Author

A. Mohamed

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

STEER: Reducing Inference Cost in Relational Foundation Models through Semantically Informed Sampling

STEER is proposed, a sampling approach that shrinks the inference context by concentrating it on the tables most relevant to the prediction task at hand, and it is shown that it reduces inference context size by about 40% on average while maintaining, and in some cases improving, prediction accuracy.

A. Mohamed, Ashraf Aboulnaga · 0 citations