Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks Paper • 2503.11514 • Published 27 days ago • 15
Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data Paper • 2404.03862 • Published Apr 5, 2024
AdapterSwap: Continuous Training of LLMs with Data Removal and Access-Control Guarantees Paper • 2404.08417 • Published Apr 12, 2024 • 1
Dated Data: Tracing Knowledge Cutoffs in Large Language Models Paper • 2403.12958 • Published Mar 19, 2024
Does your data spark joy? Performance gains from domain upsampling at the end of training Paper • 2406.03476 • Published Jun 5, 2024
Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models Paper • 2405.20541 • Published May 30, 2024 • 24
CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images Paper • 2310.16825 • Published Oct 25, 2023 • 34