Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
AI Personalized Interactive Fiction (AIPIF)
AIPIF began with three partners in Dr. Daniel Shapiro’s CMPM146: Game AI course and with his mentorship, we refined the project and showcased it at ECAI-2024 and PAIS-2024.
AI Personalized Teaching Fiction (AIPTF)
This solo summer project stemmed from my goal to make AIPIF faster and more cost-efficient. Along the way, I developed stories to teach children specific life lessons. Each story includes a quiz at the end to encourage critical thinking and tracks correct and incorrect answers. While AIPTF keeps the original AIPIF interface, I re-implemented the back-end using Javascript Cloudflare functions.
DBDoctor: LLM-Aided SMT Refutation of SQL Query Equivalence
DBDoctor uses LLMs to propose counterexamples and rewrite queries into SMT-friendly forms, dramatically reducing the rate of “unsupported” query pairs from 100% to 1% and successfully refuting 47% of previously unverifiable cases.
Embedding Vector Augmentation of USDA’s Food Nutrient Imputation
For a Statistical Machine Learning graduate course, I selected USDA’s food nutrition dataset and chose to explore whether OpenAI’s LLM technology can enhance estimates of food nutrition. This research effort was motivated by personal health interests.
HAPO: Hyper-reflection for Automatic Prompt Optimization
An improvement of GEPA (automatic prompt optimization) through “hyper-reflection”, enabling compact LLMs to achieve performance closer to frontier models on complex tasks like SQL query equivalence generation and refutation.
NutriGNN: Food Nutrient Prediction with GNNs
A graph neural network approach to predicting missing nutrient values in food composition databases. By building a knowledge graph enriched with LLM-derived semantic relations between foods, NutriGNN improves representation learning and prediction quality, especially for low-resource food items with sparse nutritional data.
State Machine Visualizer (SMV)
This project was advised by Dr. Gabriel Elkaim and began during my CAHSI/NSF-sponsored undergraduate research internship. Dr. Elkaim provided guidance on requirements, while I focused on development and testing.
SnipDue: Never Miss Another Deadline
A deadline import tool with near universal support for all the ways to represent a schedule. Our tool uses Claude 3.5 Sonnet and works with Google Calendar, Apple Calendar, Outlook, and any iCal-compatible app.
SymbolSight: Robust Symbols for Retinal Implants
A research project optimizing visual symbol sets for patients with retinal implants. By analyzing confusion matrices over simulated letter recognition using the pulse2percept framework, SymbolSight derives symbol sets that remain distinguishable even under the severe distortions introduced by low-resolution prosthetic vision.
Explainable AI Requirements: A Comparative Study of Repetitive and Unique Decision Contexts
We designed and tested two Explainable AI (XAI) prototypes with four groups of participants. My partner, Kay Krachenfels, created the “Commerce Moderator,” while I developed the “Communication Monitor.”
Zero-Shot Document Ranking Using LLMs: Replication and Improvements
My partner, Mehak Dhaliwal, and I conducted a study replicating and enhancing recent advancements in zero-shot document ranking using Large Language Models (LLMs).
publications
An Automated Tool for State Machine Diagram Generation in Mechatronics Education
Published in Technical Report, 2024
A tool that automatically generates state diagrams from event-driven control system code for mechatronics education.
Recommended citation: Lesner, J., & Elkaim, G. (2024). Technical Report.
Download Paper
AI Personalized Interactive Fiction for Young Children
Published in ECAI 2024, 2024
A high-fidelity prototype letting young children create personalized, interactive AI stories with text-to-image, text-to-sound, and text-to-music generation.
Recommended citation: Lesner, J., Murayama, L., Guizar, T., Phunjamaneechot, P., & Shapiro, D. (2024). Frontiers in Artificial Intelligence and Applications: Vol. 392. ECAI 2024 (pp. 4756-4763). IOS Press.
Download Paper | Download Slides
A Demonstration of AI Personalized Interactive Fiction for Young Children
Published in ECAI 2024, 2024
A demonstration of the AIPIF prototype that lets young children create personalized, interactive AI-generated stories.
Recommended citation: Lesner, J., Murayama, L., Guizar, T., Phunjamaneechot, P., & Shapiro, D. (2024). Frontiers in Artificial Intelligence and Applications: Vol. 392. ECAI 2024 (pp. 4487-4490). IOS Press.
Download Paper | Download Slides
Understanding XAI Requirements: A Comparative Study of Repetitive and Unique Decision Contexts
Published in Technical Report, 2024
An empirical study of two Explainable AI prototypes comparing repetitive and unique AI decision contexts.
Recommended citation: Krachenfels, K., & Lesner, J. (2024). Technical Report.
Download Paper
MIRROR: Measuring, Improving, and Reproducing Ranking with Open Retrieval Models
Published in Technical Report, 2025
A replication study of zero-shot document ranking with LLMs, confirming effectiveness and revealing efficiency gains from setwise methods.
Recommended citation: Dhaliwal, M., & Lesner, J. (2025). Technical Report.
Download Paper
NutriGNN: Food Nutrient Prediction with an LLM Enriched Knowledge Graph
Published in Technical Report, 2025
A graph neural network approach to predicting missing nutrient values in food composition databases.
Recommended citation: Lesner, J., & Anand, S. (2025). Technical Report.
Download Paper
SymbolSight: Minimizing Inter-Symbol Interference for Reading with Prosthetic Vision
Published in EMBC 2026, 2025
SymbolSight assigns symbol-to-letter mappings that minimize confusion between frequently adjacent letters, reducing predicted confusion by a median factor of 22 across Arabic, Bulgarian, and English.
Recommended citation: Lesner, J., & Beyeler, M. (2026). IEEE EMBC 2026.
Download Paper
DBDoctor: LLM-Aided SMT Refutation of SQL Query Equivalence
Pending peer review from Preparing for CAV-2026, 2025
DBDoctor uses LLMs to propose counterexamples and rewrite queries into SMT-friendly forms to refute SQL query equivalence claims.
Recommended citation: Lesner, J., Zhao, F., & Yan, X. (2025). Preparing for CAV-2026.
Download Paper
HAPO: Hyper-reflection for Automatic Prompt Optimization
Pending peer review from Preparing for IJCAI-2026, 2025
An improvement of GEPA (automatic prompt optimization) through “hyper-reflection”, enabling compact LLMs to achieve performance closer to frontier models.
Recommended citation: Lesner, J., & Yan, X. (2025). Preparing for IJCAI-2026.
Download Paper
talks
Talk 1 on Relevant Topic in Your Field
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Conference Proceeding talk 3 on Relevant Topic in Your Field
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.