LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws.
Prasanna Mayilvahanan, Thaddus Wiedemer, Sayak Mallick, Matthias Bethge, Wieland Brendel
Browse the full ICML paper archive.
Prasanna Mayilvahanan, Thaddus Wiedemer, Sayak Mallick, Matthias Bethge, Wieland Brendel
Browse the full ICML paper archive.