| FPD-Drive: Future Policy Distillation for End-to-End Autonomous Driving | | 95.5 | FPD-Drive-Pro | 2026-10-09 |
| DriveZero: End-to-End Driving Beyond Human Demonstrations | ✓ Link | 95.3 | DriveZero-Scale | 2026-09-05 |
| Plug-and-Play Traffic Element Awareness for End-to-End Autonomous Driving | ✓ Link | 95.1 | DrivoR (+SimScale) + Ours | 2026-08-18 |
| Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving | | 95.1 | RRDrive | 2026-09-18 |
| EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving | | 94.9 | EvaDrive (Aggres.) | 2025-08-05 |
| Evaluation Is All You Need for Multi-Modal Autonomous Driving | | 94.9 | iDriveVLA | 2026-09-25 |
| FPD-Drive: Future Policy Distillation for End-to-End Autonomous Driving | | 94.9 | FPD-Drive | 2026-10-09 |
| HybridDriveVLA: Vision-Language-Action Model with Visual CoT reasoning and ToT Evaluation for Autonomous Driving | | 94.89 | HybridDriveVLA (Safety) | 2026-06-03 |
| AUGUstus: Autonomous Driving VLA Model with Unified Generation and Understanding | ✓ Link | 94.64 | AUGUstus (3-step denoising) | 2026-10-12 |
| Driving on Registers | | 94.6 | DrivoR (+134k SimScale data) | 2026-01-08 |
| Vault: One-Step Latent Generation with Positive-Anchored Rewards for Autonomous Driving | | 94.6 | Vault | 2026-06-04 |
| CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning | ✓ Link | 94.5 | Clover | 2026-05-14 |
| ConDenseDrive: Knowledge-Dense, Token-Sparse Visual Encoder for End-to-End Autonomous Driving | | 94.5 | ConDenseDrive | 2026-10-12 |
| Driving on Registers | | 94.0 | DrivoR (+65k SimScale data) | 2026-01-08 |
| MM-Future: Multi-Mode Joint World-Action Modeling for Autonomous Driving | | 94.0 | MM-Future (trainval) | 2026-09-17 |
| World4Scorer: Outcome-Grounded World Modeling for Autonomous Driving | | 94.0 | World4Scorer | 2026-09-29 |
| Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving | | 93.8 | Drive-HWM | 2026-09-03 |
| PlanWAM: Planning-Shaped Future Representations for End-to-End Autonomous Driving | | 93.8 | PlanWAM | 2026-10-08 |
| DriftingPlanner: Drifting Generative Models for One-Step Trajectory Planning in End-to-End Autonomous Driving | | 93.75 | DriftingPlanner | 2026-10-31 |
| Driving on Registers | | 93.7 | DrivoR (trainval) | 2026-01-08 |
| Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving | ✓ Link | 93.7 | Drive-JEPA (ViT/L) (extra data) | 2026-01-29 |
| | 93.5 | DriveSuprim | |
| DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning | | 93.5 | DriveSuprim (ViT-L) | 2025-06-07 |
| EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving | | 93.5 | EvaDrive (Cons) | 2025-08-05 |
| MM-Future: Multi-Mode Joint World-Action Modeling for Autonomous Driving | | 93.4 | MM-Future (train) | 2026-09-17 |
| EvoAD: Self-Evolving Autonomous Driving via Latent World-Model Guided Post-hoc Reflection | | 93.4 | EvoAD (R5) | 2026-09-26 |
| World Action Critic (WAC) Model: Joint Foresight and Criticism for Policy Learning | | 93.4 | WAC | 2026-10-16 |
| MORE: Learning Motion-Oriented Registers for Driving World Models and Planning | ✓ Link | 93.2 | MORE | 2026-10-10 |
| Driving on Registers | | 93.1 | DrivoR (train) | 2026-01-08 |
| AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving | | 93.0 | AdaThinkDrive (Best-of-N) | 2025-09-17 |
| KnowVal: A Knowledge-Augmented and Value-Guided Autonomous Driving System | | 92.9 | KnowVal-iPad | 2025-12-23 |
| FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning | ✓ Link | 92.9 | FlowR2A (64 proposals, ResNet-34) | 2026-06-23 |
| WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving | | 92.9 | WCog-VLA-2B | 2026-07-09 |
| | 92.7 | DiffE2E | |
| DiffE2E: Rethinking End-to-End Driving with a Hybrid Action Diffusion and Supervised Policy | | 92.7 | DiffE2E | 2025-05-26 |
| Centaur: Robust End-to-End Autonomous Driving with Test-Time Training | | 92.6 | Centaur | 2025-03-14 |
| HiPro-AD: Sparse Trajectory Transformer for End-to-End Autonomous Driving with Hybrid Spatiotemporal Attention | | 92.6 | HiPro-AD | 2025-12-26 |
| Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features | | 92.6 | Adaptive-WAM (64 proposals) | 2026-08-06 |
| EvoAD: Self-Evolving Autonomous Driving via Latent World-Model Guided Post-hoc Reflection | | 92.6 | EvoAD (R2) | 2026-09-26 |
| DriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for Autonomous Driving | | 92.3 | DriveWLA | 2026-10-13 |
| Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning | | 92.2 | Discrete-WAM | 2026-06-04 |
| From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving | ✓ Link | 92.1 | HybridDriveVLA | 2026-02-11 |
| DR-VLA: Learning Human-Like Quadruped Navigation from Egocentric Web Videos via Domain-Invariant Scene Representations | | 92.1 | DR-VLA | 2026-10-13 |
| DriveReferee: Geometric Safety Verdicts Need Not Be Learned for Driving World-Action Models | | 92.02 | DriveReferee (full, 16B backbone) | 2026-09-19 |
| SparseDriveV2: Scoring is All You Need for End-to-End Autonomous Driving | ✓ Link | 92.0 | SparseDriveV2 | 2026-03-31 |
| DriveFine: Refining-Augmented Masked Diffusion VLA for Accurate and Robust Driving | | 91.8 | DriveFine (score-based RFT) | 2026-09-08 |
| iPad: Iterative Proposal-centric End-to-End Autonomous Driving | ✓ Link | 91.7 | iPad | 2025-05-21 |
| Reasoning-VLA: A Fast and General Vision-Language-Action Reasoning Model for Autonomous Driving | | 91.7 | Reasoning-VLA-7B | 2025-11-25 |
| DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving | | 91.7 | DynVLA | 2026-03-11 |
| RefineDrive: Reliable Failure-Guided Learning for Vision-Language-Action Driving | | 91.7 | RefineDrive | 2026-09-28 |
| | 91.6 | R2SE | |
| Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving | | 91.6 | R2SE | 2025-06-11 |
| SafeDrive: Fine-Grained Safety Reasoning for End-to-End Driving in a Sparse World | | 91.6 | SafeDrive | 2026-02-21 |
| DriveStack-VLA: Render-Teacher Alignment for BEV-Based DeepStack Vision-Language-Action Model | | 91.6 | DriveStack-VLA | 2026-06-23 |
| DriveUniTok: A Unified Multimodal Tokenizer for Driving World-Action Models | | 91.54 | DriveUniWAM + RL | 2026-10-26 |
| SimWAM: A Simple World Action Model for End-to-End Autonomous Driving | ✓ Link | 91.5 | SimWAM | 2026-08-07 |
| RISE: Adaptive Imagination for World Action Models | ✓ Link | 91.5 | RISE (extra data) | 2026-08-20 |
| DriveReferee: Geometric Safety Verdicts Need Not Be Learned for Driving World-Action Models | | 91.50 | DriveReferee (full, 4B backbone) | 2026-09-19 |
| Reflect-VLA: Internalizing Reflective Guidance via Dual-Path On-Policy Self-Distillation for Autonomous Driving | | 91.5 | Reflect-VLA-4B | 2026-10-09 |
| ASSCG: Just-Right Gating over Chattering for Fast–Slow LLM Planning in Autonomous Driving | ✓ Link | 91.4 | RecogDrive-ASSCG | 2026-06-24 |
| DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving | ✓ Link | 91.3 | DriveWorld-VLA | 2026-02-06 |
| LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving | ✓ Link | 91.3 | LaST-VLA-8B (RL) | 2026-03-02 |
| Auto-JEPA: A Latent World Model of Continuous Intent for End-to-End Autonomous Driving | | 91.3 | Auto-JEPA | 2026-07-31 |
| AffordDrive3D: Affordance-Aware World-Action Modeling with Spatial Understanding | | 91.3 | AffordDrive3D | 2026-10-08 |
| SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models | ✓ Link | 91.3 | SimVTA (extra data) | 2026-10-09 |
| Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving | ✓ Link | 91.1 | ReflectDrive (extra data) | 2025-09-24 |
| LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving | ✓ Link | 91.1 | LaST-VLA-2B (RL) | 2026-03-02 |
| Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling | | 91.1 | CaAD | 2026-05-13 |
| DriveReferee: Geometric Safety Verdicts Need Not Be Learned for Driving World-Action Models | | 91.08 | DriveReferee (base, 16B backbone) | 2026-09-19 |
| Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation | ✓ Link | 91.0 | Hydra-MDP-C | 2024-06-11 |
| Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation | ✓ Link | 91.0 | Hydra-MDP++ | 2024-06-11 |
| Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation | | 91.0 | Hydra-MDP++ (V2-99) | 2025-03-17 |
| WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving | ✓ Link | 91.0 | WAM-Diff | 2025-12-06 |
| Unleashing VLA Potentials in Autonomous Driving via Explicit Learning from Failures | | 91.0 | ELF-VLA-8B | 2026-03-01 |
| UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation | | 91.0 | UNIVERSE | 2026-07-06 |
| GeoWorldAD: Geometry World Action Model for Autonomous Driving | | 91.0 | GeoWorldAD | 2026-07-20 |
| FactorDrive: Adaptive Multi-Step Reasoning Driven by Planning-Critical Factors for End-to-End Autonomous Driving | | 91.0 | FactorDrive | 2026-08-10 |
| DriveUniTok: A Unified Multimodal Tokenizer for Driving World-Action Models | | 91.0 | DriveUniWAM | 2026-10-26 |
| KnowVal: A Knowledge-Augmented and Value-Guided Autonomous Driving System | | 90.9 | KnowVal-DiffusionDrive | 2025-12-23 |
| DriveVA: Video Action Models are Zero-Shot Drivers | | 90.9 | DriveVA | 2026-04-05 |
| 4D-WAM: 4D Consistent World Modeling for Autonomous Driving | | 90.9 | 4D-WAM | 2026-08-10 |
| VITAL: From Visual Motion to Precise Action | ✓ Link | 90.8326 | VITAL | 2026-10-14 |
| OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World Model | | 90.8 | OWMDrive | 2026-06-29 |
| Adaptive-WAM: Quality-Guided Early-Exit Planning from Intermediate Video-Diffusion Features | | 90.8 | Adaptive-WAM (single trajectory) | 2026-08-06 |
| DriveFuture: Future-Aware Latent World Models for Autonomous Driving | | 90.7 | DriveFuture | 2026-05-10 |
| Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving | ✓ Link | 90.7 | Qwen-Drive-1.0-RL | 2026-08-31 |
| READ: Learning Risk-Informed Fields for End-to-End Autonomous Driving | | 90.7 | READ (VLA setting) | 2026-09-11 |
| ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving | | 90.6 | ResAD (V2-99) | 2025-10-09 |
| FutureX: Enhance End-to-End Autonomous Driving via Latent Chain-of-Thought World Model | | 90.6 | FutureX-All (C & L) | 2025-12-12 |
| EvoAD: Self-Evolving Autonomous Driving via Latent World-Model Guided Post-hoc Reflection | | 90.6 | EvoAD (R1) | 2026-09-26 |
| ReWAM: Reciprocal World Action Models for Interactive Autonomous Driving | ✓ Link | 90.6 | ReWAM | 2026-09-30 |
| HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving | | 90.59 | HyWorldVLA | 2026-07-23 |
| GRAVA: Grounded Reasoning-to-Action Representation and Learning for Autonomous Driving | ✓ Link | 90.5 | GRAVA | 2026-09-14 |
| DriveUniTok: A Unified Multimodal Tokenizer for Driving World-Action Models | | 90.5 | DriveUniWAM (Camera-only) | 2026-10-26 |
| DriveReferee: Geometric Safety Verdicts Need Not Be Learned for Driving World-Action Models | | 90.47 | DriveReferee (base, 4B backbone) | 2026-09-19 |
| ReWorld: Representation Learning for World Action Models | ✓ Link | 90.4 | ReWorld | 2026-06-25 |
| Teaching Vision-Language-Action Models What to See and Where to Look | ✓ Link | 90.4 | DriveTeach-VLA | 2026-07-02 |
| PerceptDrive: Perception Prior World-Action Modeling with Adaptive Expert Routing for End-to-End Autonomous Driving | | 90.4 | PerceptDrive | 2026-07-22 |
| Not All History Helps: Velocity-Aware Selective Memory for Long-Horizon End-to-End Autonomous Driving | | 90.4 | StableDrive | 2026-08-16 |
| ForeDrive: Foresight-Guided End-to-End Autonomous Driving with a Planning-Relevant Latent World Model | | 90.4 | ForeDrive (ViT-L) | 2026-09-22 |
| GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving | ✓ Link | 90.3 | GoalFlow | 2025-03-07 |
| AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving | | 90.3 | AdaThinkDrive | 2025-09-17 |
| DriveSafer: End-to-End Autonomous Driving with Safety Guidance | | 90.3 | DriveSafer | 2026-05-16 |
| Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMs | | 90.3 | DiffAdapterVLA-RFT | 2026-09-14 |
| OSWAM: An Effective World Action Model with One-Step Action Generation | ✓ Link | 90.3 | OSWAM | 2026-10-26 |
| Perception in Plan: Coupled Perception and Planning for End-to-End Autonomous Driving | ✓ Link | 90.2 | VeteranAD | 2025-08-15 |
| FutureX: Enhance End-to-End Autonomous Driving via Latent Chain-of-Thought World Model | | 90.2 | FutureX-Auto (C & L) | 2025-12-12 |
| HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving | | 90.2 | HAD | 2026-04-04 |
| UniTeD: Unified Temporal Diffusion for Joint Perception and Planning in Autonomous Driving | | 90.2 | UniTeD | 2026-06-24 |
| ForgeDrive: Bidirectional Cross-Conditioning for Unified Visual-Action Generation in Autonomous Driving | | 90.2 | ForgeDrive | 2026-06-30 |
| MomWorld: Momentum-Aware Latent World Model for Long-Horizon Autonomous Driving | ✓ Link | 90.2 | MomWorld | 2026-09-27 |
| FutureX: Enhance End-to-End Autonomous Driving via Latent Chain-of-Thought World Model | | 90.1 | FutureX-All (C) | 2025-12-12 |
| DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Driving | | 90.1 | DriveWAM | 2026-05-27 |
| GraphWorld: Long-Horizon Planning with World Models for End-to-End Autonomous Driving | | 90.1 | GraphWorld | 2026-06-15 |
| FeasibleFlow: One-Step Joint Transport of Configuration Feasibility and Trajectories for End-to-End Driving | | 90.1 | FeasibleFlow | 2026-09-20 |
| DAP: A Discrete-token Autoregressive Planner for Autonomous Driving | | 90.0 | DAP | 2025-11-17 |
| IDOL: Inverse-Dynamics-Guided Future Prediction for End-to-End Autonomous Driving | ✓ Link | 90.0 | IDOL | 2026-05-29 |
| READ: Learning Risk-Informed Fields for End-to-End Autonomous Driving | | 90.0 | Drive-JEPA + READ | 2026-09-11 |
| Reflect-VLA: Internalizing Reflective Guidance via Dual-Path On-Policy Self-Distillation for Autonomous Driving | | 90.0 | Reflect-VLA-2B | 2026-10-09 |
| DeMo++: Motion Decoupling for Autonomous Driving | ✓ Link | 89.9 | DeMo-E2E++ | 2025-07-23 |
| HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving | | 89.9 | HAD-L | 2026-04-04 |
| MomADv2: Reliable Temporal Memory for End-to-End Autonomous Driving | | 89.9 | MomADv2 | 2026-08-24 |
| Designing Versatile Samples for Learned Trajectory Scoring | ✓ Link | 89.9 | MeanFuser + augmented scorer | 2026-09-01 |
| ForeDrive: Foresight-Guided End-to-End Autonomous Driving with a Planning-Relevant Latent World Model | | 89.9 | ForeDrive | 2026-09-22 |
| WALT: Learning World-Model-Aligned Latent Trajectories for Autonomous Driving | | 89.8 | WALT | 2026-09-24 |
| Dichotomous Diffusion Policy Optimization | | 89.7 | DP-VLA w/ DIPOLE | 2025-12-31 |
| Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives | ✓ Link | 89.7 | LTFv7 | 2026-05-19 |
| TPS-Drive: Task-Guided Representation Purification for VLM-based Autonomous Driving | | 89.7 | TPS-Drive | 2026-05-26 |
| ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving | | 89.6 | ReCogDrive | 2025-06-09 |
| UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generation | | 89.6 | UNIVERSE Two-DiT | 2026-07-06 |
| DRIFT: Drift and Aggregation for Motion Planning | | 89.6 | DRIFT | 2026-07-16 |
| BrainWAM: Action-Space Coordination of Semantic Priors and Predictive Dynamics for Autonomous Driving | | 89.5 | BrainWAM | 2026-08-13 |
| Designing Versatile Samples for Learned Trajectory Scoring | ✓ Link | 89.5 | DiffusionDrive + augmented scorer | 2026-09-01 |
| Uni-World VLA: Interleaved World Modeling and Planning for Autonomous Driving | | 89.4 | Uni-World VLA | 2026-03-28 |
| PLAN-S: Bridging Planning with Latent Style Dynamics for Autonomous Driving World Models | | 89.4 | PLAN-S (rule) | 2026-06-04 |
| Mimir: Hierarchical Goal-Driven Diffusion with Uncertainty Propagation for End-to-End Autonomous Driving | | 89.3 | Mimir | 2025-12-08 |
| See Tomorrow, Act Today: Foresight-Driven Autonomous Driving | ✓ Link | 89.3 | ForeSight | 2026-05-08 |
| Reflect-VLA: Internalizing Reflective Guidance via Dual-Path On-Policy Self-Distillation for Autonomous Driving | | 89.3 | Reflect-VLA-0.8B | 2026-10-09 |
| FutureX: Enhance End-to-End Autonomous Driving via Latent Chain-of-Thought World Model | | 89.2 | FutureX-Auto (C) | 2025-12-12 |
| DriveDreamer-Policy: A Geometry-Grounded World-Action Model for Unified Generation and Planning | | 89.2 | DriveDreamer-Policy | 2026-04-02 |
| DriveLaW:Unifying Planning and Video Generation in a Latent Driving World | ✓ Link | 89.1 | DriveLaW | 2025-12-29 |
| The DAWN of World-Action Interactive Models | ✓ Link | 89.1 | DAWN | 2026-05-12 |
| SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Driving | | 89.1 | SafeAlign-VLA | 2026-05-19 |
| PLAN-S: Bridging Planning with Latent Style Dynamics for Autonomous Driving World Models | | 89.1 | PLAN-S (learned) | 2026-06-04 |
| MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving | | 89.0 | MeanFuser | 2026-02-23 |
| GMF-Drive: Gated Mamba Fusion with Spatial-Aware BEV Representation for End-to-End Autonomous Driving | | 88.9 | GMF-Drive | 2025-08-08 |
| PIE: Perception and Interaction Enhanced End-to-End Motion Planning for Autonomous Driving | | 88.9 | PIE | 2025-09-23 |
| MOJITO: Modal Joint Learning for Unified End-to-End Autonomous Driving | ✓ Link | 88.9 | MOJITO | 2026-07-26 |
| GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving | | 88.8 | GaussianFusion | 2025-05-27 |
| ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving | | 88.8 | ResAD (Resnet-34) | 2025-10-09 |
| DynFlowDrive: Flow-Based Dynamic World Modeling for Autonomous Driving | ✓ Link | 88.7 | DynFlowDrive | 2026-03-20 |
| DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving | | 88.7 | DreamerAD | 2026-03-25 |
| FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving | | 88.7 | FeaXDrive-IL | 2026-04-14 |
| GraphBEV++: Multi-Modal Feature Alignment for Autonomous Driving | | 88.7 | GraphBEV++ (Query) | 2026-06-15 |
| Hydra-NeXt: Robust Closed-Loop Driving with Open-Loop Training | ✓ Link | 88.6 | Hydra-NeXt | 2025-03-15 |
| End-to-End Driving with Online Trajectory Evaluation via BEV World Model | ✓ Link | 88.3 | WoTE | 2025-04-02 |
| DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving | ✓ Link | 88.3 | DIVER | 2025-07-05 |
| Dichotomous Diffusion Policy Optimization | | 88.3 | DP-VLA | 2025-12-31 |
| Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMs | | 88.3 | DiffAdapterVLA-SFT | 2026-09-14 |
| D$^3$-MoE:Dual Disentangled Diffusion Mixture-of-Experts for Style-Controllable End-to-End Autonomous Driving | | 88.2 | D3-MoE | 2026-06-03 |
| DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving | ✓ Link | 88.1 | DiffusionDrive | 2024-11-22 |
| From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction | ✓ Link | 88.1 | PWM | 2025-10-22 |
| DRAE: Dynamic Retrieval-Augmented Expert Networks for Lifelong Learning and Task Adaptation in Robotics | | 88.0 | DRAE | 2025-07-07 |
| Two Tasks, One Goal: Uniting Motion and Planning for Excellent End To End Autonomous Driving Performance | | 87.8 | FUMP | 2025-04-17 |
| WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving | | 87.8 | WorldRFT | 2025-12-22 |
| Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous Driving | ✓ Link | 87.6 | GeoCoTDrive | 2026-10-07 |
| ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving | ✓ Link | 87.4 | InternVL2.5 + ImagiDrive-S | 2025-08-15 |
| SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving | ✓ Link | 87.4 | SGDrive-2B | 2026-01-09 |
| LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving | ✓ Link | 87.3 | LaST-VLA-8B (SFT) | 2026-03-02 |
| BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation | | 87.3 | BehaviorWorldGen | 2026-08-23 |
| | 87.0 | ARTEMIS | |
| ARTEMIS: Autoregressive End-To-End Trajectory Planning with Mixture of Experts for Autonomous Driving | | 87.0 | ARTEMIS | 2025-04-28 |
| LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving | ✓ Link | 87.0 | LaST-VLA-2B (SFT) | 2026-03-02 |
| ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving | ✓ Link | 86.9 | InternVL2.5 + ImagiDrive-A | 2025-08-15 |
| OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models | ✓ Link | 86.8 | OneDrive | 2026-04-20 |
| ReSim: Reliable World Simulation for Autonomous Driving | | 86.6 | ReSim | 2025-06-11 |
| ProDrive: Proactive Planning for Autonomous Driving via Ego-Environment Co-Evolution | | 86.6 | ProDrive | 2026-04-28 |
| ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving | ✓ Link | 86.4 | LLava-1.6 + ImagiDrive-S | 2025-08-15 |
| LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving | ✓ Link | 86.4 | LTFv6 + LEAD (extra data) | 2025-12-23 |
| | 86.2 | Epona | |
| Epona: Autoregressive Diffusion World Model for Autonomous Driving | ✓ Link | 86.2 | Epona | 2025-06-30 |
| ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving | ✓ Link | 86.0 | LLava-1.6 + ImagiDrive-A | 2025-08-15 |
| NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning | | 85.6 | NoRD | 2026-02-24 |
| | 85.5 | DRAMA | |
| DRAMA: An Efficient End-to-end Motion Planner for Autonomous Driving with Mamba | ✓ Link | 85.5 | DRAMA | 2024-08-07 |
| EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation | ✓ Link | 85.3 | EvoDriveVLA | 2026-03-10 |
| World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model | | 85.1 | World4Drive | 2025-07-01 |
| Enhancing End-to-End Autonomous Driving with Latent World Model | ✓ Link | 84.6 | LAW | 2024-06-12 |
| READ: Learning Risk-Informed Fields for End-to-End Autonomous Driving | | 84.6 | TransFuser + READ | 2026-09-11 |
| Embodied Navigation Foundation Model | | 84.3 | NavFoM (Eight views) | 2025-09-15 |
| TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving | ✓ Link | 84.0 | TransFuser | 2022-05-31 |
| PARA-Drive: Parallelized Architecture for Real-time Autonomous Driving | | 84.0 | PARA-Drive | 2024-01-01 |
| TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving | ✓ Link | 83.8 | Latent TransFuser | 2022-05-31 |
| Planning-oriented Autonomous Driving | ✓ Link | 83.4 | UniAD | 2022-12-20 |
| ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving | | 83.3 | InternVL3 | 2025-06-09 |
| ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving | | 83.3 | QwenVL2.5 | 2025-06-09 |
| DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers | | 82.4 | DrivingGPT | 2024-12-24 |
| VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning | ✓ Link | 80.9 | VAD-v2 | 2024-02-20 |
| NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking | ✓ Link | 65.6 | Ego Status MLP | 2024-06-21 |
| NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking | ✓ Link | 20.6 | Constant Velocity | 2024-06-21 |