The paper investigates whether a sparse dictionary can reuse the routing decisions already made by a mixture‑of‑experts (MoE) model. Using the NR‑SAE approach, each routed expert is given a small dictionary that is opened only when the frozen router selects that expert. Experiments on Gemma 4 26B‑A4B show that the expert‑aligned autoencoder explains 51.8 % of the variance in router‑weighted expert outputs, outperforming several control variants and suggesting that the router already encodes useful information that a dictionary would otherwise need to learn.
By Andrew Bistras, Marty Johnson
arXiv:2610.28369v1 Announce Type: cross
Abstract: A growing body of work proposes dynamic expert-skipping methods for Mixture-of-Experts (MoE) models that adjust the number of experts activated per t...
By Jakob Steimle, Thomas Elsken, Daniel Ehrhardt, Lukas Rinder, Daniel Cremers, Xi Wang
IntBMoE introduces a block‑conditioned mixture‑of‑experts that decouples participation, execution, and materialization by combining dense expert composition with sparse block execution. Each internal layer uses a lightweight hypernetwork to merge all expert bases into a single composed expert, while a router selects only a few blocks per token, keeping compute and memory costs low. Experiments on image classification, language modeling, and sequential recommendation demonstrate consistent performance gains, and the model is deployed in AMap’s generative recommendation system, improving UVCTR by 2.4% in online A/B tests.
By Ran Cheng, Longfei Xu, Zheng Liu, Kaikui Liu, Xiangxiang Chu
The paper investigates how to make Mixture-of-Experts (MoE) reward models more interpretable and useful for personalization by focusing on sparsity and diversity regularizers. By keeping the architecture and training data constant, the authors show that conventional MoE reward models learn entangled components that hinder both interpretability and personalization. Introducing a sparse MoE objective reduces entanglement, yielding experts that align with semantic categories and functional strengths, and enables composable, few‑shot personalization with a 25.81‑point improvement over entangled models.
By Yifan Wang, Jinyi Mu, Mayank Jobanputra, Yu Wang, Ji-Ung Lee, Soyoung Oh, Isabel Valera, Vera Demberg
arXiv:2609.36222v1 Announce Type: new
Abstract: Large language models are increasingly expensive to serve. In large-scale serving systems, autoregressive decoding is often bottlenecked by transferrin...
By Ali Abbasi, Justin Shi, Soheil Kolouri
arXiv:2608. 07814v1 Announce Type: cross 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.
By Inesh Chakrabarti, Sourjya Roy, Bowen Bao, Thiago Crepaldi, Spandan Tiwari, Ashish Sirasao
RouterInterp: Understanding Superposed Specialisation in Mixture of Experts Routing proposes the Superposed Specialisation Hypothesis (SSH), suggesting that experts in Sparse Mixture of Experts models specialise in a disjoint union of fine‑grained features rather than a single domain. The paper introduces RouterInterp, a method that identifies Sparse Autoencoder features predictive of routing decisions and generates unified natural‑language explanations. On the gpt‑oss‑20b model, RouterInterp achieves approximately 65% higher detection accuracy than previous token‑statistics based methods, offering a scalable way to explain expert routing.
By Ilya Lasy, Nora Yinuo Cai, Kola Ayonrinde
arXiv:2606. 05538v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models achieve strong performance through conditional computation, but their large parameter footprint poses deployment challenges.
By Haoze He, Xinkai Zou, Xuan Jiang, Xingyuan Ding, Ao Qu, Juncheng Billy Li, Heather Miller
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:2608. 08853v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) routers commonly use the same scores both to select experts and to weight their already-computed outputs.
By Zongfei Li
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
arXiv:2606. 26620v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) have emerged as a powerful tool for decomposing superposed language model representations into sparse and interpretable features.
By XinYang He, Wei Wang, Bing Zhao, Xuan Ren, WenBo Li, WeiXu Qiao, Hu Wei, Lin Qu