1 citations · 1 across the 10 of their papers we have counts for
Showing 2024Show all
3 papers · 1 filter
cs.LG2024★ 1 cited
Sometimes I am a Tree: Data Drives Unstable Hierarchical Generalization
Tian Qin, Naomi Saphra, David Alvarez-Melis
Early in training, LMs can behave like n-gram models, but eventually they often learn tree-based syntactic rules and generalize hierarchically out of distribution (OOD). We study t…
cs.LG2024
A Label is Worth a Thousand Images in Dataset Distillation
Tian Qin, Zhiwei Deng, David Alvarez-Melis
Data is a crucial factor in the performance of machine learning models, a principle that dataset distillation methods exploit by compressing training datasets in…
cs.LG2024
Distributional Dataset Distillation with Subtask Decomposition
Tian Qin, Zhiwei Deng, David Alvarez-Melis
What does a neural network learn when training from a task-specific dataset? Synthesizing this knowledge is the central idea behind Dataset Distillation, which recent work has show…