7 papers
MARS: Margin and Semantic-Aware Data Augmentation for Reward Modeling
Payel Bhattacharjee, Osvaldo Simeone, Ravi Tandon
Reward modeling is central to RLHF, RLAIF, and PPO-based alignment, but its reliability is often limited by scarce and heterogeneous human preference data. In this paper, we introd…
Prediction-Powered Risk Monitoring of Deployed Models for Detecting Harmful Distribution Shifts
Guangyi Zhang, Yunlong Cai, Guanding Yu +1
We study the problem of monitoring model performance in dynamic environments where labeled data are limited. To this end, we propose prediction-powered risk monitoring (PPRM), a se…
Communicating Properties of Quantum States over Classical Noisy Channels
Nikhitha Nunavath, Jiechen Chen, Osvaldo Simeone +2
Transmitting information about quantum states over classical noisy channels is an important problem with applications to science, computing, and sensing. This task, however, poses…
Anytime-Valid Quantum State Tomography via Confidence Sequences
Aldo Cumitini, Luca Barletta, Osvaldo Simeone
In this letter, we address the problem of developing quantum state tomography (QST) methods that remain valid at any time during a sequence of measurements. Specifically, the aim i…
Reliable Hierarchical Operating System Fingerprinting via Conformal Prediction
Rubén Pérez-Jove, Osvaldo Simeone, Alejandro Pazos +1
Operating System (OS) fingerprinting is critical for network security, but conventional methods do not provide formal uncertainty quantification mechanisms. Conformal Prediction (C…
Modern Neuromorphic AI: From Intra-Token to Inter-Token Processing
Osvaldo Simeone
The rapid growth of artificial intelligence (AI) has brought novel data processing and generative capabilities but also escalating energy requirements. This challenge motivates ren…