作者位次 #5/16ICML 2026Poster· Deep Learning / Large Language Models
Revisiting Efficiency–Accuracy Scaling in Mixture-of-Experts Architectures
Venmugil Elango · Nidhi Bhatia · Roger Waleffe · Rasoul Shafipour · Tomer Asida · Abhinav Khattar · Nave Assaf · Maximilian Golub · Joseph Guman · Tiyasa Mitra · Ritchie Zhao · Ritika Borkar · Ran Zilberstein · Mostofa Patwary · Mohammad Shoeybi · Bita Darvish Rouhani