EMBGuard introduces a novel, MLLM-based safety guardrail that explicitly identifies and explains physical hazards from (visual observation, action) pairs, enabling safer planning for embodied agents.

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 proposes an algorithmic method using conformal prediction to formally certify high-probability safety for Belief-Space Neural Safety Filters (BeliefSF), significantly improving safety guaran…

The paper introduces PaSBench-Video, a comprehensive streaming video benchmark designed to rigorously test multimodal LLMs' ability to issue proactive safety warnings, finding that current models stru…

The paper introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use scenarios.

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…

The paper introduces SABER, a new benchmark that evaluates the operational safety of LLM coding agents in complex, stateful project environments, finding that current models have a high rate of harmfu…

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 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 introduces SafetyDrift, a predictive model that forecasts when AI agents will violate safety protocols by analyzing the cumulative risk across sequences of individually safe actions.

The paper proposes SafeClaw-R, a novel framework that enforces safety as a system-level invariant over the execution graph to mitigate the high safety and security risks inherent in autonomous multi-a…

The paper addresses the difficulty of using general vision-language models (VLMs) for fine-grained driver behavior recognition by creating a new, richly described dataset and demonstrating that fine-t…

Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic ta…

The paper introduces BOA, a novel framework that measures agent safety by exhaustively searching the entire in-budget trajectory space, thereby identifying unsafe behaviors missed by traditional sampl…

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 proposes a novel attack paradigm demonstrating how compromising a single robot in an LLM-controlled multi-robot system can rapidly propagate malicious intent to cause coordinated unsafe acti…

This paper surveys the risks associated with world models, proposing a unified threat model and demonstrating adversarial attacks that show world models require rigorous safety standards comparable to…

The paper introduces a structured multi-level visual perturbation framework to systematically analyze how dependent VLA-based driving behavior is on visual information, revealing uneven visual groundi…

The paper analyzes how runtime safety enforcement impacts the performance of multi-step LLM agents, finding that while safety mechanisms can block unsafe actions, they impose a significant performance…