Tag
Proposes CAGI, a framework that integrates clustering and generative adversarial networks to improve missing data imputation by exploiting latent subgroup structures, achieving superior performance on benchmark datasets.
A guide from Cambridge University for creating disk images of floppy disks for long-term preservation, covering identification, hardware, cleaning, and imaging.
WARP is a framework that recovers the domain mixture weights of a fine-tuned model from its released weights by generating pseudo-checkpoints via model merging and extracting geometric features. It achieves low mean absolute error on BERT and GPT-2, outperforming membership inference.