collaborators

6 papers

cs.CL2026

Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models

Liran Ringel, Ameen Ali, Yaniv Romano

Discrete diffusion language models (dLLMs) accelerate text generation by unmasking multiple tokens in parallel. However, parallel decoding introduces a distributional mismatch: it…

cs.IT2026

Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective

Osvaldo Simeone, Yaniv Romano

In context-specific applications such as robotics, telecommunications, and healthcare, artificial intelligence systems often face the challenge of limited training data. This scarc…

cs.LG2026

Conformal Prediction with Corrupted Labels: Uncertain Imputation and Robust Re-weighting

Shai Feldman, Stephen Bates, Yaniv Romano

We introduce a framework for robust uncertainty quantification in situations where labeled training data are corrupted, through noisy or missing labels. We build on conformal predi…

cs.LG2026

Calibrated Predictive Lower Bounds on Time-to-Unsafe-Sampling in LLMs

Hen Davidov, Shai Feldman, Gilad Freidkin +1

We introduce time-to-unsafe-sampling, a novel safety measure for generative models, defined as the number of generations required by a large language model (LLM) to trigger an unsa…

cs.LG2025

Robust Conformal Prediction Using Privileged Information

Shai Feldman, Yaniv Romano

We develop a method to generate prediction sets with a guaranteed coverage rate that is robust to corruptions in the training data, such as missing or noisy variables. Our approach…

cs.LG2025

Protected Test-Time Adaptation via Online Entropy Matching: A Betting Approach

Yarin Bar, Shalev Shaer, Yaniv Romano

We present a novel approach for test-time adaptation via online self-training, consisting of two components. First, we introduce a statistical framework that detects distribution s…