作者位次 #2/7ICLR 2026Oral· Deep Learning / Generative Models and Autoencoders
Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks
Taishi Nakamura · Satoki Ishikawa · Masaki Kawamura · Okamoto · Daisuke Nohara · Jun Suzuki · Rio Yokota