activity
20242026
collaborators

7 papers

cs.NE2026

Automating Parent Selection Configuration in Genetic Programming with Agentic AI

Jose Guadalupe Hernandez, Jui-Hsuan Chang, Anil Kumar Saini +2

We investigate whether agentic artificial intelligence can automate parts of the process of designing genetic programming systems by introducing an agentic framework that identifie…

cs.MA2026

Ablation Study of a Fairness Auditing Agentic System for Bias Mitigation in Early-Onset Colorectal Cancer Detection

Amalia Ionescu, Jose Guadalupe Hernandez, Jui-Hsuan Chang +4

Artificial intelligence (AI) is increasingly used in clinical settings, yet limited oversight and domain expertise can allow algorithmic bias and safety risks to persist. This stud…

cs.LG2025

Evolved Sample Weights for Bias Mitigation: Effectiveness Depends on the Fairness Objective

Anil K. Saini, Jose Guadalupe Hernandez, Emily F. Wong +3

Machine learning models trained on real-world data may inadvertently make biased predictions that negatively impact marginalized communities. Reweighting, which assigns a weight to…

cs.NE2025

GP and LLMs for Program Synthesis: No Clear Winners

Jose Guadalupe Hernandez, Anil Kumar Saini, Gabriel Ketron +1

Genetic programming (GP) and large language models (LLMs) differ in how program specifications are provided: GP uses input-output examples, and LLMs use text descriptions. In this…

cs.NE2025

StarBASE-GP: Biologically-Guided Automated Machine Learning for Genotype-to-Phenotype Association Analysis

Jose Guadalupe Hernandez, Attri Ghosh, Philip J. Freda +3

We present the Star-Based Automated Single-locus and Epistasis analysis tool - Genetic Programming (StarBASE-GP), an automated framework for discovering meaningful genetic variants…

cs.NE2024

Lexicase Selection Parameter Analysis: Varying Population Size and Test Case Redundancy with Diagnostic Metrics

Jose Guadalupe Hernandez, Anil Kumar Saini, Jason H. Moore

Lexicase selection is a successful parent selection method in genetic programming that has outperformed other methods across multiple benchmark suites. Unlike other selection metho…