Skip to content
Descubridor Institucional UMAR
Inicio
Búsqueda avanzada
Explorar
Inicio
Búsqueda avanzada
Explorar
Login
Language
English
Deutsch
Español
Français
Italiano
All Fields
Title
Author
Subject
Call Number
ISBN/ISSN
Tag
Find
Advanced
Q-Jamba: Quaternion-Native Hybrid State-Space Language Models with 3.4× Parameter Compression
Q-Jamba: Quaternion-Native Hybrid State-Space Language Models with 3.4× Parameter Compression
Fuente:
Zenodo
Saved in:
Bibliographic Details
Main Author:
Aleksej Dzigirej
Format:
Recurso digital
Language:
English
Published:
Zenodo
2026
Subjects:
quaternion neural networks
state-space models
parameter compression
language models
LLM
structured weight sharing
Mamba
hybrid architectures
Hamilton product
parameter efficiency
Online Access:
Acceder al recurso
Tags:
Add Tag
No Tags, Be the first to tag this record!
Cite this
Text this
Email this
Print
Export Record
Export to RefWorks
Export to EndNoteWeb
Export to EndNote
Save to List
Permanent link
Holdings
Description
Comments
Similar Items
Staff View
Internet
https://doi.org/10.5281/zenodo.18673701
Similar Items
Exponential synchronization for second-order switched quaternion-valued neural networks with neutral-type and mixed time-varying delays
by: Tingting Zhanga
Published: (2022)
From Quaternionic Electrodynamics to Electroweak Symmetry: A Mechanical Vacuum Framework for Standard Model Parameter Reduction
by: Mahmood, Luqman
Published: (2026)
CompreSeed Advantage Catalog: A Comprehensive Analysis of Technical Benefits in Zero-Decompression Semantic AI
by: Nakamura, Yoshikazu
Published: (2025)
Ep. 1111: The Architecture of Intelligence: Beyond the Transformer
by: Rosehill, Daniel, et al.
Published: (2026)
Ep. 111: Beyond Transformers: Solving the AI Memory Crisis
by: Rosehill, Daniel, et al.
Published: (2025)