Research Portfolio

Machine Learning Researcher

Research Interests

My research investigates the fundamental mechanisms of how these systems encode knowledge. I focus on developing tools and methodologies to understand neural network behavior, particularly in addressing "hallucinations" and ensuring proper alignment with human values.

Foundation Models

Red-teaming, confabulations ["hallucinations"], reasoning, and alignment in large language models and foundation AI systems.

Video Generation Models

Physical world modeling through video generation systems and their implications for AI understanding of reality.

MLOps & System Design

Machine learning operations, deployment strategies, and scalable system architecture for AI applications.

AI Safety

From adversarial testing (red teaming) to ensuring robust alignment with human values and even oversight of AI systems.

Publications

2024 Journal Article

Enhancing HIV Testing Indicator Reporting

Victor, A.J., et al.

This paper presents novel approaches to improving the accuracy and efficiency of HIV testing indicator reporting through data science techniques.

2024 Technical Article

What is few shot learning?

Victor, A.J.

A comprehensive exploration of few-shot learning techniques and their application in In-Context Learning scenarios.

2023 Conference Paper

The Future Remains Unsupervised

Victor, A.J.

An exploration of the untapped potential of unsupervised learning in the era of large language models and foundation models.

2023 Journal Article

Effective Web Scraping for Data Scientists

Victor, A.J.

A comprehensive guide to ethical and efficient web scraping methods tailored specifically for data science applications.

Current Projects

Chain-of-Thought Faithfulness Analysis

Ongoing 2025-Present

Comprehensive mechanistic analysis of chain-of-thought faithfulness in GPT-2. Implements attribution graphs, faithfulness detection, and targeted interventions for understanding reasoning circuits in language models.

Hallucination Metrics for LLMs

Ongoing 2024-Present

Developing robust evaluation metrics for measuring and quantifying hallucinations in large language models through Value-Aligned Confabulation (VAC) research.

Research Blog

Check out my research blog for detailed articles, analyses, and tutorials on AI safety, alignment, and more.

View Blog