Buchumschlag

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

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Li, Pengxiang, Zheng, Yinan, Wang, Yue, Wang, Huimin, Zhao, Hang, Liu, Jingjing, Zhan, Xianyuan, Zhan, Kun, Lang, Xianpeng
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Robotics Artificial Intelligence Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
von: Wang, Huimin, et al.
Veröffentlicht: (2026)

Generalizing Motion Planners with Mixture of Experts for Autonomous Driving
von: Sun, Qiao, et al.
Veröffentlicht: (2024)

Unifying Language-Action Understanding and Generation for Autonomous Driving
von: Wang, Xinyang, et al.
Veröffentlicht: (2026)

Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling
von: Tan, Tianyi, et al.
Veröffentlicht: (2025)

Diffusion-Based Planning for Autonomous Driving with Flexible Guidance
von: Zheng, Yinan, et al.
Veröffentlicht: (2025)

Stable Language Guidance for Vision-Language-Action Models
von: Zhan, Zhihao, et al.
Veröffentlicht: (2026)

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

TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous Driving
von: Jiang, Xuefeng, et al.
Veröffentlicht: (2025)

DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking
von: Zheng, Weicheng, et al.
Veröffentlicht: (2025)

Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model
von: Zheng, Yinan, et al.
Veröffentlicht: (2024)

Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback
von: Li, Derun, et al.
Veröffentlicht: (2025)

The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning
von: Jiang, Titong, et al.
Veröffentlicht: (2025)

Universal Actions for Enhanced Embodied Foundation Models
von: Zheng, Jinliang, et al.
Veröffentlicht: (2025)

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Process
von: Chen, Jiayi, et al.
Veröffentlicht: (2025)

DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models
von: Tian, Xiaoyu, et al.
Veröffentlicht: (2024)

X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model
von: Zheng, Jinliang, et al.
Veröffentlicht: (2025)

Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
von: Hu, Tianshuai, et al.
Veröffentlicht: (2025)

A Superalignment Framework in Autonomous Driving with Large Language Models
von: Kong, Xiangrui, et al.
Veröffentlicht: (2024)

Towards Robust Zero-Shot Reinforcement Learning
von: Zheng, Kexin, et al.
Veröffentlicht: (2025)

X-Driver: Explainable Autonomous Driving with Vision-Language Models
von: Liu, Wei, et al.
Veröffentlicht: (2025)

Dichotomous Diffusion Policy Optimization
von: Liang, Ruiming, et al.
Veröffentlicht: (2025)

OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Driving
von: Yan, Tianyi, et al.
Veröffentlicht: (2024)

SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models
von: Fei, Senyu, et al.
Veröffentlicht: (2025)

A Survey on Vision-Language-Action Models for Autonomous Driving
von: Jiang, Sicong, et al.
Veröffentlicht: (2025)

Less is More: Lean yet Powerful Vision-Language Model for Autonomous Driving
von: Yang, Sheng, et al.
Veröffentlicht: (2025)

A Language Agent for Autonomous Driving
von: Mao, Jiageng, et al.
Veröffentlicht: (2023)

Unveiling the Potential of Vision-Language-Action Models with Open-Ended Multimodal Instructions
von: Zhao, Wei, et al.
Veröffentlicht: (2025)

AutoMoT: A Unified Vision-Language-Action Model with Asynchronous Mixture-of-Transformers for End-to-End Autonomous Driving
von: Huang, Wenhui, et al.
Veröffentlicht: (2026)

VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation
von: Zhao, Han, et al.
Veröffentlicht: (2025)

LanguageMPC: Large Language Models as Decision Makers for Autonomous Driving
von: Sha, Hao, et al.
Veröffentlicht: (2023)

EdgeVLA: Efficient Vision-Language-Action Models
von: Budzianowski, Paweł, et al.
Veröffentlicht: (2025)

VLAS: Vision-Language-Action Model With Speech Instructions For Customized Robot Manipulation
von: Zhao, Wei, et al.
Veröffentlicht: (2025)

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

LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
von: Fei, Senyu, et al.
Veröffentlicht: (2025)

AgentThink: A Unified Framework for Tool-Augmented Chain-of-Thought Reasoning in Vision-Language Models for Autonomous Driving
von: Qian, Kangan, et al.
Veröffentlicht: (2025)

DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
von: Li, Jianxiong, et al.
Veröffentlicht: (2024)

CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding
von: Song, Wenxuan, et al.
Veröffentlicht: (2025)

PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planning
von: Zheng, Yupeng, et al.
Veröffentlicht: (2024)

GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control
von: Chen, Anthony, et al.
Veröffentlicht: (2025)

DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models
von: Wen, Licheng, et al.
Veröffentlicht: (2023)