EMO: Pretraining Mixture of Experts for Emergent Modularity

• URL: http://arxiv.org/abs/2605.06663v2
• Date: Sun, 10 May 2026 16:27:36 GMT
• Title: EMO: Pretraining Mixture of Experts for Emergent Modularity
• Abstract summary: Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities.<n>MoEs offer a potential alternative by activating only a subset of experts per input, but in practice, restricting inference to a subset of experts for a given domain leads to severe performance degradation.<n>We introduce EMO, an MoE designed for modularity-the independent use and composition of expert subsets-without requiring human-defined priors.
• Score: 23.516967735771555
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are typically deployed as monolithic systems, requiring the full model even when applications need only a narrow subset of capabilities, e.g., code, math, or domain-specific knowledge. Mixture-of-Experts (MoEs) seemingly offer a potential alternative by activating only a subset of experts per input, but in practice, restricting inference to a subset of experts for a given domain leads to severe performance degradation. This limits their practicality in memory-constrained settings, especially as models grow larger and sparser. We introduce EMO, an MoE designed for modularity-the independent use and composition of expert subsets-without requiring human-defined priors. Our key idea is to encourage tokens from similar domains to rely on similar experts. Since tokens within a document often share a domain, EMO restricts them to select experts from a shared pool, while allowing different documents to use different pools. This simple constraint enables coherent expert groupings to emerge during pretraining using document boundaries alone. We pretrain a 1B-active, 14B-total EMO on 1T tokens. As a full model, it matches standard MoE performance. Crucially, it enables selective expert use: retaining only 25% (12.5%) of experts incurs just a 1% (3%) absolute drop, whereas standard MoEs break under the same setting. We further find that expert subsets in EMO specialize at semantic levels (e.g., domains such as math or code), in contrast to the low-level syntactic specialization observed in standard MoEs. Altogether, our results demonstrate a path toward modular, memory-efficient deployment of large, sparse models and open new opportunities for composable architectures.

Related papers

• Share First, Route What Remains: A Unified Framework for Token-Adaptive MoE Computation [49.8459545291965]
  Mixture-of-experts (MoE) models have recently moved beyond routing a fixed number of complete experts.<n>We study this dependency by decomposing sparsely upcycled feed-forward experts into key-value channels.<n>We instantiate it in UniF-MoE, a unified framework for token-adaptive MoE computation.
  arXiv  Detail & Related papers  (2026-08-11T02:40:58Z)
• DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts [56.175408382091796]
  We show that replacing the standard weighted-summation aggregation with structural aggregation expands the expert-combination space without altering the experts or router.<n>We propose DAG-MoE, a sparse MoE framework that employs a lightweight module to automatically learn the optimal aggregation structure among the selected experts.
  arXiv  Detail & Related papers  (2026-05-31T07:08:16Z)
• Mixture of Lookup Key-Value Experts [0.0]
  We present the textbfMixture textbfof textbfLookup textbfKey-textbfValue Experts (textbfMoLKV) model.<n>MoLKV achieves significantly lower validation loss in small-scale evaluations.
  arXiv  Detail & Related papers  (2025-12-10T15:05:55Z)
• Training Matryoshka Mixture-of-Experts for Elastic Inference-Time Expert Utilization [60.309915093470416]
  Matryoshka MoE (M-MoE) is a training framework that instills a coarse-to-fine structure directly into the expert ensemble.<n>Our work paves the way for more practical and adaptable deployments of large-scale MoE models.
  arXiv  Detail & Related papers  (2025-09-30T16:56:44Z)
• Domain-Specific Pruning of Large Mixture-of-Experts Models with Few-shot Demonstrations [48.890534958441016]
  This study investigates domain specialization and expert redundancy in large-scale MoE models.<n>We propose a simple yet effective pruning framework, EASY-EP, to identify and retain only the most relevant experts.<n>Experiments on DeepSeek-R1 and DeepSeek-V3-0324 show that our method can achieve comparable performances and $2.99times$ throughput under the same memory budget with full model with only half the experts.
  arXiv  Detail & Related papers  (2025-04-09T11:34:06Z)
• Autonomy-of-Experts Models [34.82103329222486]
  We propose a novel MoE paradigm in which experts autonomously select themselves to process inputs.<n>AoE is based on the insight that an expert is aware of its own capacity to effectively process a token.<n>Only the top-ranking experts proceed with the forward pass, while the others abort.
  arXiv  Detail & Related papers  (2025-01-22T18:37:08Z)
• MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts [63.67734699877724]
  MoE++ is a general and heterogeneous MoE framework that integrates both Feed-Forward Network(FFN) and zero-computation experts. MoE++ achieves better performance while delivering 1.1-2.1x expert forward throughput compared to a vanilla MoE model of the same size.
  arXiv  Detail & Related papers  (2024-10-09T18:01:27Z)
• BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts [41.83123857437985]
  Training MoEs from scratch in a large-scale regime is prohibitively expensive. We propose BAM (Branch-Attend-Mix), a simple yet effective method that addresses this shortcoming. Our experiments on seed models ranging from 590 million to 2 billion parameters demonstrate that BAM surpasses baselines in both perplexity and downstream task performance.
  arXiv  Detail & Related papers  (2024-08-15T17:19:12Z)
• AdaMoE: Token-Adaptive Routing with Null Experts for Mixture-of-Experts Language Models [14.646419975663367]
  We introduce AdaMoE to realize token-adaptive routing for MoE. AdaMoE does not force each token to occupy a fixed number of null experts. It can reduce average expert load (FLOPs) while achieving superior performance.
  arXiv  Detail & Related papers  (2024-06-19T05:47:10Z)
• Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts [74.40198929049959]
  Large multi-modal models (LMMs) exhibit remarkable performance across numerous tasks. generalist LMMs often suffer from performance degradation when tuned over a large collection of tasks. We propose Omni-SMoLA, an architecture that uses the Soft MoE approach to mix many multimodal low rank experts.
  arXiv  Detail & Related papers  (2023-12-01T23:04:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.