Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Pethkar, Kaustubh, Xiong, Ziyang, Shang, Zuofeng, Li, Yingcong
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning
par: Sanokowski, Sebastian, et autres
Publié: (2025)

Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
par: Van Nguyen, Chien, et autres
Publié: (2026)

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
par: Ildiz, M. Emrullah, et autres
Publié: (2024)

Equally Critical: Samples, Targets, and Their Mappings in Datasets
par: Yang, Runkang, et autres
Publié: (2025)

Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
par: Zhussip, Magauiya, et autres
Publié: (2025)

A General and Efficient Training for Transformer via Token Expansion
par: Huang, Wenxuan, et autres
Publié: (2024)

Mechanics of Next Token Prediction with Self-Attention
par: Li, Yingcong, et autres
Publié: (2024)

Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
par: Chen, Zixiang, et autres
Publié: (2023)

Detecting Hidden Triggers: Mapping Non-Markov Reward Functions to Markov
par: Hyde, Gregory, et autres
Publié: (2024)

FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits
par: Lu, Pingchen, et autres
Publié: (2025)

Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective
par: Zhang, Yuheng, et autres
Publié: (2026)

Explaining Fine Tuned LLMs via Counterfactuals A Knowledge Graph Driven Framework
par: Wang, Yucheng, et autres
Publié: (2025)

Memory-Consistent Neural Networks for Imitation Learning
par: Sridhar, Kaustubh, et autres
Publié: (2023)

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

FlashSampling: Fast and Memory-Efficient Exact Sampling
par: Ruiz, Tomas, et autres
Publié: (2026)

MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
par: Liu, Yuxi, et autres
Publié: (2025)

Generalizing Hyperedge Expansion for Hyper-relational Knowledge Graph Modeling
par: Liu, Yu, et autres
Publié: (2024)

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
par: Deiseroth, Björn, et autres
Publié: (2024)

Scalable Parameter and Memory Efficient Pretraining for LLM: Recent Algorithmic Advances and Benchmarking
par: Glentis, Athanasios, et autres
Publié: (2025)

Homomorphic Mappings for Value-Preserving State Aggregation in Markov Decision Processes
par: Zhao, Shuo, et autres
Publié: (2025)

MemoryKT: An Integrative Memory-and-Forgetting Method for Knowledge Tracing
par: Lin, Mingrong, et autres
Publié: (2025)

Towards Faster Training of Diffusion Models: An Inspiration of A Consistency Phenomenon
par: Xu, Tianshuo, et autres
Publié: (2024)

FEVO: Financial Knowledge Expansion and Reasoning Evolution for Large Language Models
par: Pang, Bo, et autres
Publié: (2025)

SaDiT: Efficient Protein Backbone Design via Latent Structural Tokenization and Diffusion Transformers
par: Mo, Shentong, et autres
Publié: (2026)

Learning Hidden Markov Models Using Conditional Samples
par: Kakade, Sham M., et autres
Publié: (2023)

Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps
par: Holderrieth, Peter, et autres
Publié: (2026)

Detecting Anomalies in Dynamic Graphs via Memory enhanced Normality
par: Liu, Jie, et autres
Publié: (2024)

Efficient State Space Model via Fast Tensor Convolution and Block Diagonalization
par: Liang, Tongyi, et autres
Publié: (2024)

MEC-IP: Efficient Discovery of Markov Equivalent Classes via Integer Programming
par: Elrefaey, Abdelmonem, et autres
Publié: (2024)

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
par: Wu, Wei, et autres
Publié: (2024)

Condensed Data Expansion Using Model Inversion for Knowledge Distillation
par: Binici, Kuluhan, et autres
Publié: (2024)

Memory-Efficient Fine-Tuning via Low-Rank Activation Compression
par: Shi, Jiang-Xin, et autres
Publié: (2025)

Context Distillation as Latent Memory Management
par: Zheng, Ziyang, et autres
Publié: (2026)

MAGIK: Mapping to Analogous Goals via Imagination-enabled Knowledge Transfer
par: Palattuparambil, Ajsal Shereef, et autres
Publié: (2025)

Efficient Real-Time Aircraft ETA Prediction via Feature Tokenization Transformer
par: Huang, Liping, et autres
Publié: (2025)

Distilled Thompson Sampling: Practical and Efficient Thompson Sampling via Imitation Learning
par: Namkoong, Hongseok, et autres
Publié: (2020)

PathletRL++: Optimizing Trajectory Pathlet Extraction and Dictionary Formation via Reinforcement Learning
par: Alix, Gian, et autres
Publié: (2024)

Token-Efficient RL for LLM Reasoning
par: Lee, Alan, et autres
Publié: (2025)

MATE: Solving Contextual Markov Decision Processes with Memory of Accumulated Transition Embeddings
par: Hwang, Himchan, et autres
Publié: (2026)

EDGE: Efficient Data Selection for LLM Agents via Guideline Effectiveness
par: Zhang, Yunxiao, et autres
Publié: (2025)