Aligning Multi-Trajectory Supervision with Policy Optimization for VLA Driving

arXiv:2608.30122 · cs.CV, cs.AI, cs.LG · Submitted 2026-08-31 · Read on arXiv

cs.CV, cs.AI, cs.LG

Submitted: 2026-08-31

Updated: 2026-08-31

Terminology

• GRPO — 66× in this paper · explained in 6 episodes
• Distillation — 9× in this paper · explained in 2 episodes
• Credit assignment — 8× in this paper · explained in 3 episodes
• Fine-Tuning — 8× in this paper · explained in 5 episodes
• Adaptive Pareto-Guided Policy Refinement — 6× in this paper
• Benchmark — 6× in this paper · explained in 2 episodes
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Alignment — 5× in this paper · explained in 1 episode
• Regularization — 5× in this paper · explained in 3 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Representation Learning — 3× in this paper · explained in 2 episodes
• Semantic Alignment — 3× in this paper · explained in 3 episodes
• World Model — 3× in this paper · explained in 7 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Feature Extraction — 2× in this paper · explained in 2 episodes
• Action Decoder — 1× in this paper · explained in 1 episode
• Aligned Multi-Trajectory Policy Training — 1× in this paper
• Alignment Problem — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• KL Regularization — 1× in this paper · explained in 2 episodes
• Multimodal Fusion — 1× in this paper · explained in 3 episodes
• Q-learning — 1× in this paper · explained in 3 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• VLA Models — 1× in this paper · explained in 3 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes

Sources

• CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
• Pseudo-Simulation for Autonomous Driving
• Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Models
• EMMA: End-to-End Multimodal Model for Autonomous Driving
• AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
• EvaDrive: Evolutionary Adversarial Policy Optimization for End-to-End Autonomous Driving
• Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation
• DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
• ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
• Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation
• AdaThinkDrive: Adaptive Thinking via Reinforcement Learning for Autonomous Driving
• AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
• Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling
• HMAD: Advancing E2E Driving with Anchored Offset Proposals and Simulation-Supervised Multi-target Scoring
• Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving
• HAD: Combining Hierarchical Diffusion with Metric-Decoupled RL for End-to-End Driving
• OpenDriveVLA: Towards End-to-end Autonomous Driving with Large Vision Language Action Model
• InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
• DiffusionDriveV2: Reinforcement Learning-Constrained Truncated Diffusion Modeling in End-to-End Autonomous Driving

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models