activity
20242026
collaborators

5 papers

cs.CV2026

Seeing Through the PRISM: Compound & Controllable Restoration of Scientific Images

Rupa Kurinchi-Vendhan, Pratyusha Sharma, Antonio Torralba +1

Scientific and environmental imagery often suffer from complex mixtures of noise related to the sensor and the environment. Existing restoration methods typically remove one degrad…

cs.LG2025

Compress to Impress: Efficient LLM Adaptation Using a Single Gradient Step on 100 Samples

Shiva Sreeram, Alaa Maalouf, Pratyusha Sharma +1

Recently, Sharma et al. suggested a method called Layer-SElective-Rank reduction (LASER) which demonstrated that pruning high-order components of carefully chosen LLM's weight matr…

cs.LG2025

Hybrid Data can Enhance the Utility of Synthetic Data for Training Anti-Money Laundering Models

Rachel Chung, Pratyush Nidhi Sharma, Mikko Siponen +2

Money laundering is a critical global issue for financial institutions. Automated Anti-money laundering (AML) models, like Graph Neural Networks (GNN), can be trained to identify i…

cs.LG2025

Dion: Distributed Orthonormalized Updates

Kwangjun Ahn, Byron Xu, Natalie Abreu +5

Orthonormalized updates accelerate training, improve stability, and enable robust hyperparameter transfer, but existing methods like Muon rely on dense matrix operations that clash…

cs.DS2024

3SUM in Preprocessed Universes: Faster and Simpler

Shashwat Kasliwal, Adam Polak, Pratyush Sharma

We revisit the 3SUM problem in the \emph{preprocessed universes} setting. We present an algorithm that, given three sets , , of integers, preprocesses them in quadrat…