Paper Notes

标签: RL

此标签下有3条笔记。

  • 2026年4月

    ParetoSlider - Diffusion Models Post-Training for Continuous Reward Control

  • 2026年4月

    World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

  • 2026年3月

    Wan-R1 - Verifiable-Reinforcement Learning for Video Reasoning


Created with Quartz v4.5.2 © 2026

  • Source