3 papers
cs.CR2026
Surprise Masking: Private Data Filtering with Model Likelihoods
Riya Tyagi, Sahra Ghalebikesabi, Vinnie Monaco +2
Data useful for language model (LM) training can contain private or unwanted information that is at risk of being learned or memorized. We propose Surprise Masking (SM), a simple f…
cs.LG2025
Harmonic Loss Trains Interpretable AI Models
David D. Baek, Ziming Liu, Riya Tyagi +1
In this paper, we introduce harmonic loss as an alternative supervisory signal for training neural networks and large language models (LLMs). Harmonic loss differs from standard cr…
cs.LG2021
Machine Learning for Real-Time, Automatic, and Early Diagnosis of Parkinson's Disease by Extracting Signs of Micrographia from Handwriting Images
Riya Tyagi, Tanish Tyagi, Ming Wang +1
Parkinson's disease (PD) is debilitating, progressive, and clinically marked by motor symptoms. As the second most common neurodegenerative disease in the world, it affects over 10…