Image de couverture de livre

Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Qi, Yin, Bo, Huang, Weiqi, Liu, Ruhao, Zou, Bojun, Yu, Runpeng, Ye, Jingwen, Yu, Weihao, Wang, Xinchao
Format:	Preprint
Publié:	2026
Sujets:	Robotics
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Attention Prompting on Image for Large Vision-Language Models
par: Yu, Runpeng, et autres
Publié: (2024)

NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language Priors
par: Ren, Lingfeng, et autres
Publié: (2026)

HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models
par: Chen, Zixing, et autres
Publié: (2026)

AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration
par: Liu, Ruhao, et autres
Publié: (2026)

KAN or MLP: A Fairer Comparison
par: Yu, Runpeng, et autres
Publié: (2024)

An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges
par: Xu, Chao, et autres
Publié: (2025)

DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation
par: Yang, Zebin, et autres
Publié: (2026)

Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior
par: Yin, Bo, et autres
Publié: (2026)

Discrete Diffusion in Large Language and Multimodal Models: A Survey
par: Yu, Runpeng, et autres
Publié: (2025)

Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation
par: Yu, Dian, et autres
Publié: (2026)

FocusVLA: Focused Visual Utilization for Vision-Language-Action Models
par: Zhang, Yichi, et autres
Publié: (2026)

VLA-REPLICA: A Low-Cost, Reproducible Benchmark for Real-World Evaluation of Vision-Language-Action Models
par: Huang, Alex S., et autres
Publié: (2026)

Cross-Hand Latent Representation for Vision-Language-Action Models
par: Jiang, Guangqi, et autres
Publié: (2026)

VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models
par: Wang, Zixuan, et autres
Publié: (2026)

10 Open Challenges Steering the Future of Vision-Language-Action Models
par: Poria, Soujanya, et autres
Publié: (2025)

Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior
par: Niu, Haochen, et autres
Publié: (2026)

NEBULA: Do We Evaluate Vision-Language-Action Agents Correctly?
par: Peng, Jierui, et autres
Publié: (2025)

ROI-Driven Foveated Attention for Unified Egocentric Representations in Vision-Language-Action Systems
par: Sun, Xinhai, et autres
Publié: (2026)

VLSA: Vision-Language-Action Models with Plug-and-Play Safety Constraint Layer
par: Hu, Songqiao, et autres
Publié: (2025)

ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training
par: Yang, Rushuai, et autres
Publié: (2026)

Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding
par: Lin, Tao, et autres
Publié: (2025)

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
par: Sun, Jingwen, et autres
Publié: (2026)

Multi-Level Collaboration in Model Merging
par: Li, Qi, et autres
Publié: (2025)

Encapsulating Knowledge in One Prompt
par: Li, Qi, et autres
Publié: (2024)

Vid-SME: Membership Inference Attacks against Large Video Understanding Models
par: Li, Qi, et autres
Publié: (2025)

DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation
par: Su, Taiyi, et autres
Publié: (2026)

Dexbotic: Open-Source Vision-Language-Action Toolbox
par: Xie, Bin, et autres
Publié: (2025)

FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization
par: Liu, Yicheng, et autres
Publié: (2025)

Causal Scene Narration with Runtime Safety Supervision for Vision-Language-Action Driving
par: Li, Yun, et autres
Publié: (2026)

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
par: Zhong, Yifan, et autres
Publié: (2025)

Formal Synthesis of Controllers for Safety-Critical Autonomous Systems: Developments and Challenges
par: Yin, Xiang, et autres
Publié: (2024)

AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
par: Yu, Wenda, et autres
Publié: (2026)

Concept-Based Dictionary Learning for Inference-Time Safety in Vision Language Action Models
par: Wen, Siqi, et autres
Publié: (2026)

Neural Lineage
par: Yu, Runpeng, et autres
Publié: (2024)

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
par: Lin, Tao, et autres
Publié: (2025)

VLATest: Testing and Evaluating Vision-Language-Action Models for Robotic Manipulation
par: Wang, Zhijie, et autres
Publié: (2024)

DAM-VLA: A Dynamic Action Model-Based Vision-Language-Action Framework for Robot Manipulation
par: Peng, Xiongfeng, et autres
Publié: (2026)

MoTVLA: A Vision-Language-Action Model with Unified Fast-Slow Reasoning
par: Huang, Wenhui, et autres
Publié: (2025)

RynnVLA-002: A Unified Vision-Language-Action and World Model
par: Cen, Jun, et autres
Publié: (2025)

ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models
par: Zhong, Linqing, et autres
Publié: (2026)