collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2026

Compressed-Sensing-Guided, Inference-Aware Structured Reduction for Large Language Models

Andrew Kiruluta

Large language models deliver strong generative performance but at the cost of massive parameter counts, memory use, and decoding latency. Prior work has shown that pruning and str…

cs.CL2026

Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention

Andrew Kiruluta

Modern large language model (LLM) inference engines optimize throughput and latency under fixed decoding rules, treating generation as a linear progression in token time. We propos…

cs.CL2025

Spectral Neuro-Symbolic Reasoning II: Semantic Node Merging, Entailment Filtering, and Knowledge Graph Alignment

Andrew Kiruluta, Priscilla Burity

This report extends the Spectral Neuro-Symbolic Reasoning (Spectral NSR) framework by introducing three semantically grounded enhancements: (1) transformer-based node merging using…

cs.CL2025

History-Aware Cross-Attention Reinforcement: Self-Supervised Multi Turn and Chain-of-Thought Fine-Tuning with vLLM

Andrew Kiruluta, Andreas Lemos, Priscilla Burity

We present CAGSR-vLLM-MTC, an extension of our Self-Supervised Cross-Attention-Guided Reinforcement (CAGSR) framework, now implemented on the high-performance vLLM runtime, to addr…

cs.CL2025

Graph Laplacian Wavelet Transformer via Learnable Spectral Decomposition

Andrew Kiruluta, Eric Lundy, Priscilla Burity

Existing sequence to sequence models for structured language tasks rely heavily on the dot product self attention mechanism, which incurs quadratic complexity in both computation a…

cs.CL2025

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

Andrew Kiruluta

We propose a novel spectral generative modeling framework for natural language processing that jointly learns a global time varying Fourier dictionary and per token mixing coeffici…