Copertina

Numerical Investigation of Sequence Modeling Theory using Controllable Memory Functions

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jiang, Haotian, Bao, Zeyu, Wang, Shida, Li, Qianxiao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

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

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

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

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

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

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

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

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

Allocation of Parameters in Transformers
di: Yu, Ruoxi, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Identifiable learning of dissipative dynamics
di: Zhu, Aiqing, et al.
Pubblicazione: (2025)

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

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

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

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

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

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

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

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

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

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

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

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