arXiv (Cornell University)
Concept-Centric Token Interpretation for Vector-Quantized Generative Models
May 2025 • Tianze Yang, Yucheng Shi, Mengnan Du, Xuansheng Wu, Qiaoyu Tan, Jing Sun, Ninghao Liu
Vector-Quantized Generative Models (VQGMs) have emerged as powerful tools for image generation. However, the key component of VQGMs -- the codebook of discrete tokens -- is still not well understood, e.g., which tokens are critical to generate an image of a certain concept? This paper introduces Concept-Oriented Token Explanation (CORTEX), a novel approach for interpreting VQGMs by identifying concept-specific token combinations. Our framework employs two methods: (1) a sample-level explanation method that analyze…