Imagen de Portada

From Attention to Atoms: Spectral Dictionary Learning for Fast, Interpretable Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Kiruluta, Andrew
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Spectral Dictionary Learning for Generative Image Modeling
por: Kiruluta, Andrew
Publicado: (2025)

Spectral Generative Flow Models: A Physics-Inspired Replacement for Vectorized Large Language Models
por: Kiruluta, Andrew
Publicado: (2026)

Adaptive Two Sided Laplace Transforms: A Learnable, Interpretable, and Scalable Replacement for Self-Attention
por: Kiruluta, Andrew
Publicado: (2025)

From Eigenmodes to Proofs: Integrating Graph Spectral Operators with Symbolic Interpretable Reasoning
por: Kiruluta, Andrew, et al.
Publicado: (2025)

Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention
por: Kiruluta, Andrew
Publicado: (2026)

From Gradients to Riccati Geometry: Kalman World Models for Single-Pass Learning
por: Kiruluta, Andrew
Publicado: (2026)

Compressed-Sensing-Guided, Inference-Aware Structured Reduction for Large Language Models
por: Kiruluta, Andrew
Publicado: (2026)

From Pixels and Words to Waves: A Unified Framework for Spectral Dictionary vLLMs
por: Kiruluta, Andrew, et al.
Publicado: (2025)

State Fourier Diffusion Language Model (SFDLM): A Scalable, Novel Iterative Approach to Language Modeling
por: Kiruluta, Andrew, et al.
Publicado: (2025)

Data-Driven Variational Basis Learning Beyond Neural Networks: A Non-Neural Framework for Adaptive Basis Discovery
por: Kiruluta, Andrew
Publicado: (2026)

Spectral Neuro-Symbolic Reasoning II: Semantic Node Merging, Entailment Filtering, and Knowledge Graph Alignment
por: Kiruluta, Andrew, et al.
Publicado: (2025)

Graph Laplacian Wavelet Transformer via Learnable Spectral Decomposition
por: Kiruluta, Andrew, et al.
Publicado: (2025)

Filtering Beats Fine Tuning: A Bayesian Kalman View of In Context Learning in LLMs
por: Kiruluta, Andrew
Publicado: (2026)

A Novel Architecture for Symbolic Reasoning with Decision Trees and LLM Agents
por: Kiruluta, Andrew
Publicado: (2025)

History-Aware Cross-Attention Reinforcement: Self-Supervised Multi Turn and Chain-of-Thought Fine-Tuning with vLLM
por: Kiruluta, Andrew, et al.
Publicado: (2025)

Learnable Multi-Scale Wavelet Transformer: A Novel Alternative to Self-Attention
por: Kiruluta, Andrew, et al.
Publicado: (2025)

Breaking Quadratic Barriers: A Non-Attention LLM for Ultra-Long Context Horizons
por: Kiruluta, Andrew, et al.
Publicado: (2025)

Beyond Self Attention: A Subquadratic Fourier Wavelet Transformer with Multi Modal Fusion
por: Kiruluta, Andrew, et al.
Publicado: (2021)

Quantum Spectral Reasoning: A Non-Neural Architecture for Interpretable Machine Learning
por: Kiruluta, Andrew
Publicado: (2025)

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
por: Karvonen, Adam, et al.
Publicado: (2024)

Bridging Dictionary: AI-Generated Dictionary of Partisan Language Use
por: Jiang, Hang, et al.
Publicado: (2024)

Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning
por: Wu, John, et al.
Publicado: (2024)

FourierNAT: A Fourier-Mixing-Based Non-Autoregressive Transformer for Parallel Sequence Generation
por: Kiruluta, Andrew, et al.
Publicado: (2025)

DILA: Dictionary Label Attention for Mechanistic Interpretability in High-dimensional Multi-label Medical Coding Prediction
por: Wu, John, et al.
Publicado: (2024)

Geometry-Adaptive Explainer for Faithful Dictionary-Based Interpretability under Distribution Shift
por: Lim, Sungjun, et al.
Publicado: (2026)

CS-VLM: Compressed Sensing Attention for Efficient Vision-Language Representation Learning
por: Kiruluta, Andrew, et al.
Publicado: (2025)

Chain-of-Dictionary Prompting Elicits Translation in Large Language Models
por: Lu, Hongyuan, et al.
Publicado: (2023)

Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning
por: Wang, Junxuan, et al.
Publicado: (2025)

Improving Language Models Trained on Translated Data with Continual Pre-Training and Dictionary Learning Analysis
por: Boughorbel, Sabri, et al.
Publicado: (2024)

Improving Rare Word Translation With Dictionaries and Attention Masking
por: Sible, Kenneth J., et al.
Publicado: (2024)

Incremental Comprehension of Garden-Path Sentences by Large Language Models: Semantic Interpretation, Syntactic Re-Analysis, and Attention
por: Li, Andrew, et al.
Publicado: (2024)

Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models
por: Lu, Hongyuan, et al.
Publicado: (2024)

Optimizing Multimodal Language Models through Attention-based Interpretability
por: Sergeev, Alexander, et al.
Publicado: (2025)

SignAttention: On the Interpretability of Transformer Models for Sign Language Translation
por: Bianco, Pedro Alejandro Dal, et al.
Publicado: (2024)

Wavelet Logic Machines: Learning and Reasoning in the Spectral Domain Without Neural Networks
por: Kiruluta, Andrew
Publicado: (2025)

How Attention Sinks Emerge in Large Language Models: An Interpretability Perspective
por: Peng, Runyu, et al.
Publicado: (2026)

V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models
por: Wang, Qidong, et al.
Publicado: (2025)

Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries
por: Sakajo, Haruki, et al.
Publicado: (2025)

From Attention to Activation: Unravelling the Enigmas of Large Language Models
por: Kaul, Prannay, et al.
Publicado: (2024)

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