This paper introduces TRAP, an adversarial attack that demonstrates how physical patches can hijack the Chain-of-Thought (CoT) reasoning process in Vision-Language-Action (VLA) models, forcing them to…

VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vi…

TempoVLA is a novel Vision-Language-Action model that enables controllable execution speed for robot manipulation by explicitly conditioning the policy on the desired speed.

The paper proposes CTRL-STEER, a closed-loop framework that adaptively adjusts intervention strength to stabilize concept regulation and improve task success in Vision-Language-Action models without r…

This paper demonstrates that reasoning-enabled Vision-Language-Action (VLA) models for autonomous driving are highly vulnerable to realistic input perturbations, significantly compromising both reason…

GSAM introduces a generalizable and safe robotic framework for articulated object manipulation, significantly improving success rates and reducing variability across diverse tasks by integrating commo…

BORA is an offline-to-online RL framework that enhances dexterous VLA models for real-world robotics by using an action-conditioned critic and a lightweight residual adaptation mechanism to correct ex…

The paper proposes Continuous Reasoning for Vision-Language-Action (VLA) models, arguing that effective reasoning must be a shared, verifiable internal latent space rather than discrete text tokens, l…

The paper introduces Center-of-Pressure (CoP), a physics-grounded tactile representation that enables robust zero-shot sim-to-real transfer for complex, contact-rich manipulation tasks.

The paper introduces a diagnostic framework to determine if World-Action Models (WAMs) provide genuinely actionable behavioral improvements beyond simply achieving task success, finding that WAMs ofte…

DeMaVLA is a generalizable Vision-Language-Action foundation model designed for deformable object manipulation, achieving strong real-world performance on folding tasks by leveraging large-scale real-…

The paper demonstrates that fine-tuning safety guard models on benign data can catastrophically collapse their safety alignment, proposing Fisher-Weighted Safety Subspace Regularization (FW-SSR) to ac…

The paper identifies a 'deployment-safety gap' in Vision-Language-Action (VLA) policies, showing that identical model checkpoints can result in physically different and unsafe robot actions due to act…

This paper presents the first systematic study of membership inference attacks (MIAs) against Vision-Language-Action (VLA) models, demonstrating that these models are highly vulnerable to privacy brea…

The paper establishes a theoretical information-theoretic bound proving that for Vision-Language-Action (VLA) models, capability and robustness cannot both be arbitrarily high, quantifying the trade-o…

The paper proposes Completion at the Boundary (CaB), a method that predicts event-local completion objects using Boundary-Phase Tokens to improve the reliability of multi-step, handoff-heavy tasks for…

The paper introduces TouchSafeBench, a physics-grounded benchmark, to evaluate collision grounding—the ability to predict robot-human collisions—and finds that current Vision-Language Models (VLMs) ar…

The paper demonstrates that many instruction-tuned language models suffer from 'silent commitment failure,' meaning they can produce confidently incorrect outputs without any warning signal, and intro…

This survey provides a comprehensive, structured review of safety research in Embodied AI, analyzing attacks and defenses across the entire embodied pipeline to guide the development of safe, robust,…

The paper provides a holistic threat model for LLM-enabled robotic systems by analyzing how conventional, adversarial, and conversational threats propagate across the entire perception-planning-actuat…