Paper Notes

标签: Unified-Multimodal-Model

此标签下有2条笔记。

  • 2026年4月

    Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

  • 2025年12月

    Tuna: Taming Unified Visual Representations for Native Unified Multimodal Models


Created with Quartz v4.5.2 © 2026

  • Source