← Search

Karthik Prasad

2 accepted papers

2025

Param$\Delta$ for Direct Mixing: Post-Train Large Language Model At Zero Cost

ICLR 2025poster

The post-training phase of large language models is essential for enhancing capabilities such as instruction-following, reasoning, and alignment with human preferences. However, it demands extensive high-quality data and poses risks like overfitting, alongside significant computational costs due to…

Cited by 0SourcePDFScholar
2021

Antipodes of Label Differential Privacy: PATE and ALIBI

NeurIPS 2021poster

We consider the privacy-preserving machine learning (ML) setting where the trained model must satisfy differential privacy (DP) with respect to the labels of the training examples. We propose two novel approaches based on, respectively, the Laplace mechanism and the PATE framework, and demonstrate t…