Cover Image

Sequential KV Cache Compression via Probabilistic Language Tries: Beyond the Per-Vector Shannon Limit

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Magarshak, Gregory
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence Information Theory Neural and Evolutionary Computing 68Q32, 94A29 I.2.7; E.4
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LAWS: Learning from Actual Workloads Symbolically -- A Self-Certifying Parametrized Cache Architecture for Neural Inference, Robotics, and Edge Deployment
by: Magarshak, Gregory
Published: (2026)

Probabilistic Language Tries: A Unified Framework for Compression, Decision Policies, and Execution Reuse
by: Magarshak, Gregory
Published: (2026)

Energy-Efficient Information Representation in MNIST Classification Using Biologically Inspired Learning
by: Stricker, Patrick, et al.
Published: (2026)

EvoPref: Multi-Objective Evolutionary Optimization Discovers Diverse LLM Alignments Beyond Gradient Descent
by: Guo, Dongxin, et al.
Published: (2026)

Phase-Coded Memory and Morphological Resonance: A Next-Generation Retrieval-Augmented Generator Architecture
by: Saklakov, Denis V.
Published: (2025)

The Lossy Horizon: Error-Bounded Predictive Coding for Lossy Text Compression (Episode I)
by: Aghanya, Nnamdi, et al.
Published: (2025)

Parameter-Efficient Neuroevolution for Diverse LLM Generation: Quality-Diversity Optimization via Prompt Embedding Evolution
by: Guo, Dongxin, et al.
Published: (2026)

MVTamperBench: Evaluating Robustness of Vision-Language Models
by: Agarwal, Amit, et al.
Published: (2024)

Evolutionary Algorithms Approach For Search Based On Semantic Document Similarity
by: Muniyappa, Chandrashekar, et al.
Published: (2025)

Graded Transformers
by: Shaska Sr, Tony
Published: (2025)

Improving Fuzzy Rule Classifier with Brain Storm Optimization and Rule Modification
by: Huang, Yan, et al.
Published: (2024)

LLM-Viterbi: Semantic-Aware Decoding for Convolutional Codes
by: Li, Zhengtong, et al.
Published: (2026)

A Dynamic-Growing Fuzzy-Neuro Controller, Application to a 3PSP Parallel Robot
by: Jalaeian-Farimani, Mohsen, et al.
Published: (2026)

Are Large Language Models In-Context Personalized Summarizers? Get an iCOPERNICUS Test Done!
by: Patel, Divya, et al.
Published: (2024)

Embodied AI in Machine Learning -- is it Really Embodied?
by: Hoffmann, Matej, et al.
Published: (2025)

Separate Before You Compress: The WWHO Tokenization Architecture
by: Darshana, Kusal
Published: (2026)

A Survey on Large Language Models with some Insights on their Capabilities and Limitations
by: Matarazzo, Andrea, et al.
Published: (2025)

Theoretical Analysis of Positional Encodings in Transformer Models: Impact on Expressiveness and Generalization
by: Li, Yin
Published: (2025)

Counter-Inferential Behavior in Natural and Artificial Cognitive Systems
by: Dolgikh, Serge
Published: (2025)

Dance of the ADS: Orchestrating Failures through Historically-Informed Scenario Fuzzing
by: Wang, Tong, et al.
Published: (2024)

Think Thrice Before You Speak: Dual knowledge-enhanced Theory-of-Mind Reasoning for Persuasive Agents
by: Ma, Minghui, et al.
Published: (2026)

Evolutionary Computation and Large Language Models: A Survey of Methods, Synergies, and Applications
by: Chauhan, Dikshit, et al.
Published: (2025)

Quantum-Inspired Evolutionary Algorithms for Feature Subset Selection: A Comprehensive Survey
by: Vivek, Yelleti, et al.
Published: (2024)

Improved Differential Evolution based Feature Selection through Quantum, Chaos, and Lasso
by: Vivek, Yelleti, et al.
Published: (2024)

Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topology
by: Da, Longchao, et al.
Published: (2025)

Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering
by: Chen, Tiejin, et al.
Published: (2026)

UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site Knowledge
by: Li, Chenao, et al.
Published: (2025)

The Lock-In Phase Hypothesis: Identity Consolidation as a Precursor to AGI
by: Amaral, Marcelo Maciel, et al.
Published: (2025)

CELI: Controller-Embedded Language Model Interactions
by: Wagner, Jan-Samuel, et al.
Published: (2024)

ITQ3_S: High-Fidelity 3-bit LLM Inference via Interleaved Ternary Quantization with Rotation-Domain Smoothing
by: Yoon, Edward J.
Published: (2026)

Faster, Cheaper, Better: Multi-Objective Hyperparameter Optimization for LLM and RAG Systems
by: Barker, Matthew, et al.
Published: (2025)

REMoH: A Reflective Evolution of Multi-objective Heuristics approach via Large Language Models
by: Forniés-Tabuenca, Diego, et al.
Published: (2025)

Interactive LLM-assisted Curriculum Learning for Multi-Task Evolutionary Policy Search
by: Sakallioglu, Berfin, et al.
Published: (2026)

DeepSeek-V3, GPT-4, Phi-4, and LLaMA-3.3 generate correct code for LoRaWAN-related engineering tasks
by: Fernandes, Daniel, et al.
Published: (2025)

Neuromorphic Deployment of Spiking Neural Networks for Cognitive Load Classification in Air Traffic Control
by: An, Jiahui, et al.
Published: (2025)

CodeEvolve: an open source evolutionary coding agent for algorithmic discovery and optimization
by: Assumpção, Henrique, et al.
Published: (2025)

A First Runtime Analysis of the PAES-25: An Enhanced Variant of the Pareto Archived Evolution Strategy
by: Opris, Andre
Published: (2025)

Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
by: Liu, Xiaoou, et al.
Published: (2026)

InhibiDistilbert: Knowledge Distillation for a ReLU and Addition-based Transformer
by: Zhang, Tony, et al.
Published: (2025)

Modularity in Transformers: Investigating Neuron Separability & Specialization
by: Pochinkov, Nicholas, et al.
Published: (2024)