Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter3

Defense type

Model hardening5Inference-time intervention4Watermarking and provenance1

System type

Models and APIs6

Attack surface / entry point

Images, audio and video3

Layer

Model layer3Training and data layer3

System component

Guardrails and judges11Reasoning chains11Fine-tuning and open weights18Vision12Audio6Image generation9Multimodal27
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.
Defense type：Model hardeningDefense type：Watermarking and provenanceSystem component：AudioClear all

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

  5. DefensesarXiv 2609.12623

    SteerDuplex：可操控的全双工语音对话模型

    提出 SteerDuplex，用监督微调与两阶段强化学习提升全双工语音对话可控性

    arXiv
    2609.12623
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    SteerDuplex-SFT, SteerDuplex-RL
    AbstractSteerDuplex 用 SFT 提升语音可控，用两阶段 RL 改时序，并记录奖励黑客。

    SteerDuplex 是基于 Moshi 的全双工语音模型，目标是在保留轮替、打断和一般任务能力的同时，按用户指令改变内容与发声。

    Paper analysisRead analysis
  6. DefensesarXiv 2608.18607

    VA-Judger：面向联合视频-音频生成的人类偏好反馈奖励建模

    提出 VA-Judger，用人类偏好训练联合音视频奖励模型

    arXiv
    2608.18607
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    VA-Judger, LTX-2 + VA-Judger
    AbstractVA-Judger 用易到难的人类偏好学习做联合音视频奖励，并用于 LTX-2 后训练。

    VA-Judger 是面向联合音视频生成的思维链全模态奖励模型，用来替代由分维度专家指标拼成的强化学习奖励。

    Paper analysisRead analysis
You have reached the end