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
arXiv:2512. 13996v3 Announce Type: replace Abstract: Sparse Mixture-of-Experts architectures are essential for scaling model capacity efficiently, yet the standard Top-$k$ routing imposes a rigid sparsity pattern that ignores the intrinsic variance in token difficulty and layer-specific computational needs.
By Can Jin, Hongwu Peng, Mingcan Xiang, Qixin Zhang, Xiangchi Yuan, Amit Hasan, Ohi Dibua, Yifan Gong, Yan Kang, Dimitris N. Metaxas
The paper introduces Ban&Pick, a post‑training, plug‑and‑play routing strategy for Sparse Mixture‑of‑Experts large language models. It identifies and reinforces a small group of highly influential experts while dynamically pruning redundant ones, leading to accuracy gains across math, code, and reasoning benchmarks. Experiments on DeepSeek and Qwen3 show notable performance improvements and a 1.25× inference speedup without retraining or architectural changes.
By Yuanteng Chen, Peisong Wang, Yuantian Shao, Nanxin Zeng, Chang Xu, Jian Cheng
arXiv:2607. 06601v1 Announce Type: cross Abstract: Conditional computation can decouple language model quality from per-token inference cost, yet leading techniques act on a single axis in isolation: Mixture-of-Experts (MoE) sparsifies the FFN, Mixture-of-Depths (MoD) skips whole transformer blocks, and KV-cache quantization compresses attention memory.
By Andrii Balashov, Olena Ponomarova
arXiv:2606. 04101v1 Announce Type: cross Abstract: Large-scale expert parallelism (EP) is becoming pivotal for training and serving frontier MoE models, but it also amplifies device-level expert load imbalance into compute stragglers, token all-to-all bottlenecks, and activation-memory spikes.
By Xinming Wei, Chao Jin, Tuo Dai, Yinmin Zhong, Shan Yu, Chengxu Yang, Bingyang Wu, Zili Zhang, Jing Mai, Qianchao Zhu, Zhouyang Li, Yuliang Liu, Guojie Luo
arXiv:2604. 01622v2 Announce Type: replace Abstract: Diffusion language models (DLMs) enable parallel, non-autoregressive text generation, yet existing DLM mixture-of-experts (MoE) models inherit token-choice (TC) routing from autoregressive systems, leading to load imbalance and rigid computation allocation.
By Shuibai Zhang, Caspian Zhuang, Chihan Cui, Zhihan Yang, Fred Zhangzhi Peng, Yanxin Zhang, Haoyue Bai, Zack Jia, Yang Zhou, Guanhua Chen, Ming Liu
arXiv:2604.23036v2 Announce Type: replace-cross
Abstract: Despite MoE models leading many benchmarks, supervised fine-tuning (SFT) for the MoE architectures remains difficult because its router layer...
By Haoze He, Xingyuan Ding, Xuan Jiang, Xinkai Zou, Alex Cheng, Yibo Zhao, Juncheng Billy Li, Heather Miller
arXiv:2609.13058v1 Announce Type: new
Abstract: Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixture-of-Experts (MoE) models hav...
By Hongyi He, Zhenghao Lin, Xiao Liu, Peng Cheng, Yan Lu, Yeyun Gong
arXiv:2607. 24665v1 Announce Type: cross Abstract: Modern large language models scale successfully by pairing capacity growth with efficiency, keeping per-token and deployment costs under control as capacity grows.
By Yanhao Jia, Jiepeng Wang, Haibin Huang, Chi Zhang, Erik Cambria, Xuelong Li
arXiv:2411. 00918v5 Announce Type: replace-cross Abstract: Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as GPT-OSS, DeepSeek-V3, Llama-4, and Gemini-2.
By Nam V. Nguyen, Thong T. Doan, Luong Tran, Van Nguyen, Quang Pham
arXiv:2608. 12146v1 Announce Type: cross Abstract: Training Mixture-of-Experts (MoE) models for reinforcement learning (RL) couples two load-balancing problems: sequence composition determines dense attention work in each data-parallel microbatch, while token routing determines sparse expert work on expert-parallel ranks.
By Yibo Shen, Xudong Han, Xiaowei Zhu, Gen Li, Zhenxuan Pan
The paper proposes a method for routing requests to a fixed pool of quantized Mixture-of-Experts (MoE) instances, aiming to maximize throughput while respecting a quality‑degradation budget. It introduces Fragility‑Weighted Perplexity (FWP) as a request‑specific risk metric derived from prompt tokens, and uses a window‑level linear program to compute a reduced‑reward score that aligns with the LP optimum. Experiments on Qwen prompts show that FWP‑based allocation improves throughput by 2.5% over request‑agnostic mixing and static configurations.
By Zhenghong Huang, Hongfan Wu, Jiheng Zhang