Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter2

Model risks

Reward hacking1

System component

Guardrails and judges15Monitors7Permissions and sandboxing5Image generation1Multimodal3
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.
Model risks：Reward hackingSystem component：Image generationClear all

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

  1. DefensesarXiv 2610.02967

    用偏好奖励与评分标准奖励组合后训练前沿文生图模型

    组合偏好奖励与评分标准奖励后训练文生图模型以抑制奖励作弊

    arXiv
    2610.02967
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    FLUX.2-dev, Ideogram-4
    Abstract组合奖励后训练 FLUX.2-dev 与 Ideogram-4，并报告高于基座的胜率与 Elo。

    作者给出一套开放域文生图后训练配方：把人类偏好奖励和 prompt 条件的 rubric 奖励合在一起，而不是换一个新优化器。问题是单一奖励盖不住用户意图。偏好模型能看整体观感，但对“是否实现每个要求”这类稀疏属性不敏感。

    Paper analysisRead analysis
You have reached the end