Imagen de Portada

Memory as a Markov Matrix: Sample Efficient Knowledge Expansion via Token-to-Dictionary Mapping

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pethkar, Kaustubh, Xiong, Ziyang, Shang, Zuofeng, Li, Yingcong
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning
por: Sanokowski, Sebastian, et al.
Publicado: (2025)

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
por: Van Nguyen, Chien, et al.
Publicado: (2026)

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
por: Ildiz, M. Emrullah, et al.
Publicado: (2024)

Equally Critical: Samples, Targets, and Their Mappings in Datasets
por: Yang, Runkang, et al.
Publicado: (2025)

Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
por: Zhussip, Magauiya, et al.
Publicado: (2025)

A General and Efficient Training for Transformer via Token Expansion
por: Huang, Wenxuan, et al.
Publicado: (2024)

Mechanics of Next Token Prediction with Self-Attention
por: Li, Yingcong, et al.
Publicado: (2024)

Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
por: Chen, Zixiang, et al.
Publicado: (2023)

Detecting Hidden Triggers: Mapping Non-Markov Reward Functions to Markov
por: Hyde, Gregory, et al.
Publicado: (2024)

FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits
por: Lu, Pingchen, et al.
Publicado: (2025)

Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective
por: Zhang, Yuheng, et al.
Publicado: (2026)

Explaining Fine Tuned LLMs via Counterfactuals A Knowledge Graph Driven Framework
por: Wang, Yucheng, et al.
Publicado: (2025)

Memory-Consistent Neural Networks for Imitation Learning
por: Sridhar, Kaustubh, et al.
Publicado: (2023)

Navigating LLM Valley: From AdamW to Memory-Efficient and Matrix-Based Optimizers
por: Ranganath, Aditya
Publicado: (2026)

FlashSampling: Fast and Memory-Efficient Exact Sampling
por: Ruiz, Tomas, et al.
Publicado: (2026)

MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
por: Liu, Yuxi, et al.
Publicado: (2025)

Generalizing Hyperedge Expansion for Hyper-relational Knowledge Graph Modeling
por: Liu, Yu, et al.
Publicado: (2024)

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
por: Deiseroth, Björn, et al.
Publicado: (2024)

Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking
por: Glentis, Athanasios, et al.
Publicado: (2025)

Homomorphic Mappings for Value-Preserving State Aggregation in Markov Decision Processes
por: Zhao, Shuo, et al.
Publicado: (2025)

MemoryKT: An Integrative Memory-and-Forgetting Method for Knowledge Tracing
por: Lin, Mingrong, et al.
Publicado: (2025)

Towards Faster Training of Diffusion Models: An Inspiration of A Consistency Phenomenon
por: Xu, Tianshuo, et al.
Publicado: (2024)

FEVO: Financial Knowledge Expansion and Reasoning Evolution for Large Language Models
por: Pang, Bo, et al.
Publicado: (2025)

SaDiT: Efficient Protein Backbone Design via Latent Structural Tokenization and Diffusion Transformers
por: Mo, Shentong, et al.
Publicado: (2026)

Learning Hidden Markov Models Using Conditional Samples
por: Kakade, Sham M., et al.
Publicado: (2023)

Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps
por: Holderrieth, Peter, et al.
Publicado: (2026)

Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality
por: Liu, Jie, et al.
Publicado: (2024)

Efficient State Space Model via Fast Tensor Convolution and Block Diagonalization
por: Liang, Tongyi, et al.
Publicado: (2024)

MEC-IP: Efficient Discovery of Markov Equivalent Classes via Integer Programming
por: Elrefaey, Abdelmonem, et al.
Publicado: (2024)

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
por: Wu, Wei, et al.
Publicado: (2024)

Condensed Data Expansion Using Model Inversion for Knowledge Distillation
por: Binici, Kuluhan, et al.
Publicado: (2024)

Memory-Efficient Fine-Tuning via Low-Rank Activation Compression
por: Shi, Jiang-Xin, et al.
Publicado: (2025)

Context Distillation as Latent Memory Management
por: Zheng, Ziyang, et al.
Publicado: (2026)

MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer
por: Palattuparambil, Ajsal Shereef, et al.
Publicado: (2025)

Efficient Real-Time Aircraft ETA Prediction via Feature Tokenization Transformer
por: Huang, Liping, et al.
Publicado: (2025)

Distilled Thompson Sampling: Practical and Efficient Thompson Sampling via Imitation Learning
por: Namkoong, Hongseok, et al.
Publicado: (2020)

PathletRL++: Optimizing Trajectory Pathlet Extraction and Dictionary Formation via Reinforcement Learning
por: Alix, Gian, et al.
Publicado: (2024)

Token-Efficient RL for LLM Reasoning
por: Lee, Alan, et al.
Publicado: (2025)

MATE: Solving Contextual Markov Decision Processes with Memory of Accumulated Transition Embeddings
por: Hwang, Himchan, et al.
Publicado: (2026)

EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness
por: Zhang, Yunxiao, et al.
Publicado: (2025)