Cite
Notes
Only stored in your browser.
Attribution
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
arXiv 2025
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
Why Not Transform Chat Large Language Models to Non-English?
arXiv 2024
from 3 papers
Chang Su
Hao Yang
Jiahuan Li
Jiajun Chen
Min Zhang
Ming Zhu
Mingkai Jia
Ping Tan
Qian Zhang
Shuaijie She