Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 7 papers
Filter3

Model risks

Dangerous agent actions3Inappropriate refusal3

Impact

Harmful content3Unauthorized actions3

System type

AI Agent5Embodied systems and robotics3

Layer

Model layer5

System component

MCP and skills3Memory5Monitors15Reasoning chains10Vision5Embeddings0Multimodal7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
System component：VisionSystem component：EmbeddingsSystem component：MultimodalClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. Risky behaviorarXiv 2609.38971

    研究测量并预测具身 VLM 规划器中任务的拒答可变性

    测量并预测具身 VLM 规划器的任务拒答可变性

    arXiv
    2609.38971
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    gemini-robotics-er-2-preview, gemini-robotics-er-1.6-preview
    Abstract日常物体能翻转一部分已给出的拒答，可翻转程度取决于任务且可被本地代理预测。

    作者测量 constitution 守护的具身 VLM 规划器：一次拒答在只往场景里放一个日常物体之后还保不保持得住，并把这种易翻转程度称为任务的 malleability。

    Paper analysisRead analysis
  2. Risky behaviorarXiv 2609.35291

    窄域多模态微调可诱发涌现性失配，覆盖 15 个视觉语言模型

    证明无显式危害的图文窄微调可诱发跨任务涌现未对齐

    arXiv
    2609.35291
    Published
    Layer
    Model layer
    Setting
    Browser and computer use
    Evaluated models
    GPT-4o, GPT-4.1, Gemini 2.5 and others15
    Abstract证实窄多模态微调可引发全面的多渠道未对齐行为转变，揭示了后训练阶段对齐被隐蔽重塑的安全隐患。

    论文系统探究了视觉-语言模型中由窄任务微调诱发的跨模态涌现未对齐（Emergent Misalignment, EM）现象。

    Paper analysisRead analysis
  3. Risky behaviorarXiv 2609.35922

    VoxParity 评测：语音智能体在需要听声判断时仍按文字行事

    提出 VoxParity，固定转写只改音频，评测语音智能体是否按行业规则改工具调用

    arXiv
    2609.35922
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    MiMo-V2.6-Pro, gemini-3.7-flash, Qwen3.8-Omni and others15
    AbstractVoxParity 用固定转写的音频对比和 words-only null，测量语音智能体是否按所听内容改变工具调用。

    VoxParity 测量语音智能体在词语不变、只有声音改变时，是否按行业规则改它所执行的工具调用。

    Paper analysisRead analysis
  4. Risky behaviorarXiv 2609.06991

    AV-SafetyBench：面向文本到音视频生成的安全基准

    提出 AV-SafetyBench 评测文生音视频模型的不安全生成

    arXiv
    2609.06991
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LTX-2.3, Ovi-1.1, JavisDiT++ and others7
    AbstractAV-SafetyBench 用三视角评五个 T2AV 模型，显示只看视频会漏掉音频与联合风险。

    AV-SafetyBench 是面向文本生成音视频（T2AV）的安全基准：一条提示词同时规定画面和音频，评测同时看两轨以及它们的交互。作者要测的是，不安全含义不只出现在画面上：它可以主要由语音或声音承载，也可以只有两轨合起来才成立。T2VSafetyBench 不评音频，TTA-Bench 不评与画面的交互，作者认为二者都盖不住这些路径。

    Paper analysisRead analysis
  5. Risky behaviorarXiv 2604.12447

    HazardArena：面向 VLA 模型的语义安全评测基准

    提出 HazardArena 基准，用孪生场景评测 VLA 的语义安全

    arXiv
    2604.12447
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    OpenVLA-OFT, π0, NORA and others4
    Abstractsafe-only 微调提升良性执行，也提升匹配不安全孪生上的危险完成。

    HazardArena 评测 VLA 在运动要求不变时，能否因语义风险而停手。

    Paper analysisRead analysis
You have reached the end