Author

Abicumaran Uthamacumaran

h-index 10 View on Semantic Scholar

We have 4 of 44 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

What Can Language Models Inherit from Solomonoff Induction? Limits, Attainable Properties, and What Served Conditionals Reveal

A familiar line of reasoning runs as follows: language models are flexible approximators trained under a strictly proper loss, so scale brings them closer to Solomonoff induction, and their predictive success is evidence of that approach. We apply known results from algorithmic information theory, universal prediction...

Luan Ozelim, Abicumaran Uthamacumaran, H. Zenil · 0 citations

#machine learning Preprint Aug 2026

Algorithmic Information Dynamics of Learning: A Certified, Differentiable Complexity Controller for Grokking

A certified, differentiable estimator is used to bring the calculus into learning dynamics: grokking, where a complexity order parameter is known but has not been made to act, and the algorithmic estimator's distinct contribution is timing (when to fire and when to release), not attribution.

Luan Ozelim, Abicumaran Uthamacumaran, H. Zenil · 0 citations

#artificial intelligence Preprint Jan 2026

Large Language Models are Shannon Lossy Compressors Not Solomonoff Induction Estimators: Self-improvement and Singularity Are Not Near Without Symbolic Model Synthesis

We connect two questions in Algorithmic Information Theory (AIT), Machine Learning (ML) and Artificial General Intelligence (AGI): whether LLMs estimate Solomonoff induction, and whether they can self-improve towards an AI Singularity. We provide theoretical, methodological and empirical answers in the negative but sho...

H. Zenil, Abicumaran Uthamacumaran, Luan Ozelim · 1 citation

#graph neural networks Preprint Aug 2026

Enhancing Clinical Decision Support and Differential Diagnosis with Knowledge Graphs, and Retrieval Augmented Generation in Generative AI

A decision-support pipeline combining disease-specific biomarker correlation graphs, ordinary differential equations (ODEs), deep sequence classification, and retrieval-augmented generation (RAG) is developed, with a decoupling between grounding and diagnostic correctness.

Henri Feto, Abicumaran Uthamacumaran, H. Zenil · 0 citations