1) Restructuring Vector Quantization with the Rotation Trick
2) LG-VQ: Language-Guided Codebook Learning
3) Vector Quantized Wasserstein Auto-Encoder
4) Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%
5) ControlVAR: Exploring Controllable Visual Autoregressive Modeling
6) Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization
7) Balance of Number of Embedding and their Dimensions in Vector Quantization
8) LASERS: LAtent Space Encoding for Representations with Sparsity for Generative Modeling
9) RAQ-VAE: Rate-Adaptive Vector-Quantized Variational Autoencoder
10) HybridFlow: Infusing Continuity into Masked Codebook for Extreme Low-Bitrate Image Compression
11) T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text
12) WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
13) Analyzing And Mitigating Inconsistency In Discrete Audio Tokens For Neural Codec Language Models
#papers #images #audio