mlsanityData to 7 Oct 2026

EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation

arXiv 2603.09465 ↗First posted 10 Mar 2026cs.CV cs.AIcited by 3

On the map: Vision-language-action models → VLA for autonomous driving

also in 1 more
Abstract (arXiv)

Vision-Language-Action models have shown great promise for autonomous driving, yet they suffer from degraded perception after unfreezing the visual encoder and struggle with accumulated instability in long-term planning. To address these challenges, we propose EvoDriveVLA-a novel collaborative perception-planning distillation framework that integrates self-anchored perceptual constraints and future-informed trajectory optimization. Specifically, self-anchored visual distillation leverages self-anchor teacher to deliver visual anchoring constraints, regularizing student representations via trajectory-guided key-region awareness. In parallel, future-informed trajectory distillation employs a future-aware oracle teacher with coarse-to-fine trajectory refinement and Monte Carlo dropout sampling to synthesize reasoning trajectories that model future evolutions, enabling the student model to internalize the future-aware insights of the teacher. EvoDriveVLA achieves SOTA performance in nuScenes open-loop evaluation and significantly enhances performance in NAVSIM closed-loop evaluation. Our code is available at: https://github.com/hey-cjj/EvoDriveVLA.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in VLA for autonomous driving, one of 13 directions in Vision-language-action models. Builds on 52 of its 56 references that are in the map. First posted on arXiv 10 Mar 2026.

Builds on

52 of 56 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving14 Oct
  2. 2025FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning31 Jul
  3. 2025Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models29 May
  4. 2025FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving23 May
  5. 2025OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model30 Mar

Other references · 47

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2023Visual Instruction Tuningcited by 7,792
  3. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  4. 2025Qwen2.5-VL Technical Reportcited by 5,418
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  7. 2022Planning-oriented Autonomous Drivingcited by 1,068
  8. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 822
  9. 2023VAD: Vectorized Scene Representation for Efficient Autonomous Drivingcited by 613
  10. 2023DriveLM: Driving with Graph Visual Question Answeringcited by 527
  11. 2024DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Modelscited by 482
  12. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 477
35 more
  1. 2022ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learningcited by 365
  2. 2023GPT-Driver: Learning to Drive with GPTcited by 344
  3. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarkingcited by 343
  4. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 336
  5. 2024DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Drivingcited by 324
  6. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 287
  7. 2024Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillationcited by 244
  8. 2023Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving?cited by 242
  9. 2023OccWorld: Learning a 3D Occupancy World Model for Autonomous Drivingcited by 230
  10. 2025ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Drivingcited by 190
  11. 2025ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generationcited by 177
  12. 2024Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMscited by 153
  13. 2025OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoningcited by 142
  14. 2024Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoderscited by 137
  15. 2024textitS3Gaussian: Self-Supervised Street Gaussians for Autonomous Drivingcited by 105
  16. 2025Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillationcited by 93
  17. 2022Differentiable Raycasting for Self-supervised Occupancy Forecastingcited by 83
  18. 2025RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learningcited by 76
  19. 2024Embodied Understanding of Driving Scenarioscited by 63
  20. 2025DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Drivingcited by 52
  21. 2025Distilling Multi-modal Large Language Models for Autonomous Drivingcited by 46
  22. 2024DME-Driver: Integrating Human Decision Logic and 3D Scene Perception in Autonomous Drivingcited by 41
  23. 2024LLaVA-KD: A Framework of Distilling Multimodal Large Language Modelscited by 37
  24. 2025Don't Blind Your VLA: Aligning Visual Representations for OOD Generalizationcited by 34
  25. 2025Semi-Supervised Vision-Centric 3D Occupancy World Model for Autonomous Drivingcited by 29
  26. 2025MoVE-KD: Knowledge Distillation for VLMs with Mixture of Visual Encoderscited by 25
  27. 2025DSDrive: Distilling Large Language Model for Lightweight End-to-End Autonomous Driving with Unified Reasoning and Planningcited by 17
  28. 2024EMD: Explicit Motion Modeling for High-Quality Street Gaussian Splattingcited by 13
  29. 2025DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Modelcited by 13
  30. 2025RoboDriveVLM: A Novel Benchmark and Baseline towards Robust Vision-Language Models for Autonomous Drivingcited by 8
  31. 2025NavigScene: Bridging Local Perception and Global Navigation for Beyond-Visual-Range Autonomous Drivingcited by 7
  32. 2026ParkGaussian: Surround-view 3D Gaussian Splatting for Autonomous Parkingcited by 7
  33. 2024AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillationcited by 5
  34. 2025VDRive: Leveraging Reinforced VLA and Diffusion Policy for End-to-end Autonomous Drivingcited by 5
  35. 2025Driving Beyond Privilege: Distilling Dense-Reward Knowledge into Sparse-Reward Policiescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 20263DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-trainingcited by 1
  2. 2026GraspFoM: Towards Reconstruction-Driven Robotic Grasping with 3D Foundation Priorscited by 1
  3. 2026SparseStreet: Sparse Gaussian Splatting for Real-Time Street Scene Simulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning
  2. 2026Learning Vision-Language-Action World Models for Autonomous Driving
  3. 2026Teaching Vision-Language-Action Models What to See and Where to Look
  4. 2026UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving
  5. 2026AnchorVLA: Bridging Discrete Decisions and Continuous Trajectories for Vision-Language-Action Planning
  6. 2025AutoDrive-R2: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving
  7. 2026Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs
  8. 2026Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMs