A new data cartography framework that uses early-epoch loss and forget-event frequency to identify memorization hotspots and guide pruning in generative model training.
Superconducting Transformer for Superconducting Cable Testing up to 45 kA
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
A facility capable of testing superconducting cables with current of tens of kA is essential for the development of large superconducting magnets. A superconducting transformer (SCT) is a suitable choice as a high DC current source for testing superconducting cables. In this work, we will present our experimental results of a SCT up to output current of 45 kA. The properties of this SCT is characterized at 4.2 K. Its behaviors during quenches at different current levels are studied.
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Data Cartography for Detecting Memorization Hotspots and Guiding Data Interventions in Generative Models
A new data cartography framework that uses early-epoch loss and forget-event frequency to identify memorization hotspots and guide pruning in generative model training.