Imagen de Portada

Numerical Investigation of Sequence Modeling Theory using Controllable Memory Functions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jiang, Haotian, Bao, Zeyu, Wang, Shida, Li, Qianxiao
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Approximation Rate of the Transformer Architecture for Sequence Modeling
por: Jiang, Haotian, et al.
Publicado: (2023)

StableSSM: Alleviating the Curse of Memory in State-space Models through Stable Reparameterization
por: Wang, Shida, et al.
Publicado: (2023)

The Effect of Depth on the Expressivity of Deep Linear State-Space Models
por: Bao, Zeyu, et al.
Publicado: (2025)

InfoFlow: A Framework for Multi-Layer Transformer Analysis
por: Yu, Penghao, et al.
Publicado: (2026)

Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
por: Wang, Shida, et al.
Publicado: (2023)

The Effect of Attention Head Count on Transformer Approximation
por: Yu, Penghao, et al.
Publicado: (2025)

Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving
por: Arisaka, Sohei, et al.
Publicado: (2024)

From Generalization Analysis to Optimization Designs for State Space Models
por: Liu, Fusheng, et al.
Publicado: (2024)

Autocorrelation Matters: Understanding the Role of Initialization Schemes for State Space Models
por: Liu, Fusheng, et al.
Publicado: (2024)

Allocation of Parameters in Transformers
por: Yu, Ruoxi, et al.
Publicado: (2025)

Learning task-specific predictive models for scientific computing
por: Yin, Jianyuan, et al.
Publicado: (2025)

Unifying back-propagation and forward-forward algorithms through model predictive control
por: Ren, Lianhai, et al.
Publicado: (2024)

LongSSM: On the Length Extension of State-space Models in Language Modelling
por: Wang, Shida
Publicado: (2024)

DynGMA: a robust approach for learning stochastic differential equations from data
por: Zhu, Aiqing, et al.
Publicado: (2024)

Learning Macroscopic Dynamics from Partial Microscopic Observations
por: Chen, Mengyi, et al.
Publicado: (2024)

Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images
por: Zhu, Aiqing, et al.
Publicado: (2025)

LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory
por: Liu, Zicheng, et al.
Publicado: (2024)

Learning Permutation-invariant Macroscopic Dynamics
por: Han, Zhichao, et al.
Publicado: (2026)

Machine Unlearning under Retain-Forget Entanglement
por: Cheng, Jingpu, et al.
Publicado: (2026)

On the Curse of Memory in Recurrent Neural Networks: Approximation and Optimization Analysis
por: Li, Zhong, et al.
Publicado: (2020)

On Hypothesis Transfer Learning of Functional Linear Models
por: Lin, Haotian, et al.
Publicado: (2022)

SMR: State Memory Replay for Long Sequence Modeling
por: Qi, Biqing, et al.
Publicado: (2024)

Multi-Modal Representation Learning for Molecular Property Prediction: Sequence, Graph, Geometry
por: Wang, Zeyu, et al.
Publicado: (2024)

MSign: An Optimizer Preventing Training Instability in Large Language Models via Stable Rank Restoration
por: Ren, Lianhai, et al.
Publicado: (2026)

Scalable learning of macroscopic stochastic dynamics
por: Chen, Mengyi, et al.
Publicado: (2025)

A unified framework for establishing the universal approximation of transformer-type architectures
por: Cheng, Jingpu, et al.
Publicado: (2025)

Deep learning and the rate of approximation by flows
por: Cheng, Jingpu, et al.
Publicado: (2026)

Identifiable learning of dissipative dynamics
por: Zhu, Aiqing, et al.
Publicado: (2025)

Mitigating distribution shift in machine learning-augmented hybrid simulation
por: Zhao, Jiaxi, et al.
Publicado: (2024)

Sequence-to-Sequence Models with Attention Mechanistically Map to the Architecture of Human Memory Search
por: Salvatore, Nikolaus, et al.
Publicado: (2025)

Memory by Design: Probabilistic Sequence Layers
por: Dowling, Matthew, et al.
Publicado: (2026)

Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling
por: Zhang, Dehao, et al.
Publicado: (2025)

Mini-Sequence Transformer: Optimizing Intermediate Memory for Long Sequences Training
por: Luo, Cheng, et al.
Publicado: (2024)

Terminally constrained flow-based generative models from an optimal control perspective
por: Gao, Weiguo, et al.
Publicado: (2026)

AutoChunk: Automated Activation Chunk for Memory-Efficient Long Sequence Inference
por: Zhao, Xuanlei, et al.
Publicado: (2024)

Long-Sequence Memory with Temporal Kernels and Dense Hopfield Functionals
por: Farooq, Ahmed
Publicado: (2025)

Language Models for Controllable DNA Sequence Design
por: Su, Xingyu, et al.
Publicado: (2025)

Adaptive Substructure-Aware Expert Model for Molecular Property Prediction
por: Jiang, Tianyi, et al.
Publicado: (2025)

Mamba-3: Improved Sequence Modeling using State Space Principles
por: Lahoti, Aakash, et al.
Publicado: (2026)

RAM-Net: Expressive Linear Attention with Selectively Addressable Memory
por: Xiao, Kaicheng, et al.
Publicado: (2026)