Logan Bolton
MS Computer Science student at NYU Courant interested in AI/ML and Computer Vision
About Me
I graduated from Auburn University with a B.S. in Computer Science and a minor in Statistics in Spring 2026. In Fall 2026, I will begin my Master's in Computer Science at NYU Courant. I have experience with Python, PyTorch, SQL, C#, JavaScript and more.
I am currently looking for AI/ML related Summer 2027 internships. Please reach out!
Selected Papers
Vision Language Models are Blind
This paper analyzes how and why VLMs such as GPT-4o have high scores on multimodal benchmarks, but often fail on extremely simple, abstract vision tasks.
This work has been featured by OpenAI, Google Deepmind, ByteDance, and has been cited 200+ times.
Understanding Generative AI Capabilities in Everyday Image Editing Tasks
Native multi-modal image-editing models like Nanobanana have shown an impressive ability to edit images through natural language prompts. This paper examines the strengths and weaknesses of these models when pitted against one-to-one matchups against human editors.
Experience
Undergraduate AI Researcher
Explainable AI Lab - Auburn UniversityI am an Undergraduate Researcher in Dr. Anh Nguyen's Explainable AI lab. Since joining in July
2024, I have co-authored three different papers on understanding the strengths and weaknesses of
multimodal LLMs/image-editing models and improving the reliability and interpretability of
LLMs.
This work led to me becoming an Auburn Undergraduate Research Fellow and receiving an
honorable mention for the Outstanding Undergraduate Researcher Award from the Computing Research
Association.
Machine Learning Intern
Corvid Technologies - Huntsville, ALDeveloped deep learning models to predict radar responses from 3D point clouds. Built roto-translation equivariant graph neural networks to leverage the geometric structure of point cloud data for more accurate signal prediction.
Biomechanics Computer Vision Lab Assistant
Sport Biomechanics Lab - Auburn UniversityCollaborated with an interdisciplinary team on a DoD-supported project studying how different movements affect the long-term health of canines. Trained pose estimation models to track joint positions across video data and analyzed kinematic patterns over time.
Other Projects
Wordle - GRPO Agent
Finetuned an open-source LLM and trained with reinforcement learning to improve the model from only being able to complete 0.1% of Wordle games to successfully completing 18% of games.
Reverse Engineering Information from LLM Attention Values
For the final project of my graph theory class, I trained a model to reconstruct the adjacency matrix of a graph based off the attention values of an LLM. This project demonstrates an example of how the attention map patterns of LLMs can be used to help interpret the inner workings of language models.
Contact
Have a question or want to work together? Feel free to send me an email:
loganbolton101@gmail.com