Paper Notes

标签: text-to-image

此标签下有9条笔记。

  • 2026年5月

    Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria

  • 2026年5月

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

  • 2026年5月

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

  • 2026年4月

    FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

  • 2026年4月

    V-GRPO - Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think

  • 2026年1月

    Forge-and-Quench: Enhancing Image Generation for Higher Fidelity in Unified Multimodal Models

  • 2025年9月

    Unified Multimodal Models as Auto-Encoders

  • 2025年8月

    AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning

  • 2025年8月

    Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning


Created with Quartz v4.5.2 © 2026

  • Source