الباحثون

Pascal Poupart

المنشورات 2

نسخة أولية وصول مفتوح

Work While They Sleep: Exploiting Evaluation Latency for Fully Bayesian Optimization

Black-box optimization problems are ubiquitous across science and engineering, often dealing with expensive objective functions. This objective latency has two consequences during optimization: (i) the objective evaluation dominates execution time, and (ii) sample-efficient algorithms are crucial to accelerate developm …

نسخة أولية وصول مفتوح

Beyond Reference-Based Evaluation: Reward Models for Meta-Evaluation of Grammatical Error Correction

Ruotian Wu, Bill E. Johnson, Gene Saunders وآخرون · 2026

Reference-based metrics for Grammatical Error Correction (GEC) such as M$^2$ and ERRANT assume that the reference set enumerates all valid edits, and therefore often penalize corrections that are grammatical and meaning-preserving but phrased differently. We introduce RM-EVAL, a reward model trained on human preference …

المؤلفون المشاركون