- Jan 2023: The End of Words? Language Modelling with Pixels at MIT
- Dec 2022: Ideals and Compromises in Multilingual Multimodal Learning at MMLow
- Dec 2022: The End of Words? Language Modelling with Pixels at KUIS AI
- Oct 2022: The End of Words? Language Modelling with Pixels at Peking University
- Sep 2022: The End of Words? Language Modelling with Pixels at Adobe Research
- Aug 2022: The End of Words? Language Modelling with Pixels at University of Edinburgh
- Mar 2022: Visually Grounded Reasoning across Languages and Cultures at University of Trento
- Mar 2022: Visually Grounded Reasoning across Languages and Cultures at HiTZ
- Nov 2021: Visually Grounded Reasoning across Languages and Cultures at FBK
- Apr 2021: Beyond Text and Back Again at the 2nd Workshop on NLP Beyond Text (NLPBT)
- Feb 2020: Compositional Generalization in Image Captioning at the University of Gothenburg
- Nov 2019: Multitask Learning from Multilingual Mutimodal Data at the 6th Workshop on Asian Translation (WAT)
- Oct 2019: Compositional Generalization in Image Captioning at the CLS Seminar, University of Amsterdam
- Sep 2019: Compositional Generalization in Image Captioning at the University of Edinburgh
- Jun 2019: Compositional Generalization in Image Captioning at Heriot-Watt University
- Jun 2019: Shortcomings in (some) Vision and Language Models at University of Helsinki
- Jan 2019: Learning from Multilingual Multimodal Data at Dagstuhl Seminar 19021
- Nov 2018: Multilingual Multimodal Language Understanding at Science AI Center, University of Copenhagen
- Jun 2018: Imagination improves Multimodal Translation at Amazon Research Berlin
- Dec 2017: Multilingual and Multimodal Natural Language Processing at UKP Lab, TU Darmstadt
- Feb 2016: Multilingual Image Description with Neural Sequence Models at University of Rijeka
- Jan 2016: Multilingual Image Description with Neural Sequence Models at Intelligent Systems Lab, University of Amsterdam
- Jul 2015: Describing Images using Inferred Visual Dependency Representations at LIIR, KU Leuven
- Mar 2015: Describing Images using Inferred Visual Dependency Representations at WILLOW Research Group, INRIA Paris