Paper

SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMs

Unreadunread

AI summary

arXiv:2606. 09886v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) large language models achieve strong quality with low per-token compute, yet their deployment is often limited by the memory wall: the full expert pool must remain resident to support token-dependent routing.

Reading status

Priority

About this paper

Authors: Yuhao Zhang
Released: 2026-06-10 (29d ago)
Topic: Related to current project
Relation to my work: Read next because SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMs overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: code, strong, text, rect, under, alpha, source, token. Source: arxiv cs.LG (Machine Learning).
arXiv: 2606.09886

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to SHAPE: Coalition-Aware Expert Pruning for Sparse Mixture-of-Experts LLMs. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.