7 papers · 1 filter
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…
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…
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…
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…
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…
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…