shane_cairns_resume.sh

$ whoami

Shane Cairns

Ph.D. researcher in continual learning, representation learning, and adaptive neural systems

location: St. Louis, MOemail: syre@duck.com

$ cat summary.txt

Ph.D. researcher in Computer Science focused on representation learning, continual learning, adaptive neural systems, and adversarial ML. First-author publication at IJCNN 2026, with two follow-up manuscripts in submission; experienced in building large-scale PyTorch experiments on GPU/HPC infrastructure. Seeking AI research and engineering roles in defense and AI safety.

$ head highlights.txt

IJCNN 2026
First-author publication
2 papers
In submission (ART-VQ, generative)
~10x
Lower reconstruction MSE vs. VQ-VAE
DARPA
Funded computer vision research
Kummer Fellow
Innovation & Entrepreneurship

$ cat experience/research.json

Graduate Researcher - Adaptive Resonance Theory & Machine Learning

Missouri S&T, Computer Science Department · Rolla, MO · Aug 2023 - Present

# Adaptive Representation Learning & Generative Modeling

  • Developed ART-VQ, a discrete-continuous latent layer replacing VQ-VAE point codebooks with Fuzzy ART hyperboxes to preserve discrete region identity and continuous within-box position; introduced a projection readout that prevents representational collapse, reducing error 35x versus midpoint training.
  • Achieved ~10x lower reconstruction MSE than VQ-VAE at matched token count on CIFAR-10 (1.01 vs. 10.55); rate-distortion controls attributed most of the improvement to increased representational rate. Under MNIST class shift, ART-VQ limited forgetting to +0.24 MSE vs. +19.3 for VQ-VAE.
  • Built a generative pipeline combining a transformer prior over hyperbox identities with diffusion modeling of within-box positions; a pre-registered 12-seed CIFAR-10 study improved FID by 3.0 points over matched VQ (p = .033).

# Adversarial Robustness of Incremental Learners (First-Author Research)

  • Developed WB-Softmax, a differentiable attack objective for non-differentiable prototype-based models, achieving 89-100% white-box attack success across USPS, MNIST, and Fashion-MNIST.
  • Designed progressive two-stage selective adversarial training and separation-aware diagnostics using iCVIs; achieved best-in-class AURAC (28.2%, 64.5%, 41.3%) and improved high-perturbation USPS robustness 4x.

# DARPA Computer Vision Research

  • Integrated ART classifiers into YOLO and built modular PyTorch infrastructure for classifier-head swapping, feature visualization, automated checkpointing, and SLURM multi-GPU training.

$ ls publications/

Robustness of Fuzzy ARTMAP to Adversarial Attacks and Progressive Adversarial Training for Streaming Learning

Cairns, S., Brito da Silva, L.E., Petrenko, S., Wunsch, D.C., & Liu, J.

ART-VQ: Vigilance-Controlled Projection Quantization for Discrete-Continuous Latent Representations

Cairns, S., Wunsch, D.C., & Liu, J.

[2026]In submission

Generating from Regions: Modeling Discrete Hyperbox Identities and Continuous Within-Region Positions

Cairns, S., Wunsch, D.C., & Liu, J.

[2026]In submission

$ cat education.json

Ph.D., Computer Science

Missouri University of Science and Technology · Rolla, MO · Expected Dec 2027

GPA: 3.75/4.0

Honors: Kummer Innovation & Entrepreneurship Fellow

B.S., Computer Science

Missouri University of Science and Technology · Rolla, MO · Dec 2022

GPA: 3.7/4.0 (Major)

Honors: Distinguished Scholar Award, Dean's List

Graduated in 3.5 years

$ cat experience/industry.json

Software Engineer Intern

Ford Motor Company · Remote · May 2022 - Aug 2022

  • Modernized legacy flat-file workflows using a SQL datastore and Java API; delivered Qlik Sense dashboards to Ford Credit stakeholders.

Software Developer Intern

Howmet Aerospace · Cleveland, OH · May 2021 - Aug 2021

  • Improved shipping traceability across North American flow paths; maintained 10+ ASP.NET applications.

$ grep -r "skills" ./resume

// ML/AI

  • Python
  • PyTorch
  • scikit-learn
  • NumPy/Pandas
  • TorchVision
  • OpenCV
  • YOLO

// HPC/Systems

  • CUDA
  • SLURM
  • Linux
  • Bash
  • Multi-GPU Training
  • Git

// research interests

  • Continual and lifelong learning
  • Representation learning (vector-quantized, prototype-based, discrete-continuous latents)
  • Adaptive neural systems and Adaptive Resonance Theory (ART)
  • Generative modeling on learned discrete representations
  • Adversarial robustness of incremental learners
  • AI safety and trustworthiness