01
Preprint · arXiv · 2026
RESEARCH & PUBLICATIONS
Responsible AI that works in the real world.
Research spanning model fairness, generative augmentation, guardrails, compliance automation, and deployable AI systems.
PEER-REVIEWED & PREPRINT RESEARCH
Selected research
Read publication ↗
02
Accepted · IEEE RTC 2026
Fairness-Latency Trade-Offs of Guardrails for Local LLM-Driven NPC Dialogue
Research on balancing response latency, safety guardrails, and fairness in local language-model game characters.03
Preprint · arXiv · 2026
When Generative Augmentation Hurts
A Benchmark Study of GAN and Diffusion Models for Bias Correction in AI Classification Systems
04
Preprint · arXiv · 2022