# SafeAlign-VLA: A Negative-Enhanced Safe Alignment Framework for Risk-Aware Autonomous Driving arXiv: https://arxiv.org/abs/2605.19524 ยท HTML: https://mlsanity.com/paper/2605.19524/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving. - Builds on 50 of its 59 references that are in the map. - First posted on arXiv 19 May 2026. ## Placed in - End-to-end autonomous driving / [Reinforcement learning for driving](https://mlsanity.com/driving/reinforcement-learning-for-driving/) ## Builds on (most cited first, 30 of 50) - [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025) - [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025) - [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022) - [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022) - [DriveLM: Driving with Graph Visual Question Answering](https://mlsanity.com/paper/2312.14150/) (2023) - [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) - [DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model](https://mlsanity.com/paper/2310.01412/) (2023) - [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018) - [Multi-Modal Fusion Transformer for End-to-End Autonomous Driving](https://mlsanity.com/paper/2104.09224/) (2021) - [ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning](https://mlsanity.com/paper/2207.07601/) (2022) - [NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking](https://mlsanity.com/paper/2406.15349/) (2024) - [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019) - [DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2411.15139/) (2024) - [LMDrive: Closed-Loop End-to-End Driving with Large Language Models](https://mlsanity.com/paper/2312.07488/) (2023) - [VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning](https://mlsanity.com/paper/2402.13243/) (2024) - [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) - [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022) - [SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation](https://mlsanity.com/paper/2405.19620/) (2024) - [ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving](https://mlsanity.com/paper/2506.08052/) (2025) - [Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey](https://mlsanity.com/paper/2503.12605/) (2025) - [ORION: A Holistic End-to-End Autonomous Driving Framework by Vision-Language Instructed Action Generation](https://mlsanity.com/paper/2503.19755/) (2025) - [OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model](https://mlsanity.com/paper/2503.23463/) (2025) - [End-to-End Driving with Online Trajectory Evaluation via BEV World Model](https://mlsanity.com/paper/2504.01941/) (2025) - [SimLingo: Vision-Only Closed-Loop Autonomous Driving with Language-Action Alignment](https://mlsanity.com/paper/2503.09594/) (2025) - [LingoQA: Visual Question Answering for Autonomous Driving](https://mlsanity.com/paper/2312.14115/) (2023) - [OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning](https://mlsanity.com/paper/2504.04348/) (2025) - [Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios](https://mlsanity.com/paper/2212.11419/) (2022) - [Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving](https://mlsanity.com/paper/2312.03661/) (2023) - [AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning](https://mlsanity.com/paper/2503.07608/) (2025) ## Built on by (most cited first, 2 of 2) - [Post-Training in End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.08072/) (2026) - [RefineDrive: Reliable Failure-Guided Learning for Vision-Language-Action Driving](https://mlsanity.com/paper/2609.35078/) (2026) ## Abstract (arXiv) End-to-end autonomous driving systems excel in common scenarios but struggle with safety-critical long-tail cases. Vision-Language-Action (VLA) models are promising due to their strong reasoning capabilities. However, most VLA-based approaches rely on positive expert demonstrations, rarely exploiting negative samples, leading to insufficient understanding of risky behaviors and safety boundaries. To address this limitation, we propose SafeAlign-VLA, a unified negative-enhanced safe alignment framework that incorporates negative data into supervised learning and reinforcement learning. First, we develop a counterfactual safety pairing paradigm to generate structured safety labels and counterfactual positive trajectories from risky scenarios via counterfactual reasoning. Then, a two-stage training strategy is adopted: negative-enhanced supervised fine-tuning for failure feedback and trajectory correction, followed by anchor-based group relative policy optimization that uses positive and negative trajectories as contrastive anchors to steer sampling and penalize high-risk behaviors via group-relative advantages. Experiments on NAVSIM and DeepAccident validate the proposed framework. SafeAlign-VLA achieves 89.1 PDMS on the NAVSIM v1 testset, improving over the baseline without negative data by 1.3%. On DeepAccident, it reduces the collision rate to 3.36%, while achieving 84.2% language accuracy and 85.8% risk prediction accuracy. These results demonstrate the effectiveness of the proposed negative-enhanced safe alignment framework for safe and robust autonomous driving.