collaborators

33 papers

cs.LG2026

Data-Driven Variational Basis Learning Beyond Neural Networks: A Non-Neural Framework for Adaptive Basis Discovery

Andrew Kiruluta

Classical representation systems such as Fourier series, wavelets, and fixed dictionaries provide analytically tractable basis expansions, but they are not intrinsically adapted to…

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.LG2026

From Gradients to Riccati Geometry: Kalman World Models for Single-Pass Learning

Andrew Kiruluta

Backpropagation dominates modern machine learning, yet it is not the only principled method for optimizing dynamical systems. We propose Kalman World Models (KWM), a class of learn…

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.LG2026

Spectral Generative Flow Models: A Physics-Inspired Replacement for Vectorized Large Language Models

Andrew Kiruluta

We introduce Spectral Generative Flow Models (SGFMs), a physics-inspired alternative to transformer-based large language models. Instead of representing text or video as sequences…

cs.LG2026

Filtering Beats Fine Tuning: A Bayesian Kalman View of In Context Learning in LLMs

Andrew Kiruluta

We present a theory-first framework that interprets inference-time adaptation in large language models (LLMs) as online Bayesian state estimation. Rather than modeling rapid adapta…