Overview

Sparse mixture-of-experts (MoE) models activate only a few experts per token, but uneven routing can overload some experts while others sit idle, slowing training and inference. Training methods use auxiliary balance losses, dynamic router biases or thresholds, hierarchical routing, and quantile- or control-based corrections to spread assignments while preserving specialization. Systems methods predict demand, replicate or migrate experts, and place or schedule them with awareness of GPU speed and network topology; evaluation spans large-scale pretraining, distributed serving, and language and multimodal workloads. The central tension is balancing utilization without degrading task quality or suppressing specialization, while avoiding communication and planning overhead, since token counts alone may not reflect actual compute time.

Latest papers

CardsList

45 papers7 papers in the last four weeks, up 17% on the four weeks before. 0.1% of all new papers.

  1. PMR: MoE Routing with Shared Prototypes and Congestion Pricing

    Nov 14, 2026Wending Wang, Binqi Huang, Ju'an Li +4Mixture-of-Experts ModelsExpert Load Balancing

  2. Fuse-All MoE Inference Kernel with Load Balancing on TPUs

    Nov 13, 2026Rupeng Liu, Bangsheng Tang, Zongwei Zhou +2Mixture-of-Experts InferenceLLM Inference Acceleration

  3. Rethinking MoE Load Balancing as Feedback Control

    Nov 6, 2026Yikun Hou, Alp YurtseverExpert Load BalancingMixture-of-Experts Models

  4. RankLane: Efficient MoE Prefill on Accelerators with Ranked Expert Capacities

    Oct 30, 2026Wentao Ni, Chihao Yu, Hong Cai +4Mixture-of-Experts InferenceLLM Inference Acceleration

  5. Muon Makes the First Mixture-of-Experts Layer Harder to Balance

    Oct 27, 2026Marcos HernanzMixture-of-Experts Language ModelsExpert Load Balancing

  6. 3D-MoE: Complementarity-Guided Hardware-Software Co-Design for MoE Decode on 3D-Stacked NMP

    Oct 19, 2026Yudong Pan, Lian Liu, Shixin Zhao +8Neural Network Hardware AccelerationMixture-of-Experts Inference

  7. BRANCH-MoE: Balance-Aware Tree Routing for Large Embedding Models

    Oct 5, 2026Gang Fu, Adel Javanmard, MohammadHossein Bateni +1Expert Load BalancingMixture-of-Experts Models

  8. CIPHER-MoE: Balancing Efficiency and Routing Fidelity in Trillion-Scale MoE Training

    Oct 5, 2026Jing Li, Jian Meng, Yingmeng Gao +8Expert Load BalancingExpert Routing

  9. ID Balancing: Stable Training of Extremely Sparse MoE via PID-Based Load Control

    Sep 30, 2026Peng Jin, Zihan Qiu, Zekun Wang +8Expert Load BalancingMixture-of-Experts Language Models

  10. TopoEP: Topology-Aware Load Balancing for Expert-Parallel MoE Training

    Sep 28, 2026Jiacheng Zhu, Xie Zhao, Gongming Zhao +3Expert ParallelismExpert Load Balancing

  11. Function Over Form: Distributional Orthogonalization in Mixture-of-Experts with Replica Expert Mechanism

    Sep 26, 2026Jinfan He, Yunzhuo Liu, Kai Zhang +3Mixture-of-Experts Language ModelsMixture of Experts

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

    Sep 3, 2026Berkcan Kapusuzoglu, Connor Pryor, Sangwoo Cho +4Mixture-of-Experts PruningExpert Routing

  13. FreeBalance: Pre-Routing Online Moe Load Balancing via Residual Workload Prediction

    Aug 14, 2026Pengfei Chen, Yize Wu, Shouxu Kuang +2Expert Load BalancingMixture-of-Experts Inference

  14. EasyBalance: Cross-Layer Load Balancing in Distributed MoE Inference

    Aug 8, 2026Yize Wu, Ke Gao, Ling Li +1Expert Load BalancingMixture-of-Experts Inference

  15. REFLEX: Rethinking MoE Inference as Refinement-Aware Compute Allocation in Diffusion Language Models

    Aug 3, 2026Xiang Xia, Cheng Yan, Yiming Zhang +3Expert Load BalancingMixture-of-Experts Inference

  16. Relax Within, Balance Across: Geometry-Guided Load Balancing for Vision-Language Mixture-of-Experts

    Aug 1, 2026Ziang Wu, Peng Jin, Qishen Yin +4Expert Load BalancingVision-Language Models

  17. UltraEP: Unleash MoE Training and Inference on Rack-Scale Nodes with Near-Optimal Load Balancing

    Jun 2, 2026Xinming Wei, Chao Jin, Tuo Dai +10Expert ParallelismExpert Load Balancing

  18. ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving

    May 30, 2026Seokjin Go, Marko Scrbak, Ephrem Wu +2Expert Load BalancingMixture-of-Experts Inference

  19. GEM: GPU-Variability-Aware Expert to GPU Mapping for MoE Systems

    May 19, 2026Sourish Wawdhane, Avinash Kumar, Poulami DasExpert Load BalancingMixture-of-Experts Inference

  20. UB-SMoE: Universally Balanced Sparse Mixture-of-Experts for Resource-adaptive Federated Fine-tuning of Foundation Models

    May 15, 2026Van-Tuan Tran, Hong-Hanh Nguyen-Le, Marco Ruffini +1Expert Load BalancingSparse Mixture-of-Experts

  21. φφ-Balancing for Mixture-of-Experts Training

    May 14, 2026Lizhang Chen, Jonathan Li, Qi Wang +5Expert Load BalancingMirror Descent