AI research

Visual Prompt Engineering

Research project on how visual prompts can improve creative story writing and iteration.

Paper: Journal of Student Research (2025) ↗Paper: National High School Journal of Science (2025) ↗

Model iteration cycle figure from the published paper — The model iteration cycle, from the NHSJS paper.

Tech

Prompt engineeringEvaluation rubricHuman gradersCreative writing analysis

Highlights

Compared prompt iterations
Evaluated stories across multiple dimensions
Turned research into a paper/poster-style project

Overview

Independent research (Jun–Nov 2024) on whether visual prompts can improve creative story writing and how stories change across prompt iterations — published as two peer-reviewed papers in 2025.

Method

I designed experiments combining LLMs with diffusion models to accelerate creative writing workflows. Stories generated under different prompt conditions were evaluated with a rubric across multiple dimensions, with human graders scoring the outputs.

Findings

The prompt-engineering techniques improved model iteration efficiency by 39–51%. Full methodology and results are in the papers linked above.

Publications

“Efficient Visual Prompt Engineering for Creative Story Writing” — Journal of Student Research (2025), independent research.

“Enhancing Narrative Efficiency in LLMs via Prompt Engineering” — The National High School Journal of Science (2025), independent research.