ResearchTrend.AI
GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling

GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling

Tobias Katsch
ArXivPDFHTML

Papers citing "GateLoop: Fully Data-Controlled Linear Recurrence for Sequence Modeling"

5 / 5 papers shown
Title
Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
M. Beck
Korbinian Poppel
Phillip Lippe
Sepp Hochreiter
59
1
0
18 Mar 2025
Conformal Transformations for Symmetric Power Transformers
Conformal Transformations for Symmetric Power Transformers
Saurabh Kumar
Jacob Buckman
Carles Gelada
Sean Zhang
65
0
0
05 Mar 2025
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling
Liliang Ren
Yang Liu
Yadong Lu
Yelong Shen
Chen Liang
Weizhu Chen
Mamba
64
55
0
11 Jun 2024
Linear Attention Sequence Parallelism
Linear Attention Sequence Parallelism
Weigao Sun
Zhen Qin
Dong Li
Xuyang Shen
Yu Qiao
Yiran Zhong
68
2
0
03 Apr 2024
Resurrecting Recurrent Neural Networks for Long Sequences
Resurrecting Recurrent Neural Networks for Long Sequences
Antonio Orvieto
Samuel L. Smith
Albert Gu
Anushan Fernando
Çağlar Gülçehre
Razvan Pascanu
Soham De
88
265
0
11 Mar 2023