← Search

Amir Rezaei Balef

2 accepted papers

2026

Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models

ICML 2026poster

Transformer-based tabular foundation models (TFMs) dominate small to medium tabular predictive benchmark tasks, yet their inference mechanisms remain largely unexplored. We present the first large-scale mechanistic study of layerwise dynamics in 6 state-of-the-art tabular in-context learning models.…

Cited by 0SourceScholar
2025

Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning

NeurIPS 2025poster

The Combined Algorithm Selection and Hyperparameter optimization (CASH) is a challenging resource allocation problem in the field of AutoML. We propose MaxUCB, a max $k$-armed bandit method to trade off exploring different model classes and conducting hyperparameter optimization. MaxUCB is specific…

Cited by 0SourcecodeScholar