Imagen de Portada

Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix Theory

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Ettori, Davide
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

Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory
por: Ettori, Davide
Publicado: (2026)

Exploring Graph Structure Comprehension Ability of Multimodal Large Language Models: Case Studies
por: Zhong, Zhiqiang, et al.
Publicado: (2024)

Beyond Frequency: The Role of Redundancy in Large Language Model Memorization
por: Zhang, Jie, et al.
Publicado: (2025)

Model-Distributed Inference for Large Language Models at the Edge
por: Macario, Davide, et al.
Publicado: (2025)

Quantifying the Reconstructability of Astrophysical Methods with Large Language Models and Information Theory: A Case Study in Spectral Reconstruction
por: Lin, Hsing Wen, et al.
Publicado: (2026)

$R^2$-dLLM: Accelerating Diffusion Large Language Models via Spatio-Temporal Redundancy Reduction
por: Du, Zhenbang, et al.
Publicado: (2026)

Detecting overfitting in Neural Networks during long-horizon grokking using Random Matrix Theory
por: Prakash, Hari K., et al.
Publicado: (2026)

TLoRA: Tri-Matrix Low-Rank Adaptation of Large Language Models
por: Islam, Tanvir
Publicado: (2025)

Redundancy and Concept Analysis for Code-trained Language Models
por: Sharma, Arushi, et al.
Publicado: (2023)

SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs
por: Jayasuriya, Dinithi, et al.
Publicado: (2025)

Maximizing the Potential of Synthetic Data: Insights from Random Matrix Theory
por: Firdoussi, Aymane El, et al.
Publicado: (2024)

Intrinsic Muon: Spectral Optimization on Riemannian Matrix Manifolds
por: Li, Yibang, et al.
Publicado: (2026)

PRISM: Structured Optimization via Anisotropic Spectral Shaping
por: Yang, Yujie
Publicado: (2026)

Spectral Editing of Activations for Large Language Model Alignment
por: Qiu, Yifu, et al.
Publicado: (2024)

Latent Structure of Affective Representations in Large Language Models
por: Choi, Benjamin J., et al.
Publicado: (2026)

ElastiFormer: Learned Redundancy Reduction in Transformer via Self-Distillation
por: Liu, Junzhang, et al.
Publicado: (2024)

Interpretable Robot Control via Structured Behavior Trees and Large Language Models
por: Chekam, Ingrid Maéva, et al.
Publicado: (2025)

A Systematic Study of Compression Ordering for Large Language Models
por: Chhawri, Shivansh, et al.
Publicado: (2025)

Redundancy as a Structural Information Principle for Learning and Generalization
por: Bi, Yuda, et al.
Publicado: (2025)

Towards Machine Theory of Mind with Large Language Model-Augmented Inverse Planning
por: Gelpí, Rebekah A., et al.
Publicado: (2025)

Understanding Post-Training Structural Changes in Large Language Models
por: He, Xinyu, et al.
Publicado: (2025)

GraphEdit: Large Language Models for Graph Structure Learning
por: Guo, Zirui, et al.
Publicado: (2024)

Model-Based Reinforcement Learning under Random Observation Delays
por: Karamzade, Armin, et al.
Publicado: (2025)

Discrete World Models via Regularization
por: Bizzaro, Davide, et al.
Publicado: (2026)

RMT-KD: Random Matrix Theoretic Causal Knowledge Distillation
por: Ettori, Davide, et al.
Publicado: (2025)

GPrune-LLM: Generalization-Aware Structured Pruning for Large Language Models
por: Liu, Xiaoyun, et al.
Publicado: (2026)

The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
por: Lu, Yao, et al.
Publicado: (2025)

Bridging Large Language Models and Graph Structure Learning Models for Robust Representation Learning
por: Su, Guangxin, et al.
Publicado: (2024)

Automatic Parameter Selection for Non-Redundant Clustering
por: Leiber, Collin, et al.
Publicado: (2023)

A Unified Theory of Random Projection for Influence Functions
por: Hu, Pingbang, et al.
Publicado: (2026)

Inertial Confinement Fusion Forecasting via Large Language Models
por: Chen, Mingkai, et al.
Publicado: (2024)

Distillation of Large Language Models via Concrete Score Matching
por: Kim, Yeongmin, et al.
Publicado: (2025)

Structured Matrix Scaling for Multi-Class Calibration
por: Berta, Eugène, et al.
Publicado: (2025)

The Hidden Bias: A Study on Explicit and Implicit Political Stereotypes in Large Language Models
por: Löhr, Konrad, et al.
Publicado: (2025)

Enhancing Transformer-based models for Long Sequence Time Series Forecasting via Structured Matrix
por: Zhang, Zhicheng, et al.
Publicado: (2024)

Latency-Response Theory Model: Evaluating Large Language Models via Response Accuracy and Chain-of-Thought Length
por: Xu, Zhiyu, et al.
Publicado: (2025)

Align to Structure: Aligning Large Language Models with Structural Information
por: Kim, Zae Myung, et al.
Publicado: (2025)

Locality-Aware Redundancy Pruning for LLM Depth Compression
por: Yun, Vincent-Daniel, et al.
Publicado: (2026)

Fusing Urban Structure and Semantics: A Conditional Diffusion Model for Cross-City OD Matrix Generation
por: Chen, Bin, et al.
Publicado: (2026)

Adaptive Redundancy Regulation for Balanced Multimodal Information Refinement
por: Yang, Zhe, et al.
Publicado: (2025)