Paper Notes

标签: reward-modeling

此标签下有5条笔记。

  • 2026年5月

    AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment

  • 2026年5月

    Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models

  • 2026年5月

    EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics

  • 2026年5月

    Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models

  • 2026年5月

    RewardHarness: Self-Evolving Agentic Post-Training


Created with Quartz v4.5.2 © 2026

  • Source