Imagen de Portada

On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Guo, Jianing, Wu, Zhenhong, Tu, Chang, Ma, Yiyao, Kong, Xiangqi, Liu, Zhiqian, Ji, Jiaming, Zhang, Shuning, Chen, Yuanpei, Chen, Kai, Dou, Qi, Yang, Yaodong, Liu, Xianglong, Zhao, Huijie, Lv, Weifeng, Li, Simin
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
por: Zhang, Borong, et al.
Publicado: (2025)

VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
por: Zhang, Borong, et al.
Publicado: (2025)

Object-Centric Dexterous Manipulation from Human Motion Data
por: Chen, Yuanpei, et al.
Publicado: (2024)

Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization
por: Li, Simin, et al.
Publicado: (2023)

Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
por: Li, Simin, et al.
Publicado: (2025)

Towards Robust Protective Perturbation against DeepFake Face Swapping
por: Yao, Hengyang, et al.
Publicado: (2025)

Dexterous Non-Prehensile Manipulation for Ungraspable Object via Extrinsic Dexterity
por: Wang, Yuhan, et al.
Publicado: (2025)

Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game
por: Li, Simin, et al.
Publicado: (2023)

RedVLA: Physical Red Teaming for Vision-Language-Action Models
por: Zhang, Yuhao, et al.
Publicado: (2026)

A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
por: Zhong, Yifan, et al.
Publicado: (2025)

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
por: Li, Simin, et al.
Publicado: (2025)

Photomolecular Effect: Visible Light Absorption at Water-Vapor Interface
por: Tu, Yaodong, et al.
Publicado: (2022)

DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping
por: Zhong, Yifan, et al.
Publicado: (2025)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
por: Fang, Hao, et al.
Publicado: (2024)

Staircase Recognition and Location Based on Polarization Vision
por: Kong, Weifeng, et al.
Publicado: (2025)

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation
por: Yang, Hao, et al.
Publicado: (2026)

CDF-Glove: A Cable-Driven Force Feedback Glove for Dexterous Teleoperation
por: Liang, Huayue, et al.
Publicado: (2026)

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
por: Ying, Zonghao, et al.
Publicado: (2024)

NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations
por: Nan, Junjie, et al.
Publicado: (2025)

Accelerating Robotic Reinforcement Learning with Agent Guidance
por: Chen, Haojun, et al.
Publicado: (2026)

CABTO: Context-Aware Behavior Tree Grounding for Robot Manipulation
por: Cai, Yishuai, et al.
Publicado: (2026)

Towards Robust Deep Reinforcement Learning against Environmental State Perturbation
por: Wang, Chenxu, et al.
Publicado: (2025)

Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models
por: Zhu, Tinghui, et al.
Publicado: (2024)

Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark
por: Fei, Zekun, et al.
Publicado: (2024)

Multi-Modality Co-Learning for Efficient Skeleton-based Action Recognition
por: Liu, Jinfu, et al.
Publicado: (2024)

35‐2: Research on Anti‐WiFi Noise Interference Technology for Display Driver IC
por: Qianqian Lv, et al.
Publicado: (2025)

Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation
por: Ma, Yiyao, et al.
Publicado: (2025)

Robustness of Vision Foundation Models to Common Perturbations
por: Liu, Hongbin, et al.
Publicado: (2026)

DebGCD: Debiased Learning with Distribution Guidance for Generalized Category Discovery
por: Liu, Yuanpei, et al.
Publicado: (2025)

Predicting Financial Distress With ESG‐Driven Deep Learning and Risk‐Based Stratification
por: Jiaming Liu, et al.
Publicado: (2025)

Robust Machine Learning for Regulatory Sequence Modeling under Biological and Technical Distribution Shifts
por: Yang, Yiyao
Publicado: (2026)

Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
por: Liu, Qianmei, et al.
Publicado: (2024)

Improving SAM for Camouflaged Object Detection via Dual Stream Adapters
por: Liu, Jiaming, et al.
Publicado: (2025)

Option‐Implied Ambiguity and Equity Return Predictability
por: Yanchu Liu, et al.
Publicado: (2024)

Communication-Efficient Desire Alignment for Embodied Agent-Human Adaptation
por: Wang, Yuanfei, et al.
Publicado: (2025)

Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations
por: Hu, Hanjiang, et al.
Publicado: (2023)

Attacking Cooperative Multi-Agent Reinforcement Learning by Adversarial Minority Influence
por: Li, Simin, et al.
Publicado: (2023)

How Emotion Shapes the Behavior of LLMs and Agents: A Mechanistic Study
por: Sun, Moran, et al.
Publicado: (2026)

Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling
por: Wei, Ruofeng, et al.
Publicado: (2024)

Elevating Skeleton-Based Action Recognition with Efficient Multi-Modality Self-Supervision
por: Wei, Yiping, et al.
Publicado: (2023)