Cover Image

Altered Thoughts, Altered Actions: Probing Chain-of-Thought Vulnerabilities in VLA Robotic Manipulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Trinh, Tuan Duong, Akhtar, Naveed, Azam, Basim
Format:	Preprint
Published:	2026
Subjects:	Robotics Artificial Intelligence Machine Learning 68T40 I.2.9; I.2.6
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

ExpReS-VLA: Specializing Vision-Language-Action Models Through Experience Replay and Retrieval
by: Syed, Shahram Najam, et al.
Published: (2025)

LLM-Guided Task- and Affordance-Level Exploration in Reinforcement Learning
by: Luijkx, Jelle, et al.
Published: (2025)

Autonomous Multi-Robot Infrastructure for AI-Enabled Healthcare Delivery and Diagnostics
by: Kalaivanan, Nakhul, et al.
Published: (2025)

RoboGrind: Intuitive and Interactive Surface Treatment with Industrial Robots
by: Alt, Benjamin, et al.
Published: (2024)

FT-NCFM: An Influence-Aware Data Distillation Framework for Efficient VLA Models
by: Chen, Kewei, et al.
Published: (2025)

Evaluating Model-Agnostic Meta-Learning on MetaWorld ML10 Benchmark: Fast Adaptation in Robotic Manipulation Tasks
by: Atamuradov, Sanjar
Published: (2025)

ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models
by: Chen, Kewei, et al.
Published: (2026)

CulinaryCut-VLAP: A Vision-Language-Action-Physics Framework for Food Cutting via a Force-Aware Material Point Method
by: Koh, Hyunseo, et al.
Published: (2026)

Learning to Walk in Costume: Adversarial Motion Priors for Aesthetically Constrained Humanoids
by: Alvarez, Arturo Flores, et al.
Published: (2025)

Connectivity-Aware Representations for Constrained Motion Planning via Multi-Scale Contrastive Learning
by: Jeon, Suhyun, et al.
Published: (2026)

PhAIL: A Real-Robot VLA Benchmark and Distributional Methodology
by: Arkhangelskiy, Sergey
Published: (2026)

ElasticFlow: One-Step Physics-Consistent Policy with Elastic Time Horizons for Language-Guided Manipulation
by: Chen, Kewei, et al.
Published: (2026)

Preventing Robotic Jailbreaking via Multimodal Domain Adaptation
by: Marchiori, Francesco, et al.
Published: (2025)

DRAE: Dynamic Retrieval-Augmented Expert Networks for Lifelong Learning and Task Adaptation in Robotics
by: Long, Yayu, et al.
Published: (2025)

Action-Aware Pro-Active Safe Exploration for Mobile Robot Mapping
by: İşleyen, Aykut, et al.
Published: (2025)

Magnet-Based Soft Robotic Skin Using a 3D-Printed Multi-Lattice Structure and CNN-Based Tactile Super-Resolution
by: Bang, Yunseong, et al.
Published: (2026)

Atomic-Probe Governance for Skill Updates in Compositional Robot Policies
by: Qin, Xue, et al.
Published: (2026)

UAIbot: Beginner-friendly web-based simulator for interactive robotics learning and research
by: Brayan, Johnata, et al.
Published: (2025)

Learning to Generate Pointing Gestures in Situated Embodied Conversational Agents
by: Deichler, Anna, et al.
Published: (2025)

To Whom are You Talking? A Deep Learning Model to Endow Social Robots with Addressee Estimation Skills
by: Mazzola, Carlo, et al.
Published: (2023)

RoboMoRe: LLM-based Robot Co-design via Joint Optimization of Morphology and Reward
by: Fang, Jiawei, et al.
Published: (2025)

Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features
by: Chahine, Makram, et al.
Published: (2024)

Learning coordinated badminton skills for legged manipulators
by: Ma, Yuntao, et al.
Published: (2025)

CaMeRL: Collision-Aware and Memory-Enhanced Reinforcement Learning for UAV Navigation in Multi-Scale Obstacle Environments
by: Hong, Hong, et al.
Published: (2026)

Affordance-Aware Interactive Decision-Making and Execution for Ambiguous Instructions
by: Xu, Hengxuan, et al.
Published: (2026)

ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow Matching
by: Qiu, Xiaotian, et al.
Published: (2026)

Pushing the Limits of Cross-Embodiment Learning for Manipulation and Navigation
by: Yang, Jonathan, et al.
Published: (2024)

Human-Aligned Skill Discovery: Balancing Behaviour Exploration and Alignment
by: Hussonnois, Maxence, et al.
Published: (2025)

Think, Act, Learn: A Framework for Autonomous Robotic Agents using Closed-Loop Large Language Models
by: Menon, Anjali R., et al.
Published: (2025)

MVB-Grasp: Minimum-Volume-Box Filtering of Diffusion-based Grasps for Frontal Manipulation
by: Poudel, Bibek, et al.
Published: (2026)

SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation
by: Huang, Mu, et al.
Published: (2026)

SaiVLA-0: Cerebrum--Pons--Cerebellum Tripartite Architecture for Compute-Aware Vision-Language-Action
by: Shi, Xiang, et al.
Published: (2026)

DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments
by: Jia, Yufei, et al.
Published: (2025)

LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios
by: Yao, Huaiyuan, et al.
Published: (2025)

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization
by: Zhou, Xueyang, et al.
Published: (2025)

Emergence of Goal-Directed Behaviors via Active Inference with Self-Prior
by: Kim, Dongmin, et al.
Published: (2025)

UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms
by: Jia, Yufei, et al.
Published: (2026)

GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning
by: Jia, Yufei, et al.
Published: (2026)

MonoForce: Self-supervised Learning of Physics-informed Model for Predicting Robot-terrain Interaction
by: Agishev, Ruslan, et al.
Published: (2023)

Newtonian and Lagrangian Neural Networks: A Comparison Towards Efficient Inverse Dynamics Identification
by: Trinh, Minh, et al.
Published: (2025)