8 papers
Small-Scale Experiments: Are We There Yet?
Nicholas Lourie, Kyunghyun Cho, Karen Ullrich +1
Scaling laws promised cost-effective experiments; six years later, they have yet to fully deliver. Instead, researchers have found them unreliable at small scales (starting at 4M p…
Neural Neural Scaling Laws
Michael Y. Hu, Jane Pan, Ayush Rajesh Jhaveri +2
Neural scaling laws predict how language model performance improves with increased training inputs. While aggregate metrics like validation loss can follow smooth power-law curves,…
Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning
Jeff Shen, Francois Lanusse, Liam Holden Parker +24
Sequential scientific data span many resolutions and domains, and unifying them into a common representation is a key step toward developing foundation models for the sciences. Ast…
AION-1: Omnimodal Foundation Model for Astronomical Sciences
Liam Parker, Francois Lanusse, Jeff Shen +24
While foundation models have shown promise across a variety of fields, astronomy still lacks a unified framework for joint modeling across its highly diverse data modalities. In th…
Scaling Laws Are Unreliable for Downstream Tasks: A Reality Check
Nicholas Lourie, Michael Y. Hu, Kyunghyun Cho
Downstream scaling laws aim to predict task performance at larger scales from the model's performance at smaller scales. Whether such prediction should be possible is unclear: some…
Hyperparameter Loss Surfaces Are Simple Near their Optima
Nicholas Lourie, He He, Kyunghyun Cho
Hyperparameters greatly impact models' capabilities; however, modern models are too large for extensive search. Instead, researchers design recipes that train well across scales ba…