# Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving

arXiv: https://arxiv.org/abs/2509.20109 · HTML: https://mlsanity.com/paper/2509.20109/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Driving VLMs and open-vocabulary detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 34 of its 41 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Driving VLMs and open-vocabulary detection](https://mlsanity.com/mllm/driving-vlms-and-open-vocabulary-detection/)
- Vision-language-action models / [VLA for autonomous driving](https://mlsanity.com/vla/vla-for-autonomous-driving/)
- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- End-to-end autonomous driving / [Reasoning VLA and VLM driving policies](https://mlsanity.com/driving/reasoning-vla-and-vlm-driving-policies/)

## Builds on (most cited first, 30 of 34)

- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Structured Denoising Diffusion Models in Discrete State-Spaces](https://mlsanity.com/paper/2107.03006/) (2021)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Large Language Diffusion Models](https://mlsanity.com/paper/2502.09992/) (2025)
- [Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution](https://mlsanity.com/paper/2310.16834/) (2023)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking](https://mlsanity.com/paper/2406.15349/) (2024)
- [DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2411.15139/) (2024)
- [Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1610.03295/) (2016)
- [Learning to Drive in a Day](https://mlsanity.com/paper/1807.00412/) (2018)
- [AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.13757/) (2025)
- [Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation](https://mlsanity.com/paper/2406.06978/) (2024)
- [Parting with Misconceptions about Learning-based Vehicle Motion Planning](https://mlsanity.com/paper/2306.07962/) (2023)
- [MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion](https://mlsanity.com/paper/2306.03083/) (2023)
- [Guided Conditional Diffusion for Controllable Traffic Simulation](https://mlsanity.com/paper/2210.17366/) (2022)
- [SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment](https://mlsanity.com/paper/2503.09594/) (2025)
- [Concrete Score Matching: Generalized Score Matching for Discrete Data](https://mlsanity.com/paper/2211.00802/) (2022)
- [LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning](https://mlsanity.com/paper/2505.16933/) (2025)
- [OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning](https://mlsanity.com/paper/2504.04348/) (2025)
- [Diffusion-Based Planning for Autonomous Driving with Flexible Guidance](https://mlsanity.com/paper/2501.15564/) (2025)
- [Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios](https://mlsanity.com/paper/2212.11419/) (2022)
- [A Survey of End-to-End Driving: Architectures and Training Methods](https://mlsanity.com/paper/2003.06404/) (2020)
- [GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving](https://mlsanity.com/paper/2503.05689/) (2025)

## Built on by (most cited first, 24 of 24)

- [Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future](https://mlsanity.com/paper/2512.16760/) (2025)
- [Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling](https://mlsanity.com/paper/2510.11083/) (2025)
- [DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving](https://mlsanity.com/paper/2602.14577/) (2026)
- [Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone](https://mlsanity.com/paper/2512.22615/) (2025)
- [EponaV2: Driving World Model with Comprehensive Future Reasoning](https://mlsanity.com/paper/2605.14696/) (2026)
- [ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving](https://mlsanity.com/paper/2510.08562/) (2025)
- [dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning](https://mlsanity.com/paper/2512.04459/) (2025)
- [Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving](https://mlsanity.com/paper/2602.22801/) (2026)
- [Qwen-RobotNav Technical Report: A Scalable Navigation Model Designed for an Agentic Navigation System](https://mlsanity.com/paper/2606.18112/) (2026)
- [WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/2512.11872/) (2025)
- [Dichotomous Diffusion Policy Optimization](https://mlsanity.com/paper/2601.00898/) (2025)
- [Fast-dDrive: Efficient Block-Diffusion VLM for Autonomous Driving](https://mlsanity.com/paper/2605.23163/) (2026)
- [E0: Enhancing Generalization and Fine-Grained Control in VLA Models via Tweedie Discrete Diffusion](https://mlsanity.com/paper/2511.21542/) (2025)
- [Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning](https://mlsanity.com/paper/2606.05645/) (2026)
- [MTDrive: Multi-turn Interactive Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/2601.22930/) (2026)
- [IDOL: Inverse-Dynamics-Guided Future Prediction for End-to-End Autonomous Driving](https://mlsanity.com/paper/2605.31476/) (2026)
- [Post-Training in End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.08072/) (2026)
- [WCog-VLA: A Dual-Level World-Cognitive Vision-Language-Action Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.08375/) (2026)
- [Unified Prediction and Planning via Conflict-Aware Disjoint Parameter Training](https://mlsanity.com/paper/2607.19971/) (2026)
- [Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs](https://mlsanity.com/paper/2608.01755/) (2026)
- [Beyond Textual Chain-of-Thought: A Survey on Action-Grounded Reasoning in Autonomous Driving](https://mlsanity.com/paper/2609.01659/) (2026)
- [VIPS: Vehicle-Infrastructure Cooperative Planning Benchmark via Pseudo-Simulation](https://mlsanity.com/paper/2609.02462/) (2026)
- [Diffusion Language Models for Mobile Edge Agentic AI: Foundations, Applications, and Challenges](https://mlsanity.com/paper/2609.04778/) (2026)
- [RefineDrive: Reliable Failure-Guided Learning for Vision-Language-Action Driving](https://mlsanity.com/paper/2609.35078/) (2026)

## Abstract (arXiv)

End-to-End (E2E) solutions have emerged as a mainstream approach for autonomous driving systems, with Vision-Language-Action (VLA) models representing a new paradigm that leverages pre-trained multimodal knowledge from Vision-Language Models (VLMs) to interpret and interact with complex real-world environments. However, these methods remain constrained by the limitations of imitation learning, which struggles to inherently encode physical rules during training. Existing approaches often rely on complex rule-based post-refinement, employ reinforcement learning that remains largely limited to simulation, or utilize diffusion guidance that requires computationally expensive gradient calculations. To address these challenges, we introduce ReflectDrive, a novel learning-based framework that integrates a reflection mechanism for safe trajectory generation via discrete diffusion. We first discretize the two-dimensional driving space to construct an action codebook, enabling the use of pre-trained Diffusion Language Models for planning tasks through fine-tuning. Central to our approach is a safety-aware reflection mechanism that performs iterative self-correction without gradient computation. Our method begins with goal-conditioned trajectory generation to model multi-modal driving behaviors. Based on this, we apply local search methods to identify unsafe tokens and determine feasible solutions, which then serve as safe anchors for inpainting-based regeneration. Evaluated on the NAVSIM benchmark, ReflectDrive demonstrates significant advantages in safety-critical trajectory generation, offering a scalable and reliable solution for autonomous driving systems.