相关论文: HomeSafeBench: A Benchmark for Embodied Vision-Lan…
The rapid evolution of embodied agents has accelerated the deployment of household robots in real-world environments. However, unlike structured industrial settings, household spaces introduce unpredictable safety risks, where system…
With the integration of large language models (LLMs), embodied agents have strong capabilities to understand and plan complicated natural language instructions. However, a foreseeable issue is that those embodied agents can also flawlessly…
Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have garnered substantial attention, MLLM-based embodied agents…
Flawed planning from VLM-driven embodied agents poses significant safety hazards, hindering their deployment in real-world household tasks. However, existing static, non-interactive evaluation paradigms fail to adequately assess risks…
The integration of vision-language models (VLMs) is driving a new generation of embodied agents capable of operating in human-centered environments. However, as deployment expands, these systems face growing safety risks, particularly when…
Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning…
Vision-Language Models (VLMs) empower embodied agents to execute complex instructions, yet they remain vulnerable to contextual safety risks where benign commands become hazardous due to subtle environmental states. Existing safeguards…
Large vision-language models (LVLMs) exhibit remarkable capabilities in cross-modal tasks but face significant safety challenges, which undermine their reliability in real-world applications. Efforts have been made to build LVLM safety…
The rapid evolution of Large Multimodal Models (LMMs) has enabled agents to perform complex digital and physical tasks, yet their deployment as autonomous decision-makers introduces substantial unintentional behavioral safety risks.…
Large Language Models (LLMs) exhibit substantial promise in enhancing task-planning capabilities within embodied agents due to their advanced reasoning and comprehension. However, the systemic safety of these agents remains an underexplored…
Vision-Language Models (VLMs) show great promise for autonomous driving, but their suitability for safety-critical scenarios is largely unexplored, raising safety concerns. This issue arises from the lack of comprehensive benchmarks that…
Recent advances in vision-language models (VLMs) have accelerated their application to indoor safety hazards assessment. However, existing benchmarks suffer from three fundamental limitations: (1) heavy reliance on synthetic datasets…
Artificial Intelligence (AI) is revolutionizing scientific research, yet its growing integration into laboratory environments presents critical safety challenges. Large language models (LLMs) and vision language models (VLMs) now assist in…
Recent advances in Vision-Language Models (VLMs) facilitate a new class of embodied AI systems, where these models are integrated into physical platforms, e.g. robots and autonomous vehicles, to interpret visual scenes and execute natural…
As large language models (LLMs) are increasingly deployed as agents, their integration into interactive environments and tool use introduce new safety challenges beyond those associated with the models themselves. However, the absence of…
Large vision-language model (LVLM)-based web agents are emerging as powerful tools for automating complex online tasks. However, when deployed in real-world environments, they face serious security risks, motivating the design of security…
The robust safety of Vision-Language Large Models (VLLMs) against joint multilingual and multimodal threats remains severely underexplored. Current benchmarks typically isolate these dimensions, being either multilingual but text-only, or…
The rapid advancement of vision-language models (VLMs) has brought a lot of attention to their safety alignment. However, existing methods have primarily focused on model undersafety, where the model responds to hazardous queries, while…
Scalable AI agents training relies on interactive environments that faithfully simulate the consequences of agent actions. Manually crafted environments are expensive to build, brittle to extend, and fundamentally limited in diversity. A…
Recent advances in vision-language models (VLMs) have enabled impressive generalization across diverse video understanding tasks under zero-shot settings. However, their capabilities in high-stakes industrial domains-where recognizing both…