Galo Castillo-López
PhD student in NLP at Université Paris-Saclay 🇫🇷
PhD student in NLP at Université Paris-Saclay 🇫🇷
I am a doctoral researcher at Université Paris-Saclay, working at CEA under the supervision of Dr. Gaël de Chalendar and Dr. Nasredine Semmar. My research consists in modeling turn-taking management in spoken multi-party dialogue systems.
Previously, I interned at ALMAnaCH, the NLP group at Inria Paris, under the supervision of Dr. Djamé Seddah. We studied multi-lingual transfer scenarios using Transformers-based language models across Spanish variants for hate speech detection in social media.
I also worked as a data scientist at Claro, the largest Latin American telecommunications company, developing supervised models for optimizing internal operations at the Finance, Customer Service, and Marketing departments.
I obtained a master's degree in Artificial Intelligence at Université Paris-Saclay in France, and a bachelor's degree in Computer Science at Escuela Superior Politécnica del Litoral in Ecuador 🇪🇨.
Jan. 2026 - Our paper "How DDAIR you? Disambiguated Data Augmentation for Intent Recognition" was accepted at EACL 2025!
Jun. 2025 - New publication🎉 at SIGDIAL 2025: Intent Recognition and Out-of-Scope Detection using LLMs in Multi-party Conversations.
May. 2025 - New publication🎉 at IWSDS 2025: A Survey of Recent Advances on Turn-taking Modeling in Spoken Dialogue Systems.
Nov. 2024 - Presented our work at EuroXR 2024: CoVA, the Cortex² Virtual Assistant for Multiparty Conversations.
Jun. 2024 - New preprint available: Benchmarks Underestimate the Readiness of Multi-lingual Dialogue Agents.
Oct. 2023 - I have just started my PhD journey at CEA!