Hey there!

I'm Eamon Niknafs

I am a computer science graduate from Boston University interested in artificial intelligence, security research, and software engineering.

My most recent role was as an AI/ML team lead at BU Spark!, an experiential learning lab and quasi tech consulting firm with clients including the Harvard Herbarium and a handful of social impact nonprofits. In my role, I architected ML projects ensuring my teams were making steady progress towards meeting client expectations.

Recently, I've been building generative AI (Stable Diffusion, LLMs) and vision (CLIP, BLIP, ViT) projects. I am specifically interested in multimodal, ensamble, and augmentation research. See my GitHub for more projects!

My Interests

I am seeking projects and work in these areas. If you would like to collaborate with me on a project, message me below!

Machine Learning
Artificial Intelligence
Security Research
Software Engineering

Projects

Ensemble Effect:
Leveraging
Fine-tuned Models
for Image Prompt Prediction

Research paper on a model that predicts text prompts from generated images using an ensemble of multimodal models, including CLIP, BLIP, and ViT. Uses a high-quality dataset and of 100k custom generated images, cleaned to have low semantic similarity.

View Paper

The Autocast Competition

Deep learning project and paper to forecast world events outside of the training data using large language models (LLMs) including GPT-3, GPT-3.5, and GPT-4. Prompt engineering techniques including few-shot learning, expert identification, and inference averaging are employed to increase accuracy.

View Paper

Adversary Emulation Framework

An adversary emulation framework with special features including use of a messaging app as a communication channel, a hybrid encryption scheme, and shell code injection. The implant is served by a containerized listening server, MySQL database, and Flask app.

Visit Readme

ML-Herbarium

A vision transformer based machine learning pipeline built to classify plant specimens and organize records, built for the Harvard HerbariumBU Spark!. The pipeline is composed of an ensamble of fine-tuned OCR and NER models along with a ViT plant classifier to pick correct classifications in the correct context.

Visit Repo

Meta AI Video Similarity Challenge

Deep learning project to create a model that finds similar videos using a dataset of 1000s of videos. Scored 8th place of 212 participants in Meta AI’s Video Similarity Challenge in the more difficult "matching" track.

See Leaderboard

Custom Interpreter & Compiler

Tail-recursive interpreter designed to parse, push, and execute 12 unique commands on a custom made stack. Compiler implemented to compile a traditional programming language into custom-built stack language.

Visit Repo

And Many More

Check out my GitHub!

 GitHub
Loading the data just for you.

Let's get in touch.

My PGP public key is available for download here.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.