@article{vqlogitscompressingtheoutputbottleneck,
  title = {VQ-Logits: Compressing the Output Bottleneck of Large Language Models via Vector Quantized Logits},
  author = {Jintian Shao and Hongyi Huang and Jiayi Wu and Yiming Cheng and Zhiyu Wu and You Shan and Mingkai Zheng},
  year = {2025},
  eprint = {2505.10202},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.10202v1},
}