4 papers
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Kyle O'Brien, Stephen Casper, Quentin Anthony +7
Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering attacks which can…
Selective Prior Synchronization via SYNC Loss
Ishan Mishra, Jiajie Li, Deepak Mishra +1
Prediction under uncertainty is a critical requirement for the deep neural network to succeed responsibly. This paper focuses on selective prediction, which allows DNNs to make inf…
Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data
Jiajie Li, Brian R Quaranto, Chenhui Xu +5
We present RASO, a foundation model designed to Recognize Any Surgical Object, offering robust open-set recognition capabilities across a broad range of surgical procedures and obj…
Client Contribution Normalization for Enhanced Federated Learning
Mayank Kumar Kundalwal, Anurag Saraswat, Ishan Mishra +1
Mobile devices, including smartphones and laptops, generate decentralized and heterogeneous data, presenting significant challenges for traditional centralized machine learning mod…