Multi-modal Planning
RAP36.9ICLR202604/10/2026starGithubRAP: 3D Rasterization Augmented End-to-End Planning
Mimir34.6RA-L202507/12/2025star GithubMimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving
LEAD31.4CVPR202620/12/2025starGithubLEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
MindDrive30.5arXiv04/12/2025-MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving
LTFv628.3CVPR202620/12/2025starGithubLEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
The Constant Eye46.7arXiv12/02/2026-The Constant Eye: Benchmarking and Bridging Appearance Robustness in Autonomous Driving
SpanVLA40.1arXiv19/04/2026coming soonSpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model
EponaV236.1arXiv14/05/2026coming soonEponaV2: Driving World Model with Comprehensive Future Reasoning
UniUncer28.7arXiv07/03/2026-UniUncer: Unified Dynamic–Static Uncertainty for End-to-End Driving

MethodPDMSVenueDateCodeTitle
CLOVER94.5arXiv15/05/2026starGithubCLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
RAP93.8ICLR202604/10/2025starGithubRAP: 3D Rasterization Augmented End-to-End Planning
DriveSuprim93.5AAAI202610/03/2025star GithubDriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning
Drive-JEPA93.3arXiv05/01/2026star GithubDrive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving
DrivoR93.1CVPR202605/01/2026star GithubDriving on Registers
SparseDriveV292.0arXiv29/03/2026star GithubSparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving
iPad91.7arXiv15/05/2025star GithubiPad: Iterative Proposal-centric End-to-End Autonomous Driving
DriveWorld-VLA86.8ICML202606/02/2026starGithubDriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous Driving
DiffusionDriveV291.2arXiv07/12/2025star GithubDiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
SGDrive91.1CVPR202605/01/2026star GithubSGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving
WAM-Diff91.0arXivscorestarGithubWAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving
ReCogDrive90.8ICLR202608/06/2025star GithubReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
SeerDrive90.7NeurIPS202511/10/2025star GithubFuture-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution
GoalFlow90.3CVPR202505/03/2025star GithubGoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving
WAM-Flow90.3CVPR202606/12/2025starGithubWAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving
Curious-VLA90.3CVPR2026 Findings05/03/2025star GithubDevil is in Narrow Policy: Unleashing Exploration in Driving VLA Models
DVGT-290.3CVPR202601/04/2026starGithubDVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale
BeyondDrive90.3arXiv19/05/2026starGithubBeyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
DriveVLA-W090.2ICLR202612/10/2025star GithubDriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
VeteranAD90.2AAAI202611/08/2025star GithubPerception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving
DeMo++89.9arXiv17/07/2025star GithubDeMo++: Motion Decoupling for Autonomous Driving
LTFv789.7arXiv19/05/2026star GithubBeyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
Uni-World VLA89.4arXiv27/03/2026star GithubUni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving
Mimir89.3RA-L202507/12/2025star GithubMimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving
AutoVLA89.1NeurIPS202513/06/2025star GithubAutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
DriveLaW89.1CVPR202623/12/2025star GithubDriveLaW:Unifying Planning and Video Generation in a Latent Driving World
MeanFuser89.0CVPR202613/06/2025star GithubMeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
VGGDrive88.8CVPR202613/06/2025star GithubVGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving
Hydra-NeXt88.6ICCV202512/03/2025star GithubHydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training
WoTE88.3ICCV202501/04/2025star GithubEnd-to-End Driving with Online Trajectory Evaluation via BEV World Model
DIVER88.3arXiv04/07/2025star GithubDIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving
DiffusionDrive88.1CVPR202515/11/2024star GithubDiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
PWM88.1NeurIPS202519/10/2024star GithubFrom Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction
BridgeDrive88.0ICLR202623/09/2024star GithubBridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving
Vega87.9arXiv25/03/20264star GithubVega: Learning to Drive with Natural Language Instructions
PRIX87.8RA-L202617/07/2025starGithubPRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving
ImagiDrive87.4ICRA202611/08/2025starGithubImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving
DistillDrive86.2ICCV202505/08/2025starGithubDistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model
LEAD86.4CVPR202620/12/2025starGithubLEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
Epona86.2ICCV202524/06/2025starGithubEpona: Autoregressive Diffusion World Model for Autonomous Driving
LTFv685.4CVPR202620/12/2025starGithubLEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
World4Drive85.1ICCV202501/07/2025starGithubWorld4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model
FSDrive85.1ICCV202517/05/2025starGithubFutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving
LAW84.6ICLR202508/06/2024starGithubEnhancing End-to-End Autonomous Driving with Latent World Model
OneDrive86.8arXiv17/04/2026starGithubOneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models
UniVLA81.7ICLR202619/06/2025starGithubUnified Vision-Language-Action Model
EvaDrive94.9arXiv09/08/2025-EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving
TransDiffuser94.9arXiv09/05/2025-TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous Driving
DiffE2E92.7NeurIPS202519/05/2025coming soonDiffE2E: Rethinking End-to-End Driving with a Hybrid Action Diffusion and Supervised Policy
NaviHydra92.7arXiv10/12/2025-NaviHydra: Controllable Navigation-guided End-to-end Autonomous Driving with Hydra-distillation
Centaur92.6arXiv11/03/2025-Centaur: Robust End-to-End Autonomous Driving with Test-Time Training
HiPro-AD92.6---HiPro-AD: Sparse Trajectory Transformer for End-to-End Autonomous Driving with Hybrid Spatiotemporal Attention
LatentVLA92.4arXiv05/01/2026-LatentVLA: Efficient Vision-Language Models for Autonomous Driving via Latent Action Prediction
AD-R191.9arXiv20/11/2025-AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models
DriveFine91.8arXiv14/02/2025-DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving
DynVLA91.7arXiv11/03/2026-DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving
R2SE91.6TPAMI202609/06/2025-Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving
SafeDrive91.6CVPR202618/02/2026coming soonSafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse World
LaST-VLA91.3arXiv01/03/2026coming soonLaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
RaWMPC91.3arXiv23/02/2026-Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving
PaIR-Drive91.2CVPR2026 findings17/11/2025coming soonFine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving
ReflectDrive91.1arXiv20/09/2025-Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving
ReflectDrive-291.0arXiv04/05/2026-ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
Hydra-MDP++91.0arXiv12/03/2025-Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation
ELF-VLA91.0arXiv01/03/2026-Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures
DriveVA90.9arXiv03/03/2026-DriveVA: Video Action Models are Zero-Shot Drivers
LADY90.9arXiv15/12/2025-LADY: Linear Attention for Autonomous Driving Efficiency without Transformers
DiffRefiner90.7AAAI202617/11/2025coming soonDiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving
FutureX90.6arXiv11/12/2025coming soonFutureX: Enhance End-to-End Autonomous Driving via Latent Chain-of-Thought World Model
UniDWM90.6arXiv01/02/2026404UniDWM: Towards a Unified Driving World Model via Multifaceted Representation Learning
ResAD90.6arXiv08/10/2025coming soonResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving
ExploreVLA90.4arXiv02/04/2026coming soonExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
EponaV236.1arXiv-coming soonEponaV2: Driving World Model with Comprehensive Future Reasoning
SpanVLA90.3arXiv19/04/2026coming soonSpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model
AdaThinkDrive90.3CVPR202513/09/2025-AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving
HAD90.2arXiv03/04/2026-HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving
FeaXDrive90.0NeurIPS202512/04/2026-FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving
DriveDPO90.0NeurIPS202517/09/2025-DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving
-89.8arXiv20/09/2025-Autoregressive End-to-End Planning with Time-Invariant Spatial Alignment and Multi-Objective Policy Refinement
CdDrive89.2arXiv03/02/2026404A Unified Candidate Set with Scene-Adaptive Refinement via Diffusion for End-to-End Autonomous Driving
MindDrive88.9arXiv04/12/2025-MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving
GMF-Drive88.9arXiv06/08/2025-GMF-Drive: Gated Mamba Fusion with Spatial-Aware BEV Representation for End-to-End Autonomous Driving
Map-World88.8arXiv20/11/2025-Map-World: Masked Action planning and Path-Integral World Model for Autonomous Driving
READ88.8-13/09/2025-READ: End-to-End Autonomous Driving Made Safer with Efficient Reinforcement Learning
DynFlowDrive88.7-19/03/2026coming soonDynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving
DreamerAD88.7-24/03/2026-DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
TrajDiff88.5arXiv01/12/2025coming soonTrajDiff: End-to-end Autonomous Driving without Perception Annotation
WorldRFT87.8AAAI202619/12/2025coming soonWorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving
SUPER-AD87.7arXiv22/11/2025-SUPER-AD: Semantic Uncertainty-aware Planning for End-to-End Robust Autonomous Driving
TrajHF87.6arXiv10/03/2025-Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback
CausalVAD87.2arXiv18/03/2026-CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention
DAP87.2arXiv13/11/2025-DAP: A Discrete-token Autoregressive Planner for Autonomous Driving
ARTEMIS87.0arXiv19/04/2025coming soonARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Driving
ProDrive86.6arXiv25/04/2026-ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution
NoRD85.6arXiv21/02/2026-NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning
LFG85.2arXiv22/02/2026-Learning to Drive is a Free Gift: Large-Scale Label-Free Autonomy Pretraining from Unposed In-The-Wild Videos
DriveX84.5ICCV202519/05/2025-DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving
DISK83.6arXiv01/02/2026-DISK: Dynamic Inference SKipping for World Models
DrivingGPT82.4ICCV202518/12/2024404DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers

wjl2244/Awesome-End-to-End-Autonomous-Driving

Awesome paper list with code about End to End Autonomous Driving in NAVSIM Benchmark

100

16 commits

updated Jun 18, 2026

See the code

README

Awesome End-to-end Autonomous Driving Papers

📕Paper List: End-to-End Autonomous Driving on NavSim

🚗This repository maintains a curated list of academic papers that implement and evaluate end-to-end autonomous driving models on the NavSim simulation benchmark. The goal is to track progress and compare methods within this benchmark setting.

If you find this repository useful, please giving this list a star ⭐. Feel free to share it with others!

📌 Table of Contents

NavSimv2 navtest

MethodPDMSVenueDateCodeTitle
BeyondDrive90.5ECCV 202619/05/2026starGithubBeyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
CLOVER90.4arXiv15/05/2026starGithubCLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
LTFv790.1ECCV 202619/05/2026star GithubBeyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
WAM-Diff89.7arXiv11/12/2025starGithubWAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving
DVGT-289.7CVPR202601/02/2026starGithubDVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale
MeanFuser89.5CVPR202613/06/2025star GithubMeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
Vega89.4arXiv25/03/2026star GithubVega: Learning to Drive with Natural Language Instructions
DiffusionDrive88.1CVPR202515/11/2024star GithubDiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
Drive-JEPA87.7arXiv05/01/2026star GithubDrive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving
DriveWorld-VLA86.8ICML202606/02/2026starGithubDriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous Driving
Senna-286.6arXiv11/03/2026starGithubSenna-2: Aligning VLM and End-to-End Driving Policy for Consistent Decision Making and Planning
ZTRS86.2arXiv14/10/2025starGithubZTRS: Zero-Imitation End-to-end Autonomous Driving with Trajectory Scoring
DriveVLA-W086.1ICLR202612/10/2025star GithubDriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
SimScale85.9CVPR2026 oral20/09/2025starGithubLearning to Drive via Real-World Simulation at Scale
DiffusionDriveV285.5arXiv07/12/2025star GithubDiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
Curious-VLA85.3CVPR2026 Findings05/03/2025star GithubDevil is in Narrow Policy: Unleashing Exploration in Driving VLA Models
WAM-Flow84.7CVPR202606/12/2025starGithubWAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving
PRIX84.2RA-L202617/07/2025starGithubPRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving
DriveSuprim83.1AAAI202610/03/2025star GithubDriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning
Latent-WAM89.3arXiv24/03/2026-Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving
ExploreVLA88.8arXiv02/04/2026coming soonExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
HAD88.6arXiv03/04/2026-HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving
PaIR-Drive87.9CVPR2026 findings17/11/2025coming soonFine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving
DiffRefiner87.9AAAI202617/11/2025coming soonDiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving
ELF-VLA87.1arXiv01/03/2026-Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures
LaST-VLA87.1arXiv01/03/2026coming soonLaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
CdDrive86.4arXiv03/02/2026404A Unified Candidate Set with Scene-Adaptive Refinement via Diffusion for End-to-End Autonomous Driving
SpanVLA86.4arXiv19/04/2026coming soonSpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model
The Constant Eye45.8arXiv12/02/2026-The Constant Eye: Benchmarking and Bridging Appearance Robustness in Autonomous Driving
AnchDrive85.5arXiv--AnchDrive: Bootstrapping Diffusion Policies with Hybrid Trajectory Anchors for End-to-End Driving
Map-World85.0arXiv17/11/2025coming soonMap-World: Masked Action planning and Path-Integral World Model for Autonomous Driving
SUPER-AD84.3arXiv22/11/2025-SUPER-AD: Semantic Uncertainty-aware Planning for End-to-End Robust Autonomous Driving
MindDrive84.2arXiv04/12/2025-MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving

MethodPDMSVenueDateCodeTitle
DrivoR54.6CVPR202605/01/2026star GithubDriving on Registers
CLOVER48.3arXiv15/05/2026starGithubCLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
SimScale48.0CVPR2026 oral20/09/2025starGithubLearning to Drive via Real-World Simulation at Scale
ZTRS45.5arXiv14/10/2025starGithubZTRS: Zero-Imitation End-to-end Autonomous Driving with Trajectory Scoring
GTRS42.1arXiv06/06/2025starGithubGeneralized Trajectory Scoring for End-to-end Multi-modal Planning
RAP36.9ICLR202604/10/2026starGithubRAP: 3D Rasterization Augmented End-to-End Planning
Mimir34.6RA-L202507/12/2025star GithubMimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving
LEAD31.4CVPR202620/12/2025starGithubLEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
MindDrive30.5arXiv04/12/2025-MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving
LTFv628.3CVPR202620/12/2025starGithubLEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
The Constant Eye46.7arXiv12/02/2026-The Constant Eye: Benchmarking and Bridging Appearance Robustness in Autonomous Driving
SpanVLA40.1arXiv19/04/2026coming soonSpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model
EponaV236.1arXiv14/05/2026coming soonEponaV2: Driving World Model with Comprehensive Future Reasoning
UniUncer28.7arXiv07/03/2026-UniUncer: Unified Dynamic–Static Uncertainty for End-to-End Driving

MethodPDMSVenueDateCodeTitle
CLOVER94.5arXiv15/05/2026starGithubCLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
RAP93.8ICLR202604/10/2025starGithubRAP: 3D Rasterization Augmented End-to-End Planning
DriveSuprim93.5AAAI202610/03/2025star GithubDriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning
Drive-JEPA93.3arXiv05/01/2026star GithubDrive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving
DrivoR93.1CVPR202605/01/2026star GithubDriving on Registers
SparseDriveV292.0arXiv29/03/2026star GithubSparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving
iPad91.7arXiv15/05/2025star GithubiPad: Iterative Proposal-centric End-to-End Autonomous Driving
DriveWorld-VLA86.8ICML202606/02/2026starGithubDriveWorld-VLA: Unified Latent-Space World Modeling with Vision–Language–Action for Autonomous Driving
DiffusionDriveV291.2arXiv07/12/2025star GithubDiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving
SGDrive91.1CVPR202605/01/2026star GithubSGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving
WAM-Diff91.0arXivscorestarGithubWAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving
ReCogDrive90.8ICLR202608/06/2025star GithubReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
SeerDrive90.7NeurIPS202511/10/2025star GithubFuture-Aware End-to-End Driving: Bidirectional Modeling of Trajectory Planning and Scene Evolution
GoalFlow90.3CVPR202505/03/2025star GithubGoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving
WAM-Flow90.3CVPR202606/12/2025starGithubWAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving
Curious-VLA90.3CVPR2026 Findings05/03/2025star GithubDevil is in Narrow Policy: Unleashing Exploration in Driving VLA Models
DVGT-290.3CVPR202601/04/2026starGithubDVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale
BeyondDrive90.3arXiv19/05/2026starGithubBeyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
DriveVLA-W090.2ICLR202612/10/2025star GithubDriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
VeteranAD90.2AAAI202611/08/2025star GithubPerception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving
DeMo++89.9arXiv17/07/2025star GithubDeMo++: Motion Decoupling for Autonomous Driving
LTFv789.7arXiv19/05/2026star GithubBeyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
Uni-World VLA89.4arXiv27/03/2026star GithubUni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving
Mimir89.3RA-L202507/12/2025star GithubMimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving
AutoVLA89.1NeurIPS202513/06/2025star GithubAutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
DriveLaW89.1CVPR202623/12/2025star GithubDriveLaW:Unifying Planning and Video Generation in a Latent Driving World
MeanFuser89.0CVPR202613/06/2025star GithubMeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
VGGDrive88.8CVPR202613/06/2025star GithubVGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving
Hydra-NeXt88.6ICCV202512/03/2025star GithubHydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training
WoTE88.3ICCV202501/04/2025star GithubEnd-to-End Driving with Online Trajectory Evaluation via BEV World Model
DIVER88.3arXiv04/07/2025star GithubDIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving
DiffusionDrive88.1CVPR202515/11/2024star GithubDiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
PWM88.1NeurIPS202519/10/2024star GithubFrom Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction
BridgeDrive88.0ICLR202623/09/2024star GithubBridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving
Vega87.9arXiv25/03/20264star GithubVega: Learning to Drive with Natural Language Instructions
PRIX87.8RA-L202617/07/2025starGithubPRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving
ImagiDrive87.4ICRA202611/08/2025starGithubImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving
DistillDrive86.2ICCV202505/08/2025starGithubDistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model
LEAD86.4CVPR202620/12/2025starGithubLEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
Epona86.2ICCV202524/06/2025starGithubEpona: Autoregressive Diffusion World Model for Autonomous Driving
LTFv685.4CVPR202620/12/2025starGithubLEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving
World4Drive85.1ICCV202501/07/2025starGithubWorld4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model
FSDrive85.1ICCV202517/05/2025starGithubFutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving
LAW84.6ICLR202508/06/2024starGithubEnhancing End-to-End Autonomous Driving with Latent World Model
OneDrive86.8arXiv17/04/2026starGithubOneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models
UniVLA81.7ICLR202619/06/2025starGithubUnified Vision-Language-Action Model
EvaDrive94.9arXiv09/08/2025-EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving
TransDiffuser94.9arXiv09/05/2025-TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous Driving
DiffE2E92.7NeurIPS202519/05/2025coming soonDiffE2E: Rethinking End-to-End Driving with a Hybrid Action Diffusion and Supervised Policy
NaviHydra92.7arXiv10/12/2025-NaviHydra: Controllable Navigation-guided End-to-end Autonomous Driving with Hydra-distillation
Centaur92.6arXiv11/03/2025-Centaur: Robust End-to-End Autonomous Driving with Test-Time Training
HiPro-AD92.6---HiPro-AD: Sparse Trajectory Transformer for End-to-End Autonomous Driving with Hybrid Spatiotemporal Attention
LatentVLA92.4arXiv05/01/2026-LatentVLA: Efficient Vision-Language Models for Autonomous Driving via Latent Action Prediction
AD-R191.9arXiv20/11/2025-AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models
DriveFine91.8arXiv14/02/2025-DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving
DynVLA91.7arXiv11/03/2026-DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving
R2SE91.6TPAMI202609/06/2025-Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving
SafeDrive91.6CVPR202618/02/2026coming soonSafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse World
LaST-VLA91.3arXiv01/03/2026coming soonLaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
RaWMPC91.3arXiv23/02/2026-Risk-Aware World Model Predictive Control for Generalizable End-to-End Autonomous Driving
PaIR-Drive91.2CVPR2026 findings17/11/2025coming soonFine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving
ReflectDrive91.1arXiv20/09/2025-Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving
ReflectDrive-291.0arXiv04/05/2026-ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
Hydra-MDP++91.0arXiv12/03/2025-Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation
ELF-VLA91.0arXiv01/03/2026-Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures
DriveVA90.9arXiv03/03/2026-DriveVA: Video Action Models are Zero-Shot Drivers
LADY90.9arXiv15/12/2025-LADY: Linear Attention for Autonomous Driving Efficiency without Transformers
DiffRefiner90.7AAAI202617/11/2025coming soonDiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving
FutureX90.6arXiv11/12/2025coming soonFutureX: Enhance End-to-End Autonomous Driving via Latent Chain-of-Thought World Model
UniDWM90.6arXiv01/02/2026404UniDWM: Towards a Unified Driving World Model via Multifaceted Representation Learning
ResAD90.6arXiv08/10/2025coming soonResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving
ExploreVLA90.4arXiv02/04/2026coming soonExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
EponaV236.1arXiv-coming soonEponaV2: Driving World Model with Comprehensive Future Reasoning
SpanVLA90.3arXiv19/04/2026coming soonSpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model
AdaThinkDrive90.3CVPR202513/09/2025-AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving
HAD90.2arXiv03/04/2026-HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving
FeaXDrive90.0NeurIPS202512/04/2026-FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving
DriveDPO90.0NeurIPS202517/09/2025-DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving
-89.8arXiv20/09/2025-Autoregressive End-to-End Planning with Time-Invariant Spatial Alignment and Multi-Objective Policy Refinement
CdDrive89.2arXiv03/02/2026404A Unified Candidate Set with Scene-Adaptive Refinement via Diffusion for End-to-End Autonomous Driving
MindDrive88.9arXiv04/12/2025-MindDrive: An All-in-One Framework Bridging World Models and Vision-Language Model for End-to-End Autonomous Driving
GMF-Drive88.9arXiv06/08/2025-GMF-Drive: Gated Mamba Fusion with Spatial-Aware BEV Representation for End-to-End Autonomous Driving
Map-World88.8arXiv20/11/2025-Map-World: Masked Action planning and Path-Integral World Model for Autonomous Driving
READ88.8-13/09/2025-READ: End-to-End Autonomous Driving Made Safer with Efficient Reinforcement Learning
DynFlowDrive88.7-19/03/2026coming soonDynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving
DreamerAD88.7-24/03/2026-DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving
TrajDiff88.5arXiv01/12/2025coming soonTrajDiff: End-to-end Autonomous Driving without Perception Annotation
WorldRFT87.8AAAI202619/12/2025coming soonWorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving
SUPER-AD87.7arXiv22/11/2025-SUPER-AD: Semantic Uncertainty-aware Planning for End-to-End Robust Autonomous Driving
TrajHF87.6arXiv10/03/2025-Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback
CausalVAD87.2arXiv18/03/2026-CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention
DAP87.2arXiv13/11/2025-DAP: A Discrete-token Autoregressive Planner for Autonomous Driving
ARTEMIS87.0arXiv19/04/2025coming soonARTEMIS: Autoregressive End-to-End Trajectory Planning with Mixture of Experts for Autonomous Driving
ProDrive86.6arXiv25/04/2026-ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution
NoRD85.6arXiv21/02/2026-NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning
LFG85.2arXiv22/02/2026-Learning to Drive is a Free Gift: Large-Scale Label-Free Autonomy Pretraining from Unposed In-The-Wild Videos
DriveX84.5ICCV202519/05/2025-DriveX: Omni Scene Modeling for Learning Generalizable World Knowledge in Autonomous Driving
DISK83.6arXiv01/02/2026-DISK: Dynamic Inference SKipping for World Models
DrivingGPT82.4ICCV202518/12/2024404DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers