arXivYanbei Chen, Anirudh Goyal, Raghuraman KrishnamoorthiWed, Sep 30, 2026, 10:53 AM PDT
score 17.1
Scaling Law Predicts Benefits of Looping AI Models With Sparse Experts
Original: Scaling Laws for Looped Mixture of Experts
Source: arxiv.org ↗
Writing ELI5 summary…