Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Peptide Identification Using Tandem Mass Spectrometry

Peptide Identification Using Tandem Mass Spectrometry

Tandem mass spectrometry, also known as MS/MS or MS2, is an analytical technique that employs two mass analyzers. Essentially it is a series of mass spectrometers that helps isolate a particular biomolecule and then helps study its chemical properties.
This technique helps gather information regarding the protein from which the peptide was obtained and to study the peptides’ amino acid sequence. Identifying peptides from a complex mixture is an important component of the growing field of...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

How PLGA Microspheres are Emerging as a Key Drug Delivery System.

International journal of nanomedicine·2026

Same author

Camouflaged object detection via context and texture-aware hierarchical interaction.

Scientific reports·2026

Same author

Low power consumption piezoelectrically tuned racetrack microring resonator based on polymer composite cantilever.

Optics express·2025

Same author

Study of Ultrasound Diagnosis of Acrania-Exencephaly-Anencephaly Sequence in Middle First Trimester: A Multicenter Center, Retrospective Analysis.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2025

Same author

An intelligent sport training method based on EEG neurofeedback.

Scientific reports·2025

Same author

Application of intelligent tongue image analysis in Conjunction with microbiomes in the diagnosis of MAFLD.

Heliyon·2024

Search research articles

Related Experiment Video

Updated: May 16, 2025

Adaptation of a Haptic Robot in a 3T fMRI

Adaptation of a Haptic Robot in a 3T fMRI

Published on: October 4, 2011

A hybrid model based on transformer and Mamba for enhanced sequence modeling.

Xiaocui Zhu¹, Qunsheng Ruan², Sai Qian³

¹Jiangxi Academy Sciences, Institute of Energy, Nanchang, 330029, Jiangxi, China. zhuxiaocui@jxas.ac.cn.

Scientific Reports

|April 3, 2025

Summary

This study introduces a novel hybrid model combining Transformer encoders and Mamba decoders for advanced language modeling. The new approach integrates feature fusion, achieving competitive results and outperforming benchmarks in various language tasks.

Keywords:

Feature fusion Mamba State space models (SSMs)Transformer

More Related Videos

The ITS2 Database

The ITS2 Database

Published on: March 12, 2012

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

Related Experiment Videos

Last Updated: May 16, 2025

Adaptation of a Haptic Robot in a 3T fMRI

Adaptation of a Haptic Robot in a 3T fMRI

Published on: October 4, 2011

The ITS2 Database

The ITS2 Database

Published on: March 12, 2012

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

Area of Science:

Artificial Intelligence
Natural Language Processing
Machine Learning

Background:

State Space Models (SSMs) and Mamba show promise in language modeling, sometimes exceeding Transformer capabilities.
Transformers remain crucial for their computational power and established effectiveness in NLP tasks.

Purpose of the Study:

To propose a novel model integrating the strengths of both Transformers and Mamba for enhanced language modeling performance.

Main Methods:

Utilized Transformer encoder for encoding and Mamba as the decoder for decoding tasks.
Introduced a feature fusion technique to merge encoder features with decoder hidden states.

Main Results:

The proposed hybrid model successfully combined Transformer and Mamba advantages.
Achieved competitive and often superior performance across various language tasks compared to existing benchmarks.

Conclusions:

The novel Transformer-Mamba hybrid model offers a powerful new architecture for language modeling.
This integration demonstrates a promising direction for future advancements in NLP.