7 papers
Re-evaluating Confidence Remasking in Masked Diffusion Language Models
Stipe Frkovic, Metod Jazbec, Dan Zhang +3
Masked diffusion language models (dLLMs) have recently emerged as a competitive alternative to autoregressive language models, with the promise of faster inference via parallel tok…
Human-AI Teaming Through the Lens of Calibration
Eric Nalisnick, Chi Zhang, Sophia Qian +1
We study models for human-AI teaming through the lens of statistical calibration. We assume the team consists of an AI model and human -- both of which are calibrated with respect…
Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement Learning
Ha Manh Bui, Metod Jazbec, Eric Nalisnick +1
Offline-to-Online Reinforcement Learning (O2O-RL) leverages an offline, pre-trained policy to minimize costly online interactions. Although data-efficient, O2O-RL is susceptible to…
Joint Model and Data Sparsification via the Marginal Likelihood
Alexander Timans, Thomas Möllenhoff, Christian A. Naesseth +2
Sparse recovery in linear systems underpins applications from signal processing to high-dimensional regression. Sparse Bayesian Learning, grounded in the principle of automatic rel…
Rethinking Calibration for Early-Exit Neural Networks
Piotr Kubaty, Filip Szatkowski, Grzegorz ChoczyÅski +2
Early-exit neural networks (EENNs) accelerate inference by allowing intermediate classifiers to stop computation once predictions are confident enough. Most methods rely on confide…
On Continuous Monitoring of Risk Violations under Unknown Shift
Alexander Timans, Rajeev Verma, Eric Nalisnick +1
Machine learning systems deployed in the real world must operate under dynamic and often unpredictable distribution shifts. This challenges the validity of statistical safety assur…