26 citations · 68 across the 41 of their papers we have counts for
Showing 2025 · cs.LGShow all
3 papers · 2 filters
cs.LG2025
Bi-directional Model Cascading with Proxy Confidence
David Warren, Mark Dras
Model Cascading, recently applied successfully to LLMs, is a simple but powerful technique that improves the efficiency of inference by selectively applying models of varying sizes…
cs.LG2025
Empirical Calibration and Metric Differential Privacy in Language Models
Pedro Faustini, Natasha Fernandes, Annabelle McIver +1
NLP models trained with differential privacy (DP) usually adopt the DP-SGD framework, and privacy guarantees are often reported in terms of the privacy budget . However, doe…
cs.LG2025
Comparing privacy notions for protection against reconstruction attacks in machine learning
Sayan Biswas, Mark Dras, Pedro Faustini +4
Within the machine learning community, reconstruction attacks are a principal concern and have been identified even in federated learning (FL), which was designed with privacy pres…