Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs 文章

ArXiv CS.CV2026-06-02NEWSen作者: Xin Gao, Cheng Yang, Chufan Shi, Taylor Berg-Kirkpatrick
查看原文 →
关系图谱

Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs · 相关技术

相关技术

Unified Multimodal modelsVQAMMS