arXiv 2610.27598 · cs.AI · 2026-10-20
Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoE
Ermo Hua, Xiangyu Hong, Baiting Wu, Che Jiang, Haozheng Hou, Yicheng Gu, Hanjing Wang, Qirui Zeng and 6 more
TsinghuaC3I
In latest · #298 Added on 2026-10-24
One-line takeaway
Tsinghua C3I studies cross-layer expert sharing in MoE: since experts in different layers are topologically independent yet highly redundant, it empirically compares per-layer Local Experts with inter-layer shared Meta Experts across multiple dimensions for storage and retrieval efficiency.
清华 C3I 研究 MoE 的跨层专家共享：主流 MoE 各层专家拓扑独立但内容高度相似冗余，论文对比“每层独立专家”和“跨层共享的 Meta Expert”，从多个维度实测共享方案在存储和检索效率上的潜力。
Read on arXiv PDF Hugging Face discussion
Topics & disciplines
More on Efficient training & inference
- The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation ▲511
- Scaling Properties of Same-Family On-Policy Distillation ▲327
- Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation ▲250
- On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics ▲205
- Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation ▲181
More on LLMs
- Jeva: System One Models from First Principles 2026-10-13 · ▲371
- Post-Training Leaves Behavioral Shadows on Unrelated Decisions 2026-09-24 · ▲273
- WeVisOne-VL: Unified Visual Perception from Objects to Pixels 2026-10-22 · ▲247
- Thinking Inertia: LLMs Keep Thinking When Told Not To 2026-10-08 · ▲241
- OmniEdu: Open Foundation Models for Learning and Teaching 2026-09-19 · ▲240
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.