Han-yu (Henry) Wang

Applied Artificial Intelligence undergraduate at the University of Hong Kong. My research studies how people form and use knowledge, how internal representations and computations support behaviour in AI systems, and how learning and thinking change when people work with AI. I use behavioural experiments, computational modelling, model analysis, and conceptual work.

Publications & preprints

Human-AI interaction & collaboration

Early Epistemic Settlement in AI-Assisted Writing (under review)
Humans Disengage, Reasoning Models Persist: Separating Difficulty Registration from Deliberation Allocation (under review)

Human learning & cognition

The Resolving Power of Transfer Experiments: When Can Designs Distinguish Accounts of Generalization? (under review)
Functional Encoding and Representational Binding in Componential Transfer (under review)
When Does a Smooth Learning Curve Mean Smooth Learning? Representational Format, Identifiability, and the Bounded Averaging Artifact (under review)

Language models: mechanisms & behavior

BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval (ICLR 2025 Spotlight)
Priors Persist Through Suppression: A Stroop Paradigm for Lexical Override (under review)
Function-Vector Heads Are Two Populations: Writers and Cancellers in In-Context Learning (under review)

CV (PDF) · GitHub · LinkedIn · whenry6688@gmail.com

This site is interactive and needs JavaScript for the full experience.