Paper Notes

标签: multimodal-generation

此标签下有5条笔记。

  • 2026年5月

    Lance: Unified Multimodal Modeling by Multi-Task Synergy

  • 2026年5月

    UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors

  • 2026年4月

    Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning

  • 2025年10月

    Video-As-Prompt: Unified Semantic Control for Video Generation

  • 2025年6月

    OmniGen2: Towards Instruction-Aligned Multimodal Generation


Created with Quartz v4.5.2 © 2026

  • Source