Paper Notes

标签: flow-matching

此标签下有9条笔记。

  • 2026年5月

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

  • 2026年4月

    LeapAlign - Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories

  • 2026年4月

    MultiWorld - Scalable Multi-Agent Multi-View Video World Models

  • 2026年3月

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

  • 2026年3月

    Wan-R1 - Verifiable-Reinforcement Learning for Video Reasoning

  • 2026年2月

    GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning

  • 2026年1月

    A Pragmatic VLA Foundation Model

  • 2026年1月

    Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization

  • 2026年1月

    NitroGen: An Open Foundation Model for Generalist Gaming Agents


Created with Quartz v4.5.2 © 2026

  • Source