Showing stat.MLShow all
2 papers · 1 filter
stat.ML2026
Transformers Can Learn Posterior Predictive Distributions In-Context
Gyeonghun Kang, Changwoo J. Lee, Xiang Cheng
Prior-data fitted networks (PFNs) have recently emerged as a powerful approach for Bayesian prediction tasks, approximating the posterior predictive distribution (PPD) through in-c…
stat.ML2025
On Understanding Attention-Based In-Context Learning for Categorical Data
Aaron T. Wang, William Convertino, Xiang Cheng +2
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 desce…