paper-with-me

Papers

BLR-MoE: Boosted Language-Routing Mixture of Experts for Domain-Robust Multilingual E2E ASR

2025-01-22 · Guodong Ma, Wenxuan Wang, Lifeng Zhou, Yuting Yang, Yuke Li, Binbin Du

Recently, the Mixture of Expert (MoE) architecture, such as LR-MoE, is often used to alleviate the impact of language confusion on the multilingual ASR (MASR) task. However, it still faces language confusion issues, especially in mismatched domain scenarios. In this paper, we decouple language confusion in LR-MoE into confusion in self-attention and router. To alleviate the language confusion in self-attention, based on LR-MoE, we propose to apply attention-MoE architecture for MASR. In our new architecture, MoE is utilized not only on feed-forward network (FFN) but also on self-attention. In addition, to improve the robustness of the LID-based router on language confusion, we propose expert pruning and router augmentation methods. Combining the above, we get the boosted language-routing MoE (BLR-MoE) architecture. We verify the effectiveness of the proposed BLR-MoE in a 10,000-hour MASR dataset.

📄 PDF Abstract BibTeX arXiv:2501.12602

Code (0)

등록된 구현이 없습니다.

Tasks

Mixture-of-Experts

Methods 이 논문이 사용한 방법론

MoE 설명 없음
Pruning 설명 없음

Similar Papers 제목 키워드 기반

Input Domain Aware MoE: Decoupling Routing Decisions from Task Optimization in Mixture of Experts

2025-10-18 · Yongxiang Hua, Haoyu Cao, Zhou Tao, Bocheng Li 외 arxiv

Sparse Mixture of Experts (sMoE) has become a pivotal approach for scaling large vision-language models, offering substantial capacity while maintaining computational efficiency through dynamic, sparse activation of expe…

Computational Efficiency

RouterRetriever: Routing over a Mixture of Expert Embedding Models

2024-09-04 · Hyunji Lee, Luca Soldaini, Arman Cohan, Minjoon Seo 외

Information retrieval methods often rely on a single embedding model trained on large, general-domain datasets like MSMARCO. While this approach can produce a retriever with reasonable overall performance, they often und…

Information RetrievalLanguage ModelingLanguage ModellingRetrieval

Seeing but Not Thinking: Routing Distraction in Multimodal Mixture-of-Experts

2026-04-09 · Haolei Xu, Haiwen Hong, Hongxing Li, Rui Zhou 외 arxiv

Multimodal Mixture-of-Experts (MoE) models have achieved remarkable performance on vision-language tasks. However, we identify a puzzling phenomenon termed Seeing but Not Thinking: models accurately perceive image conten…

Visual Reasoning

The Illusion of Specialization: Unveiling the Domain-Invariant "Standing Committee" in Mixture-of-Experts Models

2026-01-06 · Yan Wang, Yitao Xu, Nanhan Shen, Jinyan Su 외 arxiv

Mixture of Experts models are widely assumed to achieve domain specialization through sparse routing. In this work, we question this assumption by introducing COMMITTEEAUDIT, a post hoc framework that analyzes routing be…

How Many Experts Are Enough? Towards Optimal Semantic Specialization for Mixture-of-Experts

2025-12-21 · Sumin Park, Noseong Park arxiv

Finding the optimal configuration of Sparse Mixture-ofExperts (SMoE) that maximizes semantic differentiation among experts is essential for exploiting the full potential of MoE architectures. However, existing SMoE frame…