Notableefficiency inference
Post-Trained MoE Can Skip Half Experts via Self-Distillation
Xingtai Lv, Li Sheng, Kaiyan Zhang, Yichen You, Siyan Gao, Xueheng Luo
- Published
- May 18, 2026 — 16:50 UTC
By Callan Zhang · May 18, 2026 · Editorial standards →
Summarised from the primary source with AI assistance under human editorial oversight. Turing Wire is not a primary source — read the original for the authoritative account.
Source: arXiv cs.CL