All Papers
0 / 0 papers shown
Title |
|---|
Title |
|---|

Title |
|---|
![]() Out-of-distribution generalization via composition: a lens through induction heads in TransformersProceedings of the National Academy of Sciences of the United States of America (PNAS), 2024 |
![]() All or None: Identifiable Linear Properties of Next-token Predictors in Language ModelingInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 |