arXivJean Lucien Randrianantenaina, Hung Nguyen, Nasib Ullah, Jinbin Zhang, Nilesh Gupta, Inderjit S. Dhillon, Rohit BabbarFri, Oct 30, 2026, 9:17 AM PDT
score 15.3
New pruning method keeps giant AI models accurate at 90% sparsity
Original: Prune Gradually, Adapt Sparsely: Efficient Pruning of Large Language Models at Extreme Sparsity
Source: arxiv.org ↗
Writing ELI5 summary…