# VLMs for autonomous driving

Area: [End-to-end autonomous driving](https://mlsanity.com/driving/index.md). HTML: https://mlsanity.com/driving/vlms-for-autonomous-driving/

## Key facts

- VLMs for autonomous driving: 270 papers on arXiv since 2021 (data through 14 Oct 2026).
- 104 of its 270 mapped papers (39%) cite “DriveLM: Driving with Graph Visual Question Answering” (2023, arXiv 2312.14150).
- 82 of its 270 mapped papers (30%) cite “DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models” (2024, arXiv 2402.12289).
- 10 new papers 17 Sep–14 Oct.

## Most cited here

- [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023), cited by 104 papers here
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024), cited by 82 papers here
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023), cited by 41 papers here
- [LingoQA: Visual Question Answering for Autonomous Driving](https://mlsanity.com/paper/2312.14115/) (2023), cited by 39 papers here
- [Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives](https://mlsanity.com/paper/2501.04003/) (2025), cited by 37 papers here
- [Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving](https://mlsanity.com/paper/2312.03661/) (2023), cited by 31 papers here
- [Vision Language Models in Autonomous Driving: A Survey and Outlook](https://mlsanity.com/paper/2310.14414/) (2023), cited by 28 papers here
- [Language Prompt for Autonomous Driving](https://mlsanity.com/paper/2309.04379/) (2023), cited by 26 papers here
- [Dolphins: Multimodal Language Model for Driving](https://mlsanity.com/paper/2312.00438/) (2023), cited by 26 papers here
- [Talk2BEV: Language-enhanced Bird's-eye View Maps for Autonomous Driving](https://mlsanity.com/paper/2310.02251/) (2023), cited by 23 papers here

## New (17 Sep–14 Oct)

- [ConDenseDrive: Knowledge-Dense, Token-Sparse Visual Encoder for End-to-End Autonomous Driving](https://mlsanity.com/paper/2610.16908/) (2026-10-12)
- [Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving](https://mlsanity.com/paper/2610.08331/) (2026-10-06)
- [Localized Conformal Safety Monitoring with Vision-Language Models for Autonomous Driving](https://mlsanity.com/paper/2610.02765/) (2026-10-02)
- [Towards Reliable Vision-Language Models for Autonomous Driving](https://mlsanity.com/paper/2610.01531/) (2026-10-01)
- [BD-HazardVLM: Probing Vision-Language Models for Latent Defensive-Driving Hazards in Bangladesh Road Scenes](https://mlsanity.com/paper/2610.20627/) (2026-09-28)
- [Beyond Retrieval Relevance: Scene-Grounded Risk Entailment for Vision-Language Driving](https://mlsanity.com/paper/2609.34145/) (2026-09-28)
- [FocusDrive: Reasoning with Visual Focus for Autonomous Driving](https://mlsanity.com/paper/2609.33190/) (2026-09-27)
- [RCVLA: 4D Radar-Grounded Semantic Reasoning and Trajectory Arbitration for Autonomous Driving](https://mlsanity.com/paper/2609.32681/) (2026-09-26)
- [From Scene Graphs to Answers: Selective Neuro-Symbolic Reasoning for Autonomous Driving](https://mlsanity.com/paper/2609.32645/) (2026-09-26)
- [CoVLM-Bench: A Real-World Benchmark for Cooperative Driving Question Answering and Planning](https://mlsanity.com/paper/2609.35823/) (2026-09-22)