ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin 事件

ArcVQ-VAE: A Spherical Vector Quantization Framework with ArcCosine Additive Margin arXiv:2605.13517v2 Announce Type: replace Abstract: Vector Quantized Variational Autoencoder (VQ-VAE) has become a fundamental framework for learning discrete representations in image modeling. However, VQ-VAE models must tokenize entire images using a finite set of codebook vectors, and this capacity limitation restricts their ability to capture rich and diverse representations. In this paper, we propose ArcCos