When does training on downscaled images yield the same gradients? Paper • 2608.04448 • Published 4 days ago
Robust Guidance for Unsupervised Data Selection: Capturing Perplexing Named Entities for Domain-Specific Machine Translation Paper • 2402.19267 • Published May 21, 2024
Confidence Regularized Masked Language Modeling using Text Length Paper • 2504.06037 • Published Apr 8, 2025
