Skip to content
View cotenthusiast's full-sized avatar

Block or report cotenthusiast

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
cotenthusiast/README.md

Hi, I'm Karl

I'm a Computer Science student at Queen's University Belfast working on machine learning research.

Research

Amadeus: Counterpoint

Studying whether models of individual behaviour remain faithful when the people they model are placed into previously unseen interactions.

Python · PyTorch · Chess · SLURM/HPC

Submitted to AAMAS 2027, arXiv pending moderation

ChoiceBench

Researching the relationship between accuracy and option-order sensitivity in multiple-choice LLM evaluation.

ChoiceBench provides the experimental framework behind the study, supporting multiple mitigation strategies, benchmarks, API providers, local models, reproducible HPC execution, and analysis.

Python · PyTorch · Hugging Face · vLLM · SLURM/HPC

Repository · Paper

Other Projects

A multilayer perceptron implemented directly in NumPy, including forward propagation, backpropagation, optimisation, checkpoints, and controlled experiments.

Byte-pair tokenisation and decoder-only transformer work aimed at understanding the language-modelling stack from first principles.

An anime recommendation system exploring collaborative filtering and matrix-factorisation methods.

Tools

Python PyTorch NumPy Hugging Face vLLM Linux Bash Git SLURM/HPC GitHub Actions Java C++ LaTeX

Pinned Loading

  1. amadeus-counterpoint amadeus-counterpoint Public

    Compositional behavioral modeling under unseen dyadic interaction, using chess as a controlled testbed.

    Python

  2. choicebench choicebench Public

    ChoiceBench is a lightweight framework for MCQ evaluation-method research on LLMs, with built-in support for answer-order bias analysis and mitigation methods.

    Python 2

  3. neural-network-from-scratch neural-network-from-scratch Public

    Neural network from scratch in NumPy with a clean src/ layout, unit tests, and runnable train/eval scripts that save reproducible artifacts (loss curves, configs, metrics).

    Python