Imagen de Portada

Memory Retrieval in Transformers: Insights from The Encoding Specificity Principle

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dinh, Viet Hung, Ding, Ming, Qu, Youyang, Thilakarathna, Kanchana
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CAFe: Cost and Age aware Federated Learning
por: Liyanaarachchi, Sahan, et al.
Publicado: (2024)

The Frontier of Data Erasure: Machine Unlearning for Large Language Models
por: Qu, Youyang, et al.
Publicado: (2024)

SHFL: Secure Hierarchical Federated Learning Framework for Edge Networks
por: Tavallaie, Omid, et al.
Publicado: (2024)

A Multi-Drone Multi-View Dataset and Deep Learning Framework for Pedestrian Detection and Tracking
por: Dakic, Kosta, et al.
Publicado: (2025)

A Comprehensive Survey on Network Traffic Synthesis: From Statistical Models to Deep Learning
por: Sivaroopan, Nirhoshan, et al.
Publicado: (2025)

Privacy at a Price: Exploring its Dual Impact on AI Fairness
por: Yang, Mengmeng, et al.
Publicado: (2024)

Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmark
por: Manu, et al.
Publicado: (2025)

Multi-task Learning for Heterogeneous Data via Integrating Shared and Task-Specific Encodings
por: Sui, Yang, et al.
Publicado: (2025)

The Hidden Cost of Correlation: Rethinking Privacy Leakage in Local Differential Privacy
por: Jayawardana, Sandaru, et al.
Publicado: (2025)

Personalizing Federated Learning for Hierarchical Edge Networks with Non-IID Data
por: Lee, Seunghyun, et al.
Publicado: (2025)

Recent Advances in Federated Learning Driven Large Language Models: A Survey on Architecture, Performance, and Security
por: Qu, Youyang, et al.
Publicado: (2024)

SAMSA: Efficient Transformer for Many Data Modalities
por: Lenhat, Minh, et al.
Publicado: (2024)

Retrieval-Augmented Decision Transformer: External Memory for In-context RL
por: Schmied, Thomas, et al.
Publicado: (2024)

Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures
por: Omidi, Parsa, et al.
Publicado: (2025)

Range-aware Positional Encoding via High-order Pretraining: Theory and Practice
por: Nguyen, Viet Anh, et al.
Publicado: (2024)

Supra-Laplacian Encoding for Transformer on Dynamic Graphs
por: Karmim, Yannis, et al.
Publicado: (2024)

Improving Transformers using Faithful Positional Encoding
por: Idé, Tsuyoshi, et al.
Publicado: (2024)

Comparing Graph Transformers via Positional Encodings
por: Black, Mitchell, et al.
Publicado: (2024)

On the Geometry of Positional Encodings in Transformers
por: Cirrincione, Giansalvo
Publicado: (2026)

Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
por: Luo, Yuankai, et al.
Publicado: (2023)

Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers
por: Choromanski, Krzysztof Marcin, et al.
Publicado: (2023)

Memory-enhanced Invariant Prompt Learning for Urban Flow Prediction under Distribution Shifts
por: Jiang, Haiyang, et al.
Publicado: (2024)

Dynamical Properties of Tokens in Self-Attention and Effects of Positional Encoding
por: Pham, Duy-Tung, et al.
Publicado: (2025)

Retrieval-Augmented Mining of Temporal Logic Specifications from Data
por: Saveri, Gaia, et al.
Publicado: (2024)

Autoformalizing Memory Specifications with Agents
por: Ernst, Jan Ole, et al.
Publicado: (2026)

Size Transferability of Graph Transformers with Convolutional Positional Encodings
por: Porras-Valenzuela, Javier, et al.
Publicado: (2026)

Bayesian Optimization for Unknown Cost-Varying Variable Subsets with No-Regret Costs
por: Hoang, Vu Viet, et al.
Publicado: (2024)

High Dimensional Bayesian Optimization using Lasso Variable Selection
por: Hoang, Vu Viet, et al.
Publicado: (2025)

Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding
por: Ma, Qian, et al.
Publicado: (2025)

Optimizing Specific and Shared Parameters for Efficient Parameter Tuning
por: Nguyen, Van-Anh, et al.
Publicado: (2025)

Graph Transformers without Positional Encodings
por: Garg, Ayush
Publicado: (2024)

Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing
por: Li, Longlong, et al.
Publicado: (2025)

Defect Prediction with Content-based Features
por: Pham, Hung Viet, et al.
Publicado: (2024)

Continual Fine-Tuning of Large Language Models via Program Memory
por: Le, Hung, et al.
Publicado: (2026)

Test-Time Instance-Specific Parameter Composition: A New Paradigm for Adaptive Generative Modeling
por: Tran, Minh-Tuan, et al.
Publicado: (2026)

Dynamic Graph Transformer with Correlated Spatial-Temporal Positional Encoding
por: Wang, Zhe, et al.
Publicado: (2024)

Tab-PET: Graph-Based Positional Encodings for Tabular Transformers
por: Leng, Yunze, et al.
Publicado: (2025)

Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning
por: Le, Hung, et al.
Publicado: (2024)

Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, General
por: Øhrstrøm, Christoffer Koo, et al.
Publicado: (2026)

DiffPMAE: Diffusion Masked Autoencoders for Point Cloud Reconstruction
por: Li, Yanlong, et al.
Publicado: (2023)