作者位次 #2/8ICML 2026Poster· Deep Learning / Large Language Models
Beyond Sunk Costs: Boosting LLM Pre-training Efficiency via Orthogonal Growth of Mixture-of-Experts
Ruizhe Wang · Yucheng Ding · Xiao Liu · Yaoxiang Wang · Peng CHENG · Baining Guo · Zheng-Jun Zha · Yeyun Gong