paper-with-me

Papers

MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts

2024-01-08 · Maciej Pióro, Kamil Ciebiera, Krystian Król, Jan Ludziejewski, Michał Krutul, Jakub Krajewski, Szymon Antoniak, Piotr Miłoś, Marek Cygan, Sebastian Jaszczur

State Space Models (SSMs) have become serious contenders in the field of sequential modeling, challenging the dominance of Transformers. At the same time, Mixture of Experts (MoE) has significantly improved Transformer-based Large Language Models, including recent state-of-the-art open models. We propose that to unlock the potential of SSMs for scaling, they should be combined with MoE. We showcase this on Mamba, a recent SSM-based model that achieves remarkable performance. Our model, MoE-Mamba, outperforms both Mamba and baseline Transformer-MoE. In particular, MoE-Mamba reaches the same performance as Mamba in $2.35\times$ fewer training steps while preserving the inference performance gains of Mamba against Transformer.

📄 PDF Abstract BibTeX arXiv:2401.04081

Code (1)

llm-random/llm-random 공식 구현 pytorch

Tasks

MambaMixture-of-ExpertsState Space Models

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

OTCE: Hybrid SSM and Attention with Cross Domain Mixture of Experts to construct Observer-Thinker-Conceiver-Expresser

2024-06-24 · Jingze Shi, Ting Xie, Bingheng Wu, Chunjun Zheng 외

Recent research has shown that combining Mamba with Transformer architecture, which has selective state space and quadratic self-attention mechanism, outperforms using Mamba or Transformer architecture alone in language …

Language ModelingLanguage ModellingMambaMixture-of-Experts+1

Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation

2025-07-08 · Szymon Płotka, Gizem Mert, Maciej Chrabaszcz, Ewa Szczurek 외 arxiv

In recent years, artificial intelligence has significantly advanced medical image segmentation. Nonetheless, challenges remain, including efficient 3D medical image processing across diverse modalities and handling data …

Medical Image Segmentation

MoEMambaMIL: Structure-Aware Selective State Space Modeling for Whole-Slide Image Analysis

2026-03-06 · Dongqing Xie, Yonghuang Wu arxiv

Whole-slide image (WSI) analysis is challenging due to the gigapixel scale of slides and their inherent hierarchical multi-resolution structure. Existing multiple instance learning (MIL) approaches often model WSIs as un…

Multiple Instance Learning

Mammo-Mamba: A Hybrid State-Space and Transformer Architecture with Sequential Mixture of Experts for Multi-View Mammography

2025-07-23 · Farnoush Bayatmakou, Reza Taleei, Nicole Simone, Arash Mohammadi arxiv

Breast cancer (BC) remains one of the leading causes of cancer-related mortality among women, despite recent advances in Computer-Aided Diagnosis (CAD) systems. Accurate and efficient interpretation of multi-view mammogr…

Computational EfficiencyRepresentation Learning

Swimba: Switch Mamba Model Scales State Space Models

2026-03-06 · Zhixu Du, Krishna Teja Chitty-Venkata, Murali Emani, Venkatram Vishwanath 외 arxiv

Mixture-of-experts (MoE) is a common approach for increasing parameter capacity, but applying MoE to state space model (SSM) token mixers can multiply the cost of the recurrent state update. We study how to introduce exp…

Computational Efficiency