439 citations · 867 across the 14 of their papers we have counts for
3 papers · 1 filter
Intriguing Properties of Compression on Multilingual Models
Kelechi Ogueji, Orevaoghene Ahia, Gbemileke Onilude +3
Multilingual models are often particularly dependent on scaling to generalize to a growing number of languages. Compression techniques are widely relied upon to reconcile the growt…
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
Shoaib Ahmed Siddiqui, Nitarshan Rajkumar, Tegan Maharaj +2
Modern machine learning research relies on relatively few carefully curated datasets. Even in these datasets, and typically in `untidy' or raw data, practitioners are faced with si…
When less is more: Simplifying inputs aids neural network understanding
Robin Tibor Schirrmeister, Rosanne Liu, Sara Hooker +1
How do neural network image classifiers respond to simpler and simpler inputs? And what do such responses reveal about the learning process? To answer these questions, we need a cl…