activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

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…

cs.LG2026

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…

cs.LG2026

Rethinking Calibration for Early-Exit Neural Networks

Piotr Kubaty, Filip Szatkowski, Grzegorz Choczyński +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…

cs.LG2024

On Calibration in Multi-Distribution Learning

Rajeev Verma, Volker Fischer, Eric Nalisnick

Modern challenges of robustness, fairness, and decision-making in machine learning have led to the formulation of multi-distribution learning (MDL) frameworks in which a predictor…

cs.LG2024

Learning to Defer to a Population: A Meta-Learning Approach

Dharmesh Tailor, Aditya Patra, Rajeev Verma +2

The learning to defer (L2D) framework allows autonomous systems to be safe and robust by allocating difficult decisions to a human expert. All existing work on L2D assumes that eac…