← Back to all news
arXiv Machine Learning By Anik Jha

Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for Coding

Read the original on arXiv Machine Learning →

arXiv:2607. 16721v1 Announce Type: new Abstract: The strongest open-weight coding models are mixture-of-experts (MoE) networks: most of their size comes from large pools of "expert" subnetworks, of which only a few act on any token.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 23

You Only Need 2/3 of the Chosen Experts: An Empirical Study of Dynamic Expert Pruning in Fine-Grained MoE LLMs

arXiv:2609.25809v1 Announce Type: new Abstract: Fine-grained mixture-of-experts (MoE) architectures have become a mainstream design for open-weight LLMs, with hundreds of experts and increasingly man...

By Yuanteng Chen, Qiwei Lai, Chen Tianqi, Peisong Wang, Yuantian Shao, Nanxin Zeng, Zhilei Liu, Chuangyi Li, Jing Liu, Jian Cheng
llmsefficiencymultimodalbenchmarks
More like this →
arXiv AI
Sep 17

Higher-order pruning of experts in mixture-of-experts language models

The paper introduces HOPE, a second‑order pruning method for Mixture‑of‑Experts language models that accounts for cooperative interactions between experts. Unlike first‑order methods such as REAP, HOPE derives an objective that provably bounds pruning error and is shown to outperform baselines across three large MoE models, multiple calibration sets, and diverse benchmarks, especially at high pruning rates and on agentic tasks. The results demonstrate that preserving expert interactions allows aggressive compression with minimal performance loss on complex workloads.

By Alex M. Tseng, Prannay Kaul, Luca Zancato, Wei Xia, Stefano Soatto
llmsagentsefficiencybenchmarks
More like this →
arXiv AI
Sep 7

When Load-Balancing Goes Too Far: Expert Pruning in Over-Dispersed Mixture-of-Experts Models

The paper examines how expert pruning—removing low‑importance experts in Mixture‑of‑Experts models—fails when the router is over‑dispersed, a condition caused by aggressive load‑balancing that spreads tokens nearly uniformly across experts. In this regime, traditional importance signals from router probabilities collapse, making perplexity an unreliable predictor of downstream accuracy; for example, the lowest‑perplexity pruning on gpt‑oss‑20B harms mathematical reasoning while the highest‑perplexity pruning preserves it. To address this, the authors introduce Minimax Expert Score Allocation (MESA), a domain‑aware method that iteratively boosts scores for the most affected domain, achieving minimal worst‑case degradation across domains and outperforming baseline pruning strategies on multiple benchmarks while reducing memory usage.

By Berkcan Kapusuzoglu, Connor Pryor, Sangwoo Cho, Supriyo Chakraborty, Shi-Xiong Zhang, Sambit Sahu, Milind Naphade
llmsefficiencybenchmarks
More like this →