Paper Notes

标签: MMDiT

此标签下有4条笔记。

  • 2026年5月

    Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation

  • 2026年5月

    Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models

  • 2026年5月

    Qwen-Image-2.0 Technical Report

  • 2025年6月

    Ovis-U1 Technical Report


Created with Quartz v4.5.2 © 2026

  • Source