4 citations · 9 across the 6 of their papers we have counts for
3 papers · 1 filter
LLMs on the Line: Data Determines Loss-to-Loss Scaling Laws
Prasanna Mayilvahanan, Thaddäus Wiedemer, Sayak Mallick +2
Scaling laws guide the development of large language models (LLMs) by offering estimates for the optimal balance of model size, tokens, and compute. More recently, loss-to-loss sca…
Provable Compositional Generalization for Object-Centric Learning
Thaddäus Wiedemer, Jack Brady, Alexander Panfilov +3
Learning representations that generalize to novel compositions of known concepts is crucial for bridging the gap between human and machine perception. One prominent effort is learn…
Compositional Generalization from First Principles
Thaddäus Wiedemer, Prasanna Mayilvahanan, Matthias Bethge +1
Leveraging the compositional nature of our world to expedite learning and facilitate generalization is a hallmark of human perception. In machine learning, on the other hand, achie…