Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter3

Model risks

Dangerous agent actions4

Impact

Harmful content78Unauthorized actions4Data and privacy leaks27Output manipulation84Availability and reliability16Oversight failure34Increased misuse capability1

System type

AI Agent3Embodied systems and robotics3

Layer

Model layer5Application layer219Training and data layer7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Impact：Unauthorized actionsImpact：Increased misuse capabilityLayer：Model layerClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.05166

    安全动作不等于可行动作：VICS-G 为 VLA 策略做可行未来解码

    提出 VICS-G 可行未来解码，重排冻结 VLA 策略的动作候选

    arXiv
    2610.05166
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    SafeVLA (task-optimized / base), SafeVLA (safety-aligned / safe)
    Abstract作者用可行未来解码重排冻结 VLA 的下一步，并称 VICS-G 降低观测代价且完成率接近策略采样。

    训练无关解码器 VICS 在冻结 VLA 的推理阶段重排动作块，使当前选择带上该动作仍可能留下的安全完成质量。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 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