RAF-VLA: Representation Alignment with the Future for End-to-End Autonomous Driving

arXiv:2609.17728 · cs.RO · Submitted 2026-09-15 · Read on arXiv

cs.RO

Submitted: 2026-09-15

Updated: 2026-09-15

Code: https://github.com/OpenDriveLab/OpenScene

Terminology

• Alignment — 37× in this paper · explained in 1 episode
• Fine-Tuning — 10× in this paper · explained in 5 episodes
• Regularization — 10× in this paper · explained in 3 episodes
• Transformer — 10× in this paper · explained in 2 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• GRPO — 6× in this paper · explained in 6 episodes
• Joint Attention — 6× in this paper · explained in 2 episodes
• Reinforcement Fine-Tuning — 5× in this paper
• World Model — 5× in this paper · explained in 7 episodes
• Computer Vision and Pattern Recognition — 4× in this paper
• Future-Aligned Supervised Fine-Tuning — 4× in this paper
• CVF International Conference on Computer Vision — 3× in this paper
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Vision-Language-Action (VLA) Models — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Ablation Studies — 2× in this paper · explained in 1 episode
• Distillation — 2× in this paper · explained in 2 episodes
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Predictive Driver Model Score — 2× in this paper
• Supervised Fine-Tuning (SFT) — 2× in this paper · explained in 8 episodes
• Action Flow — 1× in this paper · explained in 1 episode
• Adaptive Reasoning — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Drivable Area Compliance — 1× in this paper
• Driving Direction Compliance — 1× in this paper
• EMMA — 1× in this paper · explained in 2 episodes
• Ego Progress — 1× in this paper
• Extended Comfort — 1× in this paper
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Group Relative Policy Optimization — 1× in this paper
• History Comfort — 1× in this paper
• Lane Keeping — 1× in this paper
• No At-Fault Collision — 1× in this paper
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Recent Vision-Language-Action — 1× in this paper
• Representation Learning — 1× in this paper · explained in 2 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Traffic Light Compliance — 1× in this paper
• Two-Stage Training Strategy — 1× in this paper · explained in 3 episodes
• Two-stage training — 1× in this paper · explained in 2 episodes
• Vision-Language Models (VLMs) — 1× in this paper · explained in 6 episodes
• Vision-language models — 1× in this paper · explained in 2 episodes

Sources

• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
• EMMA: End-to-End Multimodal Model for Autonomous Driving
• AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving
• Robotic Control via Embodied Chain-of-Thought Reasoning
• SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving
• ExploreVLA: Dense World Modeling and Exploration for End-to-End Autonomous Driving
• To View Transform or Not to View Transform: NeRF-based Pre-training Perspective
• Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
• OpenVLA: An Open-Source Vision-Language-Action Model
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning
• Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning
• Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation
• Pseudo-Simulation for Autonomous Driving
• Qwen2.5-VL Technical Report
• Cosmos World Foundation Model Platform for Physical AI

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving