Back to Discover
cs.CLcs.LG

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling

Alireza Dadgarnia, Soroush Tabesh, Mahdi Nikdan, Michael Helcig, Eldar Kurtic +1 more4/20/2026arxiv

This paper hasn't been summarized yet