Aaron T Wang — accepted AI-conference papers

2026

In Context Semi-Supervised Learning

Jiashuo Fan, Paul Rosu, Aaron T Wang, Lawrence Carin, Xiang Cheng

ICLR 2026poster

There has been significant recent interest on understanding the capacity of Transformers for in-context learning (ICL), yet most theory focuses on supervised settings with explicitly labeled pairs. In practice, Transformers often perform well even when labels are sparse or absent, suggesting crucial…

Cited by 0 Source ↗code ↗Scholar ↗

2025

On Understanding Attention-Based In-Context Learning for Categorical Data

Aaron T Wang, William Convertino, Xiang Cheng, Ricardo Henao, Lawrence Carin

ICML 2025poster

In-context learning based on attention models is examined for data with categorical outcomes, with inference in such models viewed from the perspective of functional gradient descent (GD). We develop a network composed of attention blocks, with each block employing a self-attention layer followed by…

Cited by 0 Source ↗PDF ↗Scholar ↗