Paper Notes

标签: SigLIP2

此标签下有2条笔记。

  • 2025年12月

    Tuna: Taming Unified Visual Representations for Native Unified Multimodal Models

  • 2025年6月

    UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation


Created with Quartz v4.5.2 © 2026

  • Source