Andrea Cui

Applied Research

Owning evaluation and metrics across generative image and video models, agentic systems, and physical-AI research. The work spans post-training and human preference alignment, benchmarks for world models, and automated research on self-evolving agents.

Research Data Scientist · Internship

A research-oriented data science role developing theory-grounded behavioral models, machine learning methods, and causal frameworks.

PhD in Cognitive Science · M.S. in Computer Science · M.S. in Statistics

Researcher at the intersection of human cognition, decision-making, and computational modeling.

Lead

Measuring how much physical hardware variation a learned robot policy can tolerate, across 9 vision-language-action models. Paper on arXiv.

Evaluation lead

Led evaluation for Layers, which generates and decomposes images into independently editable layers.

User signals to model alignment

Post-training to improve model alignment with user preferences.

Evaluation and metrics

Owned evaluation and metrics for the program. More at sear.bot; paper on arXiv.