1 citations · 1 across the 2 of their papers we have counts for
2 papers
cs.LG2026
More Data Cannot Break a Symmetry: Identifiability by Design
Jing Xu, Christopher Kanan
Unsupervised representational alignment recovers a stimulus-by-stimulus correspondence from geometry alone, but the automorphism group of the stimulus geometry bounds what any such…
cs.LG2023★ 1 cited
Quantifying the Variability Collapse of Neural Networks
Jing Xu, Haoxiong Liu
Recent studies empirically demonstrate the positive relationship between the transferability of neural networks and the within-class variation of the last layer features. The recen…