{"ok":true,"article":{"slug":"shape-mutating-expert-compression-lorexperts-and-btexperts-c8424a84","title":"Shape Mutating Expert Compression:LorExperts and BTExperts","url":"https://arxiv.org/abs/2608.07814","canonical":"https://www.aimode.news/article/shape-mutating-expert-compression-lorexperts-and-btexperts-c8424a84","sourceName":"arXiv cs.LG","summary":"arXiv:2608.07814v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) language models deliver high capacity at low per-token compute, but deploying them cheaply requires compressing their many expert weight matrices. Expert pruning (e.g., REAP) and merging reduce cost but sacrifice accuracy and require retraining t…","category":"AI","image":"https://static.arxiv.org/icons/twitter/arxiv-logo-twitter-square.png","lang":"en","publishedAt":"2026-08-11T04:00:00+00:00","createdAt":"2026-08-11T19:09:30.456448+00:00"}}