Concept-Centric Token Interpretation for Vector-Quantized Generative Models
面向概念的标记解释方法用于向量量化生成模型
机构 * School of Computing, University of Georgia(佐治亚大学计算学院) ; Department of Data Science, New Jersey Institute of Technology(新泽西理工学院数据科学系) ; Department of Computer Science, New York University(纽约大学计算机科学系)
AI总结 本文提出CORTEX方法,通过分析标记重要性及代码本来解释VQGMs生成过程,提升模型透明度并应用于图像编辑和特征检测。
Comments 17 pages, 7 figures
Journal ref In Proceedings of the 42nd International Conference on Machine Learning (ICML), PMLR 267:71034-71050, 2025