Xinyu Wang · University of Connecticut
I work on how models learn representations, how language agents make decisions, and how to turn computationally demanding ideas into working systems.
Ph.D. candidate in Computer Science & Engineering · Expected October 2026
Seeking full-time machine learning and research engineering opportunities.
From learning algorithms to operational systems.
Language agents / Learning
Learning action scores from the states an agent actually reaches, rather than relying only on offline training data.
Foundation models / Adaptation
Diagnosing unreliable layers and adjusting how model updates are combined—without task examples or validation search.
ML systems / Distributed generation
An asynchronous pipeline separating model generation, token-level scoring, and evaluation across GPUs.
Applied ML / Operational forecasting
Designing and maintaining UConn’s weather-to-outage forecasting workflow, from data readiness through automated delivery and recovery.
My work on molecular sequence models explores a broader question: how can different representations of the same object lead to consistent predictions? SIGMA improves mean performance across six molecular prediction benchmarks.