Sewoong Oh

7

Papers

18

Total Citations

Papers (7)

PLeaS - Merging Models with Permutations and Least Squares

Scalable Fingerprinting of Large Language Models

Privacy-Preserving Instructions for Aligning Large Language Models

DeepPolar: Inventing Nonlinear Large-Kernel Polar Codes via Deep Learning

DPZero: Private Fine-Tuning of Language Models without Backpropagation

Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy

Understanding the Gain from Data Filtering in Multimodal Contrastive Learning

NeurIPS 2025arXiv