Image de couverture de livre

Jailbreaking Embodied LLMs via Action-level Manipulation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Huang, Xinyu, Yang, Qiang, Shen, Leming, Ma, Zijing, Zheng, Yuanqing
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

Towards Privacy-Preserving and Personalized Smart Homes via Tailored Small Language Models
par: Huang, Xinyu, et autres
Publié: (2025)

GPIoT: Tailoring Small Language Models for IoT Program Synthesis and Development
par: Shen, Leming, et autres
Publié: (2025)

BadRobot: Jailbreaking Embodied LLMs in the Physical World
par: Zhang, Hangtao, et autres
Publié: (2024)

Survey of Vision-Language-Action Models for Embodied Manipulation
par: Li, Haoran, et autres
Publié: (2025)

Spatially anchored Tactile Awareness for Robust Dexterous Manipulation
par: Huang, Jialei, et autres
Publié: (2025)

AutoIOT: LLM-Driven Automated Natural Language Programming for AIoT Applications
par: Shen, Leming, et autres
Publié: (2025)

Learning Instruction-Guided Manipulation Affordance via Large Models for Embodied Robotic Tasks
par: Li, Dayou, et autres
Publié: (2024)

Humanoid Agent via Embodied Chain-of-Action Reasoning with Multimodal Foundation Models for Zero-Shot Loco-Manipulation
par: Wen, Congcong, et autres
Publié: (2025)

EmbodiedCoder: Parameterized Embodied Mobile Manipulation via Modern Coding Model
par: Lin, Zefu, et autres
Publié: (2025)

Beyond Model Jailbreak: Systematic Dissection of the "Ten DeadlySins" in Embodied Intelligence
par: Huang, Yuhang, et autres
Publié: (2025)

DaDu-Corki: Algorithm-Architecture Co-Design for Embodied AI-powered Robotic Manipulation
par: Huang, Yiyang, et autres
Publié: (2024)

Motion Before Action: Diffusing Object Motion as Manipulation Condition
par: Su, Yue, et autres
Publié: (2024)

The Shawshank Redemption of Embodied AI: Understanding and Benchmarking Indirect Environmental Jailbreaks
par: Li, Chunyang, et autres
Publié: (2025)

Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
par: Guan, Weifan, et autres
Publié: (2025)

Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
par: Yuan, Yifu, et autres
Publié: (2025)

AR-VRM: Imitating Human Motions for Visual Robot Manipulation with Analogical Reasoning
par: Yang, Dejie, et autres
Publié: (2025)

An Atomic Skill Library Construction Method for Data-Efficient Embodied Manipulation
par: Li, Dongjiang, et autres
Publié: (2025)

JailWAM: Jailbreaking World Action Models in Robot Control
par: Liu, Hanqing, et autres
Publié: (2026)

Language-Grounded Decoupled Action Representation for Robotic Manipulation
par: Weng, Wuding, et autres
Publié: (2026)

Unmasking the Illusion of Embodied Reasoning in Vision-Language-Action Models
par: Xu, Haiweng, et autres
Publié: (2026)

Embodied Robot Manipulation in the Era of Foundation Models: Planning and Learning Perspectives
par: Bai, Shuanghao, et autres
Publié: (2025)

GSR: Learning Structured Reasoning for Embodied Manipulation
par: Hu, Kewei, et autres
Publié: (2026)

LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion
par: Lyu, Jiangran, et autres
Publié: (2026)

DexFormer: Cross-Embodied Dexterous Manipulation via History-Conditioned Transformer
par: Zhang, Ke, et autres
Publié: (2026)

RealMirror: A Comprehensive, Open-Source Vision-Language-Action Platform for Embodied AI
par: Tai, Cong, et autres
Publié: (2025)

Reinforced Embodied Planning with Verifiable Reward for Real-World Robotic Manipulation
par: Bo, Zitong, et autres
Publié: (2025)

CLASS: Contrastive Learning via Action Sequence Supervision for Robot Manipulation
par: Lee, Sung-Wook, et autres
Publié: (2025)

Gaze2Act: Gaze-Conditioned Vision-Language-Action Policies for Interactive Robot Manipulation
par: Zuo, Kuangji, et autres
Publié: (2026)

DM0: An Embodied-Native Vision-Language-Action Model towards Physical AI
par: Yu, En, et autres
Publié: (2026)

Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation
par: Xiao, Junjin, et autres
Publié: (2026)

LAGEA: Language Guided Embodied Agents for Robotic Manipulation
par: Chowdhury, Abdul Monaf, et autres
Publié: (2025)

EHC-MM: Embodied Holistic Control for Mobile Manipulation
par: Wang, Jiawen, et autres
Publié: (2024)

Autoregressive Action Sequence Learning for Robotic Manipulation
par: Zhang, Xinyu, et autres
Publié: (2024)

Empowering Embodied Manipulation: A Bimanual-Mobile Robot Manipulation Dataset for Household Tasks
par: Zhang, Tianle, et autres
Publié: (2024)

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

Towards Dexterous Embodied Manipulation via Deep Multi-Sensory Fusion and Sparse Expert Scaling
par: Sun, Yirui, et autres
Publié: (2026)

Speedup Patch: Learning a Plug-and-Play Policy to Accelerate Embodied Manipulation
par: Wu, Zhichao, et autres
Publié: (2026)

TravExplorer: Cross-Floor Embodied Exploration via Traversability-Aware 3-D Planning
par: Zheng, Han, et autres
Publié: (2026)

HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models
par: Feng, Qiuxuan, et autres
Publié: (2026)

VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis
par: Lang, Xiaolei, et autres
Publié: (2026)