Paper Notes

标签: GRPO

此标签下有10条笔记。

  • 2026年5月

    Breaking Dual Bottlenecks: Evolving Unified Multimodal Models into Self-Adaptive Interleaved Visual Reasoners

  • 2026年5月

    Flow-OPD: On-Policy Distillation for Flow Matching Models

  • 2026年5月

    RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO

  • 2026年4月

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

  • 2026年3月

    From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

  • 2026年3月

    Gen-Searcher: Reinforcing Agentic Search for Image Generation

  • 2026年3月

    Manifold-Aware Exploration for Reinforcement Learning in Video Generation

  • 2026年3月

    VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward

  • 2026年3月

    Wan-R1 - Verifiable-Reinforcement Learning for Video Reasoning

  • 2026年1月

    NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation


Created with Quartz v4.5.2 © 2026

  • Source