Karin Sevegnani — accepted AI-conference papers

2026

Evolution Strategies at the Hyperscale

Bidipta Sarkar, Mattie Fellows, Juan Duque, Alistair Letcher, Antonio León Villares, Anya Sims +14

ICML 2026poster

Evolution Strategies (ES) is a class of powerful black-box optimisation methods that are highly parallelisable and can handle non-differentiable and noisy objectives. However, naïve ES becomes prohibitively expensive at scale on GPUs due to the low arithmetic intensity of batched matrix multiplicati…

Cited by 0 Source ↗Scholar ↗

2021

OTTers: One-turn Topic Transitions for Open-Domain Dialogue

Karin Sevegnani, David M. Howcroft, Ioannis Konstas, Verena Rieser

ACL 2021long

Mixed initiative in open-domain dialogue requires a system to pro-actively introduce new topics. The one-turn topic transition task explores how a system connects two topics in a cooperative and coherent manner. The goal of the task is to generate a “bridging” utterance connecting the new topic to t…

Cited by 47 Source ↗PDF ↗code ↗Scholar ↗