Cover Image

DriveFine: Refining-Augmented Masked Diffusion VLA for Precise and Robust Driving

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dang, Chenxu, Ang, Sining, Li, Yongkang, Tian, Haochen, Wang, Jie, Li, Guang, Ye, Hangjun, Ma, Jie, Chen, Long, Wang, Yan
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving
by: Wang, Jie, et al.
Published: (2026)

SAMoE-VLA: A Scene Adaptive Mixture-of-Experts Vision-Language-Action Model for Autonomous Driving
by: You, Zihan, et al.
Published: (2026)

SparseOccVLA: Bridging Occupancy and Vision-Language Models via Sparse Queries for Unified 4D Scene Understanding and Planning
by: Dang, Chenxu, et al.
Published: (2026)

UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Driving
by: Li, Yongkang, et al.
Published: (2026)

Learning from Mistakes: Post-Training for Driving VLA with Takeover Data
by: Gao, Yinfeng, et al.
Published: (2026)

DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving
by: jia, Feiyang, et al.
Published: (2026)

SimScale: Learning to Drive via Real-World Simulation at Scale
by: Tian, Haochen, et al.
Published: (2025)

CLOVER: Closed-Loop Value Estimation and Ranking for End-to-End Autonomous Driving Planning
by: Ang, Sining, et al.
Published: (2026)

ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving
by: Li, Yongkang, et al.
Published: (2025)

Beyond Imitation: Learning Safe End-to-End Autonomous Driving from Hard Negatives
by: Wang, Junli, et al.
Published: (2026)

DriveLaW:Unifying Planning and Video Generation in a Latent Driving World
by: Xia, Tianze, et al.
Published: (2025)

From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving
by: Ang, Sining, et al.
Published: (2026)

Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Driving
by: Liu, Haochen, et al.
Published: (2025)

LaST-VLA: Thinking in Latent Spatio-Temporal Space for Vision-Language-Action in Autonomous Driving
by: Luo, Yuechen, et al.
Published: (2026)

Mirage: One-Step Video Diffusion for Photorealistic and Coherent Asset Editing in Driving Scenes
by: Wang, Shuyun, et al.
Published: (2025)

DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving
by: Li, Yingyan, et al.
Published: (2025)

EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation
by: Cao, Jiajun, et al.
Published: (2026)

WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving
by: Xu, Mingwang, et al.
Published: (2025)

LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model
by: Mei, Xiaodong, et al.
Published: (2026)

Unleashing the Potential of Diffusion Models for End-to-End Autonomous Driving
by: Zheng, Yinan, et al.
Published: (2026)

MeanFuser: Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via MeanFlow for End-to-End Autonomous Driving
by: Wang, Junli, et al.
Published: (2026)

UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling
by: Tan, Kaiyuan, et al.
Published: (2026)

DiffVLA: Vision-Language Guided Diffusion Planning for Autonomous Driving
by: Jiang, Anqing, et al.
Published: (2025)

DriveAction: A Benchmark for Exploring Human-like Driving Decisions in VLA Models
by: Hao, Yuhan, et al.
Published: (2025)

DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
by: Chen, Xiaoxue, et al.
Published: (2025)

PerlAD: Towards Enhanced Closed-loop End-to-end Autonomous Driving with Pseudo-simulation-based Reinforcement Learning
by: Gao, Yinfeng, et al.
Published: (2026)

Toward Physically Consistent Driving Video World Models under Challenging Trajectories
by: Zhou, Jiawei, et al.
Published: (2026)

DynVLA: Learning World Dynamics for Action Reasoning in Autonomous Driving
by: Shang, Shuyao, et al.
Published: (2026)

DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving
by: Liao, Bencheng, et al.
Published: (2024)

RealDrive: Retrieval-Augmented Driving with Diffusion Models
by: Ding, Wenhao, et al.
Published: (2025)

Learning Probabilities of Causation with Mask-Augmented Data
by: Wang, Shuai, et al.
Published: (2025)

Characterized Diffusion and Spatial-Temporal Interaction Network for Trajectory Prediction in Autonomous Driving
by: Liao, Haicheng, et al.
Published: (2024)

DriveSplat: Unified Neural Gaussian Reconstruction for Dynamic Driving Scenes
by: Wang, Cong, et al.
Published: (2025)

Map-World: Masked Action planning and Path-Integral World Model for Autonomous Driving
by: Hu, Bin, et al.
Published: (2025)

Devil is in Narrow Policy: Unleashing Exploration in Driving VLA Models
by: Chen, Canyu, et al.
Published: (2026)

StyleVLA: Driving Style-Aware Vision Language Action Model for Autonomous Driving
by: Gao, Yuan, et al.
Published: (2026)

MindVLA-U1: VLA Beats VA with Unified Streaming Architecture for Autonomous Driving
by: Huang, Yuzhou, et al.
Published: (2026)

PointForward: Feedforward Driving Reconstruction through Point-Aligned Representations
by: Chi, Cheng, et al.
Published: (2026)

FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning
by: Cao, Jiajun, et al.
Published: (2025)

DriveMRP: Enhancing Vision-Language Models with Synthetic Motion Data for Motion Risk Prediction
by: Hou, Zhiyi, et al.
Published: (2025)