paper-with-me

Papers

Omni-Router: Sharing Routing Decisions in Sparse Mixture-of-Experts for Speech Recognition

2025-07-08 · Zijin Gu, Tatiana Likhomanenko, Navdeep Jaitly arxiv

Mixture-of-experts (MoE) architectures have expanded from language modeling to automatic speech recognition (ASR). Traditional MoE methods, such as the Switch Transformer, route experts independently within each layer. Our analysis reveals that routers in most layers make expert choices that are not strongly correlated with the choices of the routers in other layers. To increase the cooperation between experts in different layers and encourage greater specialization, we use a shared router across different MoE layers. We call this model Omni-router Transformer. Extensive experiments on a large-scale pseudo-labeled dataset and evaluations across 10 diverse, out-of-domain ASR benchmarks demonstrate that the Omni-router Transformer is able to achieve lower training loss and consistently outperform dense and Switch Transformer models, reducing average word error rates by 11.2% and 8.2%, respectively, while providing structured expert usage and improved robustness to diverse data.

📄 PDF Abstract BibTeX arXiv:2507.05724

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Recognition

Similar Papers 제목 키워드 기반

OmniRouter: Budget and Performance Controllable Multi-LLM Routing

2025-02-27 · Kai Mei, Wujiang Xu, Shuhang Lin, Yongfeng Zhang

Large language models (LLMs) deliver superior performance but require substantial computational resources and operate with relatively low efficiency, while smaller models can efficiently handle simpler tasks with fewer r…

AI AgentMathematical ReasoningScheduling

Routers Learn the Geometry of Their Experts: Geometric Coupling in Sparse Mixture-of-Experts

2026-05-12 · Sagi Ahrac, Noya Hochwald, Mor Geva arxiv

Sparse Mixture-of-Experts (SMoE) models enable scaling language models efficiently, but training them remains challenging, as routing can collapse onto few experts and auxiliary load-balancing losses can reduce specializ…

Routing by Analogy: kNN-Augmented Expert Assignment for Mixture-of-Experts

2026-01-05 · Boxuan Lyu, Soichiro Murakami, Hidetaka Kamigaito, Peinan Zhang arxiv

Mixture-of-Experts (MoE) architectures scale large language models efficiently by employing a parametric ``router'' to dispatch tokens to a sparse subset of experts. Typically, this router is trained once and then frozen…

PROTEUS: SLA-Aware Routing via Lagrangian RL for Multi-LLM Serving Systems

2026-01-27 · Amit Singh Bhatti, Vishal Vaddina, Dagnachew Birru arxiv

Production LLM deployments serve diverse workloads where cost and quality requirements vary by customer tier, time of day, and query criticality. Model serving systems accept latency SLOs directly. LLM routers do not. Th…

HeadRouter: Dynamic Head-Weight Routing for Task-Adaptive Audio Token Pruning in Large Audio Language Models

2026-04-26 · Peize He, Yaodi Luo, Xiaoqian Liu, Xuyang Liu 외 arxiv

Recent large audio language models (LALMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet incur high inference costs. Token compression is an effective method that directly reduces …