Back
What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis
@conference{OrmDanSin25, title = {What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis}, booktitle = {The Thirteenth International Conference on Learning Representations (ICLR)}, month = apr, year = {2025}, slug = {ormdansin25}, author = {Ormaniec, W. and Dangel, F. and Singh, S. P.}, month_numeric = {4} }
More information